Token | happy |
Token ID | 3772 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
helmets | +0.127 |
ates | +0.120 |
numbers | +0.119 |
skills | +0.117 |
himself | +0.109 |
Neg logit contributions | |
bug | -0.123 |
chick | -0.122 |
shower | -0.118 |
heaven | -0.112 |
Lilly | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
chick | +0.017 |
bug | +0.017 |
shower | +0.016 |
Lilly | +0.015 |
lyss | +0.015 |
Neg logit contributions | |
helmets | -0.016 |
skills | -0.015 |
numbers | -0.015 |
ates | -0.015 |
himself | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
helmets | +0.014 |
numbers | +0.013 |
skills | +0.013 |
ates | +0.013 |
himself | +0.013 |
Neg logit contributions | |
chick | -0.019 |
bug | -0.019 |
shower | -0.019 |
Lilly | -0.018 |
heaven | -0.018 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
helmets | +0.222 |
numbers | +0.209 |
skills | +0.209 |
ates | +0.207 |
himself | +0.202 |
Neg logit contributions | |
chick | -0.231 |
bug | -0.225 |
shower | -0.224 |
heaven | -0.206 |
Lilly | -0.206 |
Token | that |
Token ID | 326 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
helmets | +0.189 |
ates | +0.178 |
numbers | +0.178 |
skills | +0.178 |
himself | +0.172 |
Neg logit contributions | |
chick | -0.186 |
bug | -0.182 |
shower | -0.180 |
Lilly | -0.166 |
heaven | -0.166 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
chick | +0.346 |
shower | +0.343 |
bug | +0.336 |
Lilly | +0.320 |
heaven | +0.319 |
Neg logit contributions | |
helmets | -0.276 |
ates | -0.269 |
bled | -0.254 |
numbers | -0.251 |
skills | -0.245 |
Token | could |
Token ID | 714 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
helmets | +0.786 |
numbers | +0.741 |
ates | +0.740 |
skills | +0.739 |
himself | +0.717 |
Neg logit contributions | |
chick | -0.713 |
bug | -0.700 |
shower | -0.689 |
Lilly | -0.634 |
heaven | -0.633 |
Token | make |
Token ID | 787 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
bug | +0.098 |
shower | +0.097 |
chick | +0.094 |
die | +0.092 |
bloom | +0.089 |
Neg logit contributions | |
ates | -0.149 |
helmets | -0.149 |
bled | -0.140 |
skills | -0.139 |
numbers | -0.136 |
Token | things |
Token ID | 1243 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
chick | +0.064 |
bug | +0.063 |
shower | +0.062 |
heaven | +0.059 |
Lilly | +0.059 |
Neg logit contributions | |
helmets | -0.047 |
ates | -0.044 |
skills | -0.043 |
numbers | -0.043 |
himself | -0.041 |
Token | so |
Token ID | 523 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
helmets | +0.444 |
numbers | +0.421 |
skills | +0.420 |
ates | +0.417 |
himself | +0.408 |
Neg logit contributions | |
chick | -0.374 |
bug | -0.366 |
shower | -0.359 |
Lilly | -0.330 |
heaven | -0.330 |
Token | special |
Token ID | 2041 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
shower | +0.340 |
chick | +0.336 |
bug | +0.335 |
Lilly | +0.325 |
die | +0.320 |
Neg logit contributions | |
ates | -0.336 |
helmets | -0.330 |
skills | -0.303 |
bled | -0.297 |
numbers | -0.296 |
Token | gift |
Token ID | 6979 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
chick | +0.160 |
bug | +0.158 |
shower | +0.154 |
Lilly | +0.143 |
heaven | +0.142 |
Neg logit contributions | |
helmets | -0.171 |
numbers | -0.161 |
skills | -0.161 |
ates | -0.160 |
himself | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
chick | +0.251 |
bug | +0.246 |
shower | +0.242 |
lyss | +0.238 |
die | +0.232 |
Neg logit contributions | |
helmets | -0.166 |
skills | -0.161 |
numbers | -0.161 |
ates | -0.157 |
himself | -0.156 |
Token | she |
Token ID | 673 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
helmets | +0.038 |
numbers | +0.036 |
skills | +0.035 |
ates | +0.035 |
himself | +0.034 |
Neg logit contributions | |
chick | -0.047 |
bug | -0.046 |
shower | -0.046 |
die | -0.042 |
lyss | -0.042 |
Token | could |
Token ID | 714 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
chick | +0.058 |
shower | +0.057 |
bug | +0.056 |
die | +0.052 |
heaven | +0.052 |
Neg logit contributions | |
helmets | -0.051 |
skills | -0.048 |
numbers | -0.048 |
ates | -0.047 |
himself | -0.047 |
Token | add |
Token ID | 751 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
chick | +0.129 |
bug | +0.122 |
shower | +0.119 |
lamb | +0.115 |
lyss | +0.114 |
Neg logit contributions | |
helmets | -0.142 |
himself | -0.139 |
skills | -0.138 |
numbers | -0.136 |
ates | -0.132 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
helmets | +0.026 |
numbers | +0.024 |
skills | +0.024 |
ates | +0.024 |
himself | +0.023 |
Neg logit contributions | |
chick | -0.037 |
bug | -0.036 |
shower | -0.036 |
Lilly | -0.033 |
heaven | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
helmets | +0.729 |
ates | +0.681 |
skills | +0.677 |
numbers | +0.673 |
himself | +0.655 |
Neg logit contributions | |
bug | -0.764 |
chick | -0.763 |
shower | -0.741 |
Lilly | -0.690 |
heaven | -0.687 |
Token | her |
Token ID | 607 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
chick | +0.021 |
bug | +0.020 |
shower | +0.020 |
heaven | +0.019 |
Lilly | +0.019 |
Neg logit contributions | |
helmets | -0.018 |
ates | -0.017 |
skills | -0.017 |
numbers | -0.017 |
himself | -0.016 |
Token | head |
Token ID | 1182 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
chick | +0.004 |
bug | +0.003 |
shower | +0.003 |
Lilly | +0.003 |
heaven | +0.003 |
Neg logit contributions | |
helmets | -0.003 |
numbers | -0.003 |
skills | -0.003 |
ates | -0.003 |
himself | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
helmets | +0.216 |
numbers | +0.204 |
skills | +0.203 |
ates | +0.203 |
himself | +0.197 |
Neg logit contributions | |
chick | -0.239 |
bug | -0.234 |
shower | -0.231 |
heaven | -0.214 |
Lilly | -0.214 |
Token | She |
Token ID | 1375 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
chick | +0.020 |
shower | +0.019 |
bug | +0.019 |
die | +0.019 |
lamb | +0.018 |
Neg logit contributions | |
helmets | -0.016 |
himself | -0.016 |
numbers | -0.016 |
ates | -0.015 |
skills | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
chick | +0.045 |
bug | +0.044 |
shower | +0.043 |
lyss | +0.042 |
heaven | +0.041 |
Neg logit contributions | |
helmets | -0.035 |
numbers | -0.033 |
skills | -0.033 |
ates | -0.032 |
himself | -0.032 |
Token | There |
Token ID | 1318 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
helmets | +0.001 |
numbers | +0.001 |
himself | +0.001 |
ates | +0.001 |
skills | +0.001 |
Neg logit contributions | |
chick | -0.001 |
shower | -0.001 |
bug | -0.001 |
die | -0.001 |
lamb | -0.001 |
Token | were |
Token ID | 547 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
chick | +0.214 |
bug | +0.210 |
shower | +0.207 |
Lilly | +0.192 |
heaven | +0.191 |
Neg logit contributions | |
helmets | -0.199 |
numbers | -0.187 |
skills | -0.186 |
ates | -0.186 |
himself | -0.180 |
Token | five |
Token ID | 1936 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
chick | +0.134 |
bug | +0.132 |
shower | +0.131 |
Lilly | +0.123 |
heaven | +0.123 |
Neg logit contributions | |
helmets | -0.069 |
numbers | -0.063 |
skills | -0.063 |
ates | -0.063 |
himself | -0.060 |
Token | little |
Token ID | 1310 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
helmets | +0.422 |
ates | +0.409 |
skills | +0.393 |
himself | +0.389 |
bled | +0.386 |
Neg logit contributions | |
bug | -0.541 |
chick | -0.538 |
shower | -0.515 |
sip | -0.478 |
lamb | -0.478 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
chick | +0.321 |
bug | +0.315 |
shower | +0.314 |
Lilly | +0.294 |
die | +0.294 |
Neg logit contributions | |
helmets | -0.247 |
numbers | -0.236 |
skills | -0.229 |
ates | -0.225 |
himself | -0.220 |
Token | on |
Token ID | 319 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
helmets | +0.730 |
ates | +0.688 |
skills | +0.683 |
numbers | +0.674 |
himself | +0.658 |
Neg logit contributions | |
bug | -0.762 |
chick | -0.761 |
shower | -0.741 |
Lilly | -0.683 |
die | -0.676 |
Token | the |
Token ID | 262 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
helmets | +0.417 |
ates | +0.416 |
bled | +0.390 |
skills | +0.390 |
hardest | +0.389 |
Neg logit contributions | |
chick | -0.422 |
shower | -0.408 |
bug | -0.405 |
Lilly | -0.387 |
Nina | -0.379 |
Token | square |
Token ID | 6616 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
helmets | +0.035 |
ates | +0.034 |
skills | +0.033 |
numbers | +0.032 |
himself | +0.032 |
Neg logit contributions | |
chick | -0.039 |
shower | -0.039 |
bug | -0.038 |
heaven | -0.035 |
Lilly | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
chick | +0.025 |
bug | +0.024 |
shower | +0.024 |
Lilly | +0.023 |
lamb | +0.023 |
Neg logit contributions | |
helmets | -0.022 |
skills | -0.021 |
numbers | -0.021 |
ates | -0.020 |
himself | -0.020 |
Token | Jack |
Token ID | 3619 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
chick | +0.007 |
shower | +0.007 |
bug | +0.007 |
die | +0.007 |
lamb | +0.007 |
Neg logit contributions | |
helmets | -0.007 |
numbers | -0.007 |
ates | -0.006 |
himself | -0.006 |
skills | -0.006 |
Token | ding |
Token ID | 44852 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
chick | +0.057 |
bug | +0.056 |
shower | +0.056 |
Lilly | +0.051 |
heaven | +0.051 |
Neg logit contributions | |
helmets | -0.057 |
ates | -0.053 |
skills | -0.053 |
numbers | -0.053 |
himself | -0.051 |
Token | sounds |
Token ID | 5238 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
chick | +0.052 |
bug | +0.051 |
shower | +0.051 |
Lilly | +0.047 |
heaven | +0.047 |
Neg logit contributions | |
helmets | -0.052 |
numbers | -0.049 |
skills | -0.049 |
ates | -0.049 |
himself | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
helmets | +0.106 |
numbers | +0.099 |
hard | +0.097 |
himself | +0.095 |
skills | +0.094 |
Neg logit contributions | |
chick | -0.171 |
bug | -0.167 |
lyss | -0.160 |
shower | -0.157 |
lamb | -0.156 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
helmets | +0.041 |
numbers | +0.039 |
skills | +0.038 |
himself | +0.038 |
ates | +0.037 |
Neg logit contributions | |
chick | -0.037 |
bug | -0.037 |
shower | -0.035 |
Lilly | -0.033 |
lyss | -0.033 |
Token | five |
Token ID | 1936 |
Feature activation | +7.78e+00 |
Pos logit contributions | |
helmets | +0.104 |
numbers | +0.099 |
skills | +0.098 |
himself | +0.096 |
ates | +0.095 |
Neg logit contributions | |
chick | -0.129 |
bug | -0.126 |
shower | -0.126 |
lyss | -0.118 |
heaven | -0.116 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
helmets | +0.435 |
ates | +0.421 |
bled | +0.412 |
himself | +0.407 |
skills | +0.399 |
Neg logit contributions | |
chick | -0.502 |
bug | -0.497 |
shower | -0.494 |
heaven | -0.452 |
sip | -0.448 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
helmets | +0.744 |
ates | +0.707 |
skills | +0.695 |
numbers | +0.684 |
himself | +0.679 |
Neg logit contributions | |
bug | -0.731 |
chick | -0.725 |
shower | -0.715 |
heaven | -0.651 |
die | -0.646 |
Token |
|
Token ID | 198 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
chick | +0.015 |
bug | +0.014 |
shower | +0.014 |
heaven | +0.013 |
Lilly | +0.013 |
Neg logit contributions | |
helmets | -0.016 |
numbers | -0.015 |
skills | -0.015 |
ates | -0.015 |
himself | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
bug | +0.044 |
chick | +0.042 |
shower | +0.042 |
Lilly | +0.041 |
heaven | +0.039 |
Neg logit contributions | |
helmets | -0.059 |
skills | -0.055 |
ates | -0.055 |
hardest | -0.055 |
numbers | -0.054 |
Token | " |
Token ID | 1 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
bug | +0.056 |
chick | +0.055 |
shower | +0.053 |
heaven | +0.051 |
Lilly | +0.051 |
Neg logit contributions | |
helmets | -0.050 |
skills | -0.048 |
ates | -0.047 |
numbers | -0.047 |
hardest | -0.046 |
Token | It |
Token ID | 1026 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
helmets | +0.282 |
skills | +0.267 |
ates | +0.266 |
numbers | +0.264 |
himself | +0.257 |
Neg logit contributions | |
chick | -0.266 |
bug | -0.263 |
shower | -0.257 |
Lilly | -0.237 |
heaven | -0.236 |
Token | already |
Token ID | 1541 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
chick | +0.038 |
bug | +0.038 |
shower | +0.037 |
Lilly | +0.034 |
heaven | +0.034 |
Neg logit contributions | |
helmets | -0.036 |
numbers | -0.034 |
ates | -0.034 |
skills | -0.034 |
himself | -0.033 |
Token | had |
Token ID | 550 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
helmets | +0.051 |
numbers | +0.049 |
skills | +0.048 |
ates | +0.047 |
himself | +0.047 |
Neg logit contributions | |
chick | -0.059 |
shower | -0.057 |
bug | -0.056 |
die | -0.052 |
lamb | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
helmets | +0.097 |
ates | +0.094 |
skills | +0.090 |
numbers | +0.089 |
himself | +0.087 |
Neg logit contributions | |
chick | -0.139 |
bug | -0.137 |
shower | -0.135 |
heaven | -0.129 |
Lilly | -0.127 |
Token | knack |
Token ID | 47868 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
helmets | +0.105 |
numbers | +0.099 |
skills | +0.099 |
hard | +0.094 |
ates | +0.093 |
Neg logit contributions | |
bug | -0.127 |
chick | -0.126 |
shower | -0.122 |
Lilly | -0.116 |
heaven | -0.115 |
Token | for |
Token ID | 329 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
helmets | +0.180 |
ates | +0.168 |
skills | +0.168 |
numbers | +0.168 |
himself | +0.160 |
Neg logit contributions | |
chick | -0.194 |
bug | -0.193 |
shower | -0.190 |
Lilly | -0.177 |
heaven | -0.177 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
helmets | +0.195 |
ates | +0.183 |
skills | +0.181 |
numbers | +0.179 |
himself | +0.173 |
Neg logit contributions | |
chick | -0.223 |
shower | -0.218 |
bug | -0.218 |
heaven | -0.204 |
Lilly | -0.204 |
Token | and |
Token ID | 290 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
helmets | +0.724 |
ates | +0.678 |
numbers | +0.678 |
skills | +0.677 |
himself | +0.656 |
Neg logit contributions | |
chick | -0.763 |
bug | -0.753 |
shower | -0.740 |
Lilly | -0.687 |
heaven | -0.685 |
Token | patterns |
Token ID | 7572 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ates | +0.026 |
helmets | +0.026 |
bled | +0.025 |
bles | +0.023 |
skills | +0.023 |
Neg logit contributions | |
bug | -0.057 |
chick | -0.056 |
shower | -0.055 |
Lilly | -0.054 |
Nina | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -7.98e-02 |
Pos logit contributions | |
helmets | +0.098 |
numbers | +0.092 |
skills | +0.092 |
ates | +0.092 |
himself | +0.089 |
Neg logit contributions | |
chick | -0.106 |
bug | -0.105 |
shower | -0.103 |
Lilly | -0.096 |
heaven | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
chick | +0.006 |
shower | +0.006 |
bug | +0.005 |
die | +0.005 |
sip | +0.005 |
Neg logit contributions | |
helmets | -0.004 |
numbers | -0.004 |
himself | -0.004 |
ates | -0.004 |
skills | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
bug | +0.041 |
chick | +0.041 |
shower | +0.039 |
Lilly | +0.037 |
heaven | +0.037 |
Neg logit contributions | |
helmets | -0.045 |
numbers | -0.042 |
skills | -0.042 |
ates | -0.042 |
hardest | -0.040 |
Token | word |
Token ID | 1573 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
helmets | +0.132 |
hard | +0.129 |
numbers | +0.127 |
skills | +0.121 |
hardest | +0.114 |
Neg logit contributions | |
bug | -0.149 |
chick | -0.142 |
shower | -0.137 |
die | -0.136 |
ount | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
helmets | +0.276 |
numbers | +0.275 |
skills | +0.261 |
ates | +0.253 |
himself | +0.248 |
Neg logit contributions | |
chick | -0.347 |
shower | -0.334 |
bug | -0.331 |
Lilly | -0.324 |
Nina | -0.319 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
helmets | +0.008 |
numbers | +0.008 |
ates | +0.008 |
skills | +0.008 |
himself | +0.008 |
Neg logit contributions | |
chick | -0.009 |
shower | -0.008 |
bug | -0.008 |
die | -0.008 |
lamb | -0.008 |
Token | knew |
Token ID | 2993 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
chick | +0.121 |
bug | +0.119 |
shower | +0.117 |
Lilly | +0.109 |
heaven | +0.108 |
Neg logit contributions | |
helmets | -0.114 |
numbers | -0.107 |
skills | -0.107 |
ates | -0.107 |
himself | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
chick | +0.032 |
bug | +0.031 |
shower | +0.031 |
Lilly | +0.028 |
heaven | +0.028 |
Neg logit contributions | |
helmets | -0.042 |
numbers | -0.040 |
skills | -0.040 |
ates | -0.040 |
himself | -0.039 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
helmets | +0.029 |
ates | +0.027 |
bled | +0.027 |
himself | +0.026 |
bles | +0.025 |
Neg logit contributions | |
chick | -0.039 |
shower | -0.038 |
bug | -0.038 |
die | -0.035 |
heaven | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
helmets | +0.769 |
numbers | +0.735 |
skills | +0.729 |
ates | +0.713 |
himself | +0.701 |
Neg logit contributions | |
chick | -0.725 |
bug | -0.700 |
shower | -0.696 |
Lilly | -0.644 |
heaven | -0.643 |
Token | the |
Token ID | 262 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
helmets | +0.030 |
ates | +0.029 |
skills | +0.028 |
numbers | +0.028 |
himself | +0.027 |
Neg logit contributions | |
chick | -0.031 |
bug | -0.031 |
shower | -0.030 |
Lilly | -0.028 |
heaven | -0.028 |
Token | word |
Token ID | 1573 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
helmets | +0.019 |
bled | +0.019 |
ates | +0.019 |
himself | +0.018 |
skills | +0.017 |
Neg logit contributions | |
chick | -0.028 |
shower | -0.027 |
bug | -0.027 |
heaven | -0.025 |
lamb | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
helmets | +0.284 |
numbers | +0.272 |
skills | +0.268 |
ates | +0.264 |
himself | +0.258 |
Neg logit contributions | |
chick | -0.284 |
bug | -0.276 |
shower | -0.274 |
heaven | -0.254 |
Lilly | -0.254 |
Token | She |
Token ID | 1375 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
chick | +0.020 |
shower | +0.019 |
bug | +0.019 |
die | +0.018 |
lamb | +0.018 |
Neg logit contributions | |
helmets | -0.024 |
numbers | -0.024 |
skills | -0.023 |
ates | -0.023 |
himself | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
chick | +0.004 |
bug | +0.004 |
shower | +0.004 |
die | +0.003 |
heaven | +0.003 |
Neg logit contributions | |
helmets | -0.003 |
numbers | -0.003 |
skills | -0.003 |
ates | -0.003 |
himself | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
bug | +0.039 |
chick | +0.038 |
shower | +0.038 |
Lilly | +0.036 |
Nina | +0.035 |
Neg logit contributions | |
helmets | -0.047 |
numbers | -0.045 |
skills | -0.045 |
ates | -0.044 |
hardest | -0.044 |
Token | Billy |
Token ID | 49640 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
bug | +0.048 |
chick | +0.047 |
shower | +0.046 |
lyss | +0.044 |
Lilly | +0.044 |
Neg logit contributions | |
helmets | -0.038 |
skills | -0.037 |
numbers | -0.036 |
ates | -0.036 |
hardest | -0.034 |
Token | watched |
Token ID | 7342 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
helmets | +0.162 |
ates | +0.156 |
skills | +0.153 |
numbers | +0.151 |
himself | +0.145 |
Neg logit contributions | |
bug | -0.137 |
chick | -0.133 |
shower | -0.126 |
Lilly | -0.119 |
lyss | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
chick | +0.021 |
shower | +0.020 |
bug | +0.020 |
Lilly | +0.019 |
heaven | +0.019 |
Neg logit contributions | |
helmets | -0.020 |
ates | -0.019 |
numbers | -0.019 |
skills | -0.019 |
hardest | -0.018 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
helmets | +0.037 |
ates | +0.036 |
skills | +0.035 |
numbers | +0.035 |
himself | +0.034 |
Neg logit contributions | |
chick | -0.043 |
shower | -0.043 |
bug | -0.042 |
lyss | -0.039 |
lamb | -0.039 |
Token | change |
Token ID | 1487 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
ates | +0.717 |
helmets | +0.713 |
skills | +0.667 |
numbers | +0.652 |
bled | +0.639 |
Neg logit contributions | |
bug | -0.744 |
shower | -0.741 |
chick | -0.713 |
sip | -0.664 |
bloom | -0.658 |
Token | as |
Token ID | 355 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
chick | +0.321 |
bug | +0.316 |
shower | +0.315 |
Lilly | +0.296 |
Nina | +0.292 |
Neg logit contributions | |
helmets | -0.298 |
ates | -0.286 |
skills | -0.271 |
numbers | -0.271 |
bled | -0.268 |
Token | the |
Token ID | 262 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
chick | +0.133 |
Lilly | +0.131 |
Nina | +0.129 |
bug | +0.128 |
shower | +0.127 |
Neg logit contributions | |
ates | -0.140 |
helmets | -0.129 |
skills | -0.128 |
icycle | -0.126 |
hardest | -0.120 |
Token | elevator |
Token ID | 20932 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ates | +0.032 |
helmets | +0.031 |
bled | +0.030 |
himself | +0.029 |
skills | +0.029 |
Neg logit contributions | |
shower | -0.045 |
chick | -0.044 |
bug | -0.042 |
lamb | -0.040 |
lyss | -0.039 |
Token | moved |
Token ID | 3888 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
helmets | +0.217 |
ates | +0.204 |
numbers | +0.204 |
skills | +0.203 |
himself | +0.197 |
Neg logit contributions | |
chick | -0.213 |
bug | -0.210 |
shower | -0.207 |
Lilly | -0.191 |
heaven | -0.190 |
Token | carefully |
Token ID | 7773 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
helmets | +0.223 |
ates | +0.214 |
numbers | +0.198 |
skills | +0.197 |
himself | +0.196 |
Neg logit contributions | |
bug | -0.228 |
shower | -0.216 |
chick | -0.215 |
Lilly | -0.205 |
bloom | -0.199 |
Token | and |
Token ID | 290 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
helmets | +0.294 |
ates | +0.276 |
bled | +0.260 |
skills | +0.260 |
numbers | +0.255 |
Neg logit contributions | |
bug | -0.246 |
chick | -0.234 |
shower | -0.234 |
bloom | -0.220 |
Lilly | -0.218 |
Token | wrote |
Token ID | 2630 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
helmets | +0.038 |
ates | +0.037 |
skills | +0.035 |
numbers | +0.034 |
himself | +0.033 |
Neg logit contributions | |
bug | -0.034 |
chick | -0.032 |
shower | -0.031 |
Lilly | -0.031 |
Nina | -0.030 |
Token | down |
Token ID | 866 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
helmets | +0.126 |
ates | +0.124 |
icycle | +0.121 |
hardest | +0.114 |
skills | +0.113 |
Neg logit contributions | |
Lilly | -0.120 |
bug | -0.120 |
shower | -0.118 |
Nina | -0.118 |
chick | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
helmets | +0.201 |
ates | +0.197 |
skills | +0.184 |
bled | +0.182 |
himself | +0.182 |
Neg logit contributions | |
chick | -0.255 |
shower | -0.253 |
bug | -0.251 |
Lilly | -0.238 |
heaven | -0.237 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
ates | +0.016 |
helmets | +0.016 |
bled | +0.015 |
himself | +0.015 |
bles | +0.014 |
Neg logit contributions | |
shower | -0.020 |
chick | -0.019 |
bug | -0.019 |
sip | -0.018 |
Lilly | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
helmets | +0.720 |
ates | +0.679 |
skills | +0.665 |
numbers | +0.661 |
himself | +0.650 |
Neg logit contributions | |
bug | -0.765 |
chick | -0.761 |
shower | -0.745 |
Lilly | -0.688 |
heaven | -0.682 |
Token | |
Token ID | 220 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
chick | +0.009 |
bug | +0.009 |
shower | +0.009 |
die | +0.008 |
heaven | +0.008 |
Neg logit contributions | |
helmets | -0.008 |
numbers | -0.008 |
skills | -0.008 |
ates | -0.008 |
himself | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
helmets | +0.143 |
skills | +0.132 |
numbers | +0.131 |
ates | +0.128 |
hardest | +0.126 |
Neg logit contributions | |
bug | -0.114 |
shower | -0.109 |
chick | -0.109 |
Lilly | -0.107 |
Nina | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
bug | +0.036 |
chick | +0.035 |
shower | +0.035 |
Lilly | +0.034 |
Nina | +0.033 |
Neg logit contributions | |
helmets | -0.043 |
skills | -0.040 |
numbers | -0.039 |
ates | -0.039 |
hardest | -0.038 |
Token | After |
Token ID | 3260 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
chick | +0.043 |
bug | +0.043 |
shower | +0.042 |
Lilly | +0.039 |
heaven | +0.039 |
Neg logit contributions | |
helmets | -0.037 |
numbers | -0.034 |
skills | -0.034 |
ates | -0.034 |
himself | -0.033 |
Token | Molly |
Token ID | 30236 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
helmets | +0.055 |
ates | +0.054 |
numbers | +0.052 |
skills | +0.052 |
bled | +0.050 |
Neg logit contributions | |
chick | -0.030 |
bug | -0.030 |
shower | -0.029 |
Lilly | -0.028 |
Nina | -0.026 |
Token | each |
Token ID | 1123 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
chick | +0.446 |
shower | +0.434 |
bug | +0.432 |
heaven | +0.404 |
Lilly | +0.401 |
Neg logit contributions | |
helmets | -0.377 |
numbers | -0.353 |
skills | -0.350 |
ates | -0.349 |
himself | -0.340 |
Token | had |
Token ID | 550 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
chick | +0.068 |
bug | +0.068 |
shower | +0.065 |
Lilly | +0.061 |
lamb | +0.061 |
Neg logit contributions | |
helmets | -0.068 |
numbers | -0.064 |
ates | -0.063 |
skills | -0.063 |
himself | -0.059 |
Token | two |
Token ID | 734 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
helmets | +0.080 |
numbers | +0.073 |
skills | +0.072 |
ates | +0.071 |
himself | +0.069 |
Neg logit contributions | |
chick | -0.142 |
bug | -0.140 |
shower | -0.138 |
Lilly | -0.130 |
heaven | -0.130 |
Token | special |
Token ID | 2041 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
helmets | +0.321 |
ates | +0.296 |
numbers | +0.294 |
skills | +0.294 |
himself | +0.282 |
Neg logit contributions | |
chick | -0.682 |
bug | -0.672 |
shower | -0.664 |
heaven | -0.625 |
Lilly | -0.623 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
chick | +0.235 |
shower | +0.233 |
bug | +0.225 |
lamb | +0.215 |
heaven | +0.212 |
Neg logit contributions | |
ates | -0.132 |
bled | -0.130 |
helmets | -0.130 |
himself | -0.127 |
bles | -0.123 |
Token | which |
Token ID | 543 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
helmets | +0.767 |
ates | +0.722 |
numbers | +0.722 |
skills | +0.720 |
himself | +0.701 |
Neg logit contributions | |
chick | -0.713 |
bug | -0.705 |
shower | -0.690 |
heaven | -0.634 |
Lilly | -0.632 |
Token | were |
Token ID | 547 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
bug | +0.188 |
chick | +0.185 |
shower | +0.181 |
Lilly | +0.167 |
bloom | +0.165 |
Neg logit contributions | |
helmets | -0.196 |
ates | -0.189 |
bled | -0.180 |
himself | -0.179 |
skills | -0.175 |
Token | the |
Token ID | 262 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
bug | +0.099 |
chick | +0.094 |
shower | +0.088 |
Lilly | +0.086 |
bloom | +0.085 |
Neg logit contributions | |
helmets | -0.096 |
ates | -0.096 |
bled | -0.091 |
skills | -0.090 |
himself | -0.089 |
Token | same |
Token ID | 976 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
helmets | +0.024 |
ates | +0.022 |
bled | +0.022 |
skills | +0.021 |
himself | +0.021 |
Neg logit contributions | |
chick | -0.050 |
bug | -0.049 |
shower | -0.049 |
lamb | -0.046 |
heaven | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
helmets | +0.190 |
ates | +0.180 |
skills | +0.173 |
numbers | +0.172 |
himself | +0.171 |
Neg logit contributions | |
chick | -0.225 |
bug | -0.222 |
shower | -0.220 |
heaven | -0.204 |
Lilly | -0.201 |
Token | he |
Token ID | 339 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
helmets | +0.039 |
ates | +0.038 |
skills | +0.036 |
numbers | +0.035 |
bled | +0.033 |
Neg logit contributions | |
bug | -0.059 |
shower | -0.059 |
chick | -0.059 |
Lilly | -0.058 |
Nina | -0.056 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
helmets | +0.202 |
ates | +0.192 |
numbers | +0.189 |
skills | +0.189 |
himself | +0.183 |
Neg logit contributions | |
bug | -0.182 |
chick | -0.180 |
shower | -0.174 |
Lilly | -0.162 |
lyss | -0.160 |
Token | strange |
Token ID | 6283 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
chick | +0.047 |
bug | +0.046 |
shower | +0.045 |
Lilly | +0.042 |
heaven | +0.042 |
Neg logit contributions | |
helmets | -0.048 |
ates | -0.045 |
skills | -0.045 |
numbers | -0.045 |
himself | -0.043 |
Token | symbols |
Token ID | 14354 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
chick | +0.388 |
bug | +0.382 |
shower | +0.374 |
Lilly | +0.355 |
heaven | +0.355 |
Neg logit contributions | |
helmets | -0.202 |
numbers | -0.191 |
skills | -0.188 |
ates | -0.179 |
himself | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
helmets | +0.321 |
numbers | +0.305 |
skills | +0.301 |
ates | +0.296 |
himself | +0.292 |
Neg logit contributions | |
chick | -0.384 |
bug | -0.371 |
shower | -0.370 |
Lilly | -0.347 |
heaven | -0.346 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
helmets | +0.040 |
ates | +0.039 |
skills | +0.038 |
numbers | +0.037 |
himself | +0.036 |
Neg logit contributions | |
bug | -0.043 |
chick | -0.043 |
shower | -0.042 |
Lilly | -0.040 |
Nina | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
helmets | +0.732 |
ates | +0.691 |
skills | +0.684 |
numbers | +0.679 |
himself | +0.659 |
Neg logit contributions | |
chick | -0.738 |
bug | -0.736 |
shower | -0.717 |
Lilly | -0.664 |
die | -0.662 |
Token | he |
Token ID | 339 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
chick | +0.355 |
bug | +0.353 |
shower | +0.346 |
Lilly | +0.327 |
die | +0.320 |
Neg logit contributions | |
helmets | -0.317 |
ates | -0.300 |
skills | -0.292 |
numbers | -0.291 |
himself | -0.281 |
Token | didn |
Token ID | 1422 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
helmets | +0.210 |
ates | +0.200 |
skills | +0.194 |
numbers | +0.193 |
himself | +0.188 |
Neg logit contributions | |
bug | -0.173 |
chick | -0.168 |
shower | -0.157 |
Lilly | -0.151 |
lyss | -0.149 |
Token | 't |
Token ID | 470 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
helmets | +0.049 |
ates | +0.045 |
skills | +0.043 |
numbers | +0.043 |
hardest | +0.041 |
Neg logit contributions | |
shower | -0.043 |
bug | -0.043 |
chick | -0.041 |
die | -0.040 |
Lilly | -0.040 |
Token | understand |
Token ID | 1833 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
helmets | +0.329 |
numbers | +0.322 |
himself | +0.317 |
skills | +0.317 |
ates | +0.307 |
Neg logit contributions | |
chick | -0.251 |
bug | -0.237 |
shower | -0.234 |
lamb | -0.215 |
heaven | -0.212 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
chick | +0.317 |
bug | +0.313 |
shower | +0.296 |
lyss | +0.290 |
lamb | +0.283 |
Neg logit contributions | |
helmets | -0.232 |
numbers | -0.217 |
skills | -0.214 |
himself | -0.211 |
ates | -0.202 |
Token | door |
Token ID | 3420 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
helmets | +0.041 |
numbers | +0.040 |
skills | +0.039 |
hard | +0.037 |
top | +0.035 |
Neg logit contributions | |
bug | -0.038 |
chick | -0.036 |
lyss | -0.036 |
Lilly | -0.035 |
Nina | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
helmets | +0.040 |
numbers | +0.038 |
skills | +0.038 |
himself | +0.036 |
hard | +0.036 |
Neg logit contributions | |
chick | -0.062 |
bug | -0.059 |
shower | -0.058 |
lyss | -0.057 |
lamb | -0.056 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
helmets | +0.031 |
himself | +0.028 |
numbers | +0.028 |
skills | +0.027 |
hard | +0.027 |
Neg logit contributions | |
chick | -0.032 |
shower | -0.030 |
bug | -0.030 |
lyss | -0.028 |
lamb | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
chick | +0.049 |
bug | +0.048 |
shower | +0.047 |
lyss | +0.045 |
heaven | +0.044 |
Neg logit contributions | |
helmets | -0.035 |
numbers | -0.034 |
himself | -0.033 |
skills | -0.032 |
ates | -0.031 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
helmets | +0.022 |
numbers | +0.022 |
skills | +0.021 |
ates | +0.021 |
himself | +0.020 |
Neg logit contributions | |
bug | -0.021 |
chick | -0.021 |
shower | -0.020 |
Lilly | -0.019 |
lyss | -0.019 |
Token | going |
Token ID | 1016 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
helmets | +0.593 |
numbers | +0.549 |
ates | +0.548 |
skills | +0.548 |
himself | +0.526 |
Neg logit contributions | |
chick | -0.885 |
bug | -0.873 |
shower | -0.862 |
Lilly | -0.807 |
heaven | -0.806 |
Token | up |
Token ID | 510 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
ates | +0.109 |
helmets | +0.109 |
skills | +0.103 |
numbers | +0.103 |
himself | +0.100 |
Neg logit contributions | |
shower | -0.103 |
bug | -0.103 |
chick | -0.102 |
Lilly | -0.096 |
Nina | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
helmets | +0.315 |
ates | +0.302 |
numbers | +0.294 |
skills | +0.291 |
himself | +0.283 |
Neg logit contributions | |
chick | -0.297 |
bug | -0.297 |
shower | -0.291 |
Lilly | -0.271 |
heaven | -0.269 |
Token | up |
Token ID | 510 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
helmets | +0.021 |
ates | +0.020 |
numbers | +0.020 |
skills | +0.020 |
himself | +0.019 |
Neg logit contributions | |
chick | -0.028 |
bug | -0.028 |
shower | -0.028 |
Lilly | -0.026 |
heaven | -0.026 |
Token | ! |
Token ID | 0 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
helmets | +0.312 |
ates | +0.300 |
skills | +0.290 |
numbers | +0.290 |
himself | +0.281 |
Neg logit contributions | |
bug | -0.291 |
chick | -0.291 |
shower | -0.287 |
Lilly | -0.267 |
heaven | -0.264 |
Token | park |
Token ID | 3952 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
helmets | +0.043 |
numbers | +0.041 |
skills | +0.041 |
ates | +0.040 |
himself | +0.039 |
Neg logit contributions | |
chick | -0.036 |
bug | -0.036 |
shower | -0.035 |
die | -0.032 |
Lilly | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
bug | +0.138 |
shower | +0.134 |
chick | +0.133 |
Lilly | +0.124 |
heaven | +0.123 |
Neg logit contributions | |
helmets | -0.134 |
ates | -0.128 |
numbers | -0.123 |
skills | -0.121 |
bled | -0.119 |
Token | looking |
Token ID | 2045 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ates | +0.059 |
helmets | +0.059 |
skills | +0.056 |
numbers | +0.055 |
himself | +0.052 |
Neg logit contributions | |
bug | -0.053 |
shower | -0.050 |
chick | -0.049 |
Lilly | -0.047 |
Nina | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
shower | +0.020 |
bug | +0.020 |
chick | +0.020 |
Lilly | +0.019 |
Nina | +0.018 |
Neg logit contributions | |
ates | -0.020 |
helmets | -0.019 |
numbers | -0.018 |
skills | -0.018 |
himself | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
helmets | +0.183 |
ates | +0.175 |
skills | +0.170 |
numbers | +0.169 |
himself | +0.164 |
Neg logit contributions | |
chick | -0.227 |
bug | -0.225 |
shower | -0.222 |
Lilly | -0.208 |
heaven | -0.208 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
bled | +0.035 |
ates | +0.034 |
helmets | +0.033 |
aged | +0.032 |
himself | +0.031 |
Neg logit contributions | |
shower | -0.047 |
chick | -0.046 |
bug | -0.045 |
drink | -0.042 |
party | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
helmets | +0.709 |
numbers | +0.666 |
skills | +0.664 |
ates | +0.664 |
himself | +0.642 |
Neg logit contributions | |
chick | -0.770 |
bug | -0.758 |
shower | -0.746 |
Lilly | -0.692 |
heaven | -0.691 |
Token |
|
Token ID | 198 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
chick | +0.001 |
bug | +0.001 |
shower | +0.001 |
die | +0.001 |
heaven | +0.001 |
Neg logit contributions | |
helmets | -0.001 |
numbers | -0.001 |
ates | -0.001 |
himself | -0.001 |
skills | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
bug | +0.034 |
chick | +0.033 |
shower | +0.032 |
Lilly | +0.031 |
Nina | +0.030 |
Neg logit contributions | |
helmets | -0.042 |
numbers | -0.040 |
skills | -0.039 |
ates | -0.039 |
hardest | -0.038 |
Token | But |
Token ID | 1537 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
bug | +0.046 |
chick | +0.045 |
shower | +0.045 |
Lilly | +0.042 |
lyss | +0.042 |
Neg logit contributions | |
helmets | -0.033 |
skills | -0.032 |
ates | -0.031 |
numbers | -0.031 |
himself | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
helmets | +0.285 |
skills | +0.272 |
ates | +0.271 |
numbers | +0.269 |
himself | +0.256 |
Neg logit contributions | |
chick | -0.265 |
bug | -0.262 |
shower | -0.255 |
Lilly | -0.241 |
heaven | -0.234 |
Token | they |
Token ID | 484 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
chick | +0.349 |
bug | +0.343 |
shower | +0.337 |
heaven | +0.311 |
Lilly | +0.310 |
Neg logit contributions | |
helmets | -0.359 |
numbers | -0.339 |
skills | -0.337 |
ates | -0.335 |
himself | -0.327 |
Token | exchanged |
Token ID | 22112 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
chick | +0.061 |
shower | +0.060 |
bug | +0.059 |
heaven | +0.056 |
lyss | +0.055 |
Neg logit contributions | |
helmets | -0.059 |
skills | -0.055 |
numbers | -0.054 |
himself | -0.053 |
hard | -0.052 |
Token | emails |
Token ID | 7237 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
chick | +0.115 |
bug | +0.114 |
shower | +0.113 |
heaven | +0.106 |
Lilly | +0.105 |
Neg logit contributions | |
helmets | -0.092 |
ates | -0.090 |
numbers | -0.086 |
skills | -0.086 |
himself | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
helmets | +0.165 |
numbers | +0.155 |
skills | +0.154 |
ates | +0.154 |
himself | +0.149 |
Neg logit contributions | |
chick | -0.174 |
bug | -0.171 |
shower | -0.168 |
Lilly | -0.156 |
heaven | -0.156 |
Token | telephone |
Token ID | 11426 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
helmets | +0.047 |
numbers | +0.044 |
skills | +0.044 |
ates | +0.043 |
himself | +0.042 |
Neg logit contributions | |
chick | -0.052 |
bug | -0.051 |
shower | -0.050 |
lyss | -0.046 |
Lilly | -0.046 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
chick | +0.163 |
bug | +0.160 |
shower | +0.156 |
lyss | +0.147 |
Lilly | +0.146 |
Neg logit contributions | |
helmets | -0.144 |
numbers | -0.136 |
skills | -0.135 |
ates | -0.131 |
himself | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
helmets | +0.681 |
numbers | +0.637 |
skills | +0.636 |
ates | +0.636 |
himself | +0.614 |
Neg logit contributions | |
chick | -0.794 |
bug | -0.781 |
shower | -0.770 |
Lilly | -0.716 |
heaven | -0.715 |
Token | addresses |
Token ID | 9405 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
helmets | +0.031 |
ates | +0.029 |
numbers | +0.029 |
skills | +0.029 |
himself | +0.027 |
Neg logit contributions | |
chick | -0.046 |
bug | -0.045 |
shower | -0.045 |
Lilly | -0.042 |
heaven | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
helmets | +0.362 |
ates | +0.339 |
skills | +0.338 |
numbers | +0.336 |
himself | +0.328 |
Neg logit contributions | |
chick | -0.356 |
bug | -0.352 |
shower | -0.343 |
Lilly | -0.322 |
heaven | -0.318 |
Token | |
Token ID | 220 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
chick | +0.012 |
bug | +0.011 |
shower | +0.011 |
die | +0.011 |
lamb | +0.010 |
Neg logit contributions | |
helmets | -0.009 |
numbers | -0.009 |
ates | -0.009 |
himself | -0.009 |
skills | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
helmets | +0.136 |
skills | +0.128 |
numbers | +0.127 |
ates | +0.123 |
hardest | +0.121 |
Neg logit contributions | |
bug | -0.117 |
chick | -0.114 |
shower | -0.112 |
Lilly | -0.108 |
Nina | -0.105 |
Token | still |
Token ID | 991 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
helmets | +0.177 |
ates | +0.170 |
numbers | +0.166 |
skills | +0.164 |
himself | +0.160 |
Neg logit contributions | |
chick | -0.172 |
bug | -0.169 |
shower | -0.165 |
die | -0.153 |
Lilly | -0.152 |
Token | couldn |
Token ID | 3521 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
helmets | +0.076 |
ates | +0.075 |
skills | +0.071 |
numbers | +0.071 |
himself | +0.069 |
Neg logit contributions | |
chick | -0.066 |
bug | -0.066 |
shower | -0.064 |
die | -0.060 |
Lilly | -0.060 |
Token | 't |
Token ID | 470 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
helmets | +0.042 |
ates | +0.040 |
numbers | +0.039 |
skills | +0.039 |
himself | +0.037 |
Neg logit contributions | |
chick | -0.047 |
shower | -0.046 |
bug | -0.046 |
die | -0.043 |
Lilly | -0.043 |
Token | show |
Token ID | 905 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
himself | +0.289 |
helmets | +0.289 |
skills | +0.279 |
numbers | +0.278 |
hard | +0.268 |
Neg logit contributions | |
chick | -0.312 |
bug | -0.306 |
shower | -0.291 |
lyss | -0.286 |
lamb | -0.281 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
chick | +0.100 |
bug | +0.099 |
shower | +0.097 |
heaven | +0.092 |
Lilly | +0.092 |
Neg logit contributions | |
helmets | -0.097 |
ates | -0.093 |
skills | -0.091 |
numbers | -0.091 |
himself | -0.086 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
helmets | +0.013 |
numbers | +0.013 |
skills | +0.013 |
ates | +0.013 |
himself | +0.012 |
Neg logit contributions | |
chick | -0.012 |
bug | -0.012 |
shower | -0.011 |
Lilly | -0.010 |
heaven | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
helmets | +0.697 |
numbers | +0.656 |
skills | +0.652 |
ates | +0.648 |
himself | +0.630 |
Neg logit contributions | |
chick | -0.783 |
bug | -0.767 |
shower | -0.756 |
Lilly | -0.703 |
heaven | -0.702 |
Token |
|
Token ID | 198 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
chick | +0.019 |
bug | +0.019 |
shower | +0.019 |
die | +0.018 |
heaven | +0.018 |
Neg logit contributions | |
helmets | -0.016 |
numbers | -0.015 |
skills | -0.015 |
ates | -0.014 |
himself | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
bug | +0.043 |
chick | +0.042 |
shower | +0.041 |
Lilly | +0.040 |
lyss | +0.038 |
Neg logit contributions | |
helmets | -0.054 |
numbers | -0.051 |
skills | -0.050 |
ates | -0.050 |
hardest | -0.049 |
Token | He |
Token ID | 1544 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
bug | +0.052 |
chick | +0.051 |
shower | +0.049 |
lyss | +0.048 |
Lilly | +0.048 |
Neg logit contributions | |
helmets | -0.047 |
numbers | -0.045 |
ates | -0.045 |
skills | -0.044 |
hardest | -0.042 |
Token | was |
Token ID | 373 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
helmets | +0.228 |
ates | +0.218 |
numbers | +0.215 |
skills | +0.214 |
himself | +0.207 |
Neg logit contributions | |
chick | -0.209 |
bug | -0.208 |
shower | -0.201 |
Lilly | -0.186 |
heaven | -0.185 |
Token | things |
Token ID | 1243 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
helmets | +0.044 |
ates | +0.041 |
numbers | +0.039 |
skills | +0.039 |
himself | +0.038 |
Neg logit contributions | |
chick | -0.075 |
shower | -0.075 |
bug | -0.075 |
Lilly | -0.070 |
heaven | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
helmets | +0.382 |
skills | +0.366 |
numbers | +0.365 |
himself | +0.357 |
ates | +0.350 |
Neg logit contributions | |
chick | -0.434 |
bug | -0.416 |
shower | -0.409 |
lamb | -0.385 |
heaven | -0.382 |
Token | like |
Token ID | 588 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
helmets | +0.065 |
numbers | +0.062 |
skills | +0.062 |
himself | +0.060 |
ates | +0.059 |
Neg logit contributions | |
chick | -0.062 |
bug | -0.060 |
shower | -0.059 |
lyss | -0.055 |
die | -0.055 |
Token | songs |
Token ID | 7259 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
chick | +0.187 |
bug | +0.183 |
shower | +0.178 |
heaven | +0.167 |
die | +0.167 |
Neg logit contributions | |
helmets | -0.160 |
numbers | -0.153 |
skills | -0.151 |
himself | -0.146 |
ates | -0.145 |
Token | and |
Token ID | 290 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
helmets | +0.129 |
skills | +0.124 |
numbers | +0.123 |
ates | +0.119 |
himself | +0.118 |
Neg logit contributions | |
chick | -0.153 |
bug | -0.148 |
shower | -0.146 |
heaven | -0.137 |
lamb | -0.137 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
helmets | +0.047 |
numbers | +0.044 |
skills | +0.044 |
ates | +0.043 |
himself | +0.042 |
Neg logit contributions | |
chick | -0.059 |
bug | -0.058 |
shower | -0.057 |
heaven | -0.053 |
Lilly | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
helmets | +0.710 |
numbers | +0.668 |
skills | +0.666 |
ates | +0.663 |
himself | +0.643 |
Neg logit contributions | |
chick | -0.767 |
bug | -0.752 |
shower | -0.742 |
Lilly | -0.688 |
heaven | -0.687 |
Token | With |
Token ID | 2080 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
helmets | +0.006 |
numbers | +0.005 |
himself | +0.005 |
skills | +0.005 |
ates | +0.005 |
Neg logit contributions | |
chick | -0.007 |
bug | -0.006 |
shower | -0.006 |
die | -0.006 |
lamb | -0.006 |
Token | each |
Token ID | 1123 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
helmets | +0.095 |
numbers | +0.089 |
skills | +0.089 |
ates | +0.089 |
himself | +0.086 |
Neg logit contributions | |
chick | -0.121 |
bug | -0.119 |
shower | -0.118 |
Lilly | -0.110 |
heaven | -0.110 |
Token | new |
Token ID | 649 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
shower | +0.074 |
bug | +0.073 |
chick | +0.071 |
sip | +0.069 |
heaven | +0.067 |
Neg logit contributions | |
helmets | -0.070 |
ates | -0.067 |
bled | -0.067 |
bles | -0.064 |
himself | -0.063 |
Token | lesson |
Token ID | 11483 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
helmets | +0.019 |
ates | +0.018 |
numbers | +0.018 |
skills | +0.017 |
himself | +0.017 |
Neg logit contributions | |
chick | -0.028 |
bug | -0.028 |
shower | -0.028 |
heaven | -0.026 |
Lilly | -0.026 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
chick | +0.016 |
bug | +0.016 |
shower | +0.015 |
die | +0.014 |
lamb | +0.014 |
Neg logit contributions | |
helmets | -0.013 |
himself | -0.012 |
numbers | -0.012 |
ates | -0.011 |
skills | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
bug | +0.019 |
chick | +0.018 |
shower | +0.017 |
Lilly | +0.016 |
lamb | +0.015 |
Neg logit contributions | |
helmets | -0.027 |
numbers | -0.026 |
skills | -0.025 |
ates | -0.025 |
bled | -0.024 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
helmets | +0.197 |
ates | +0.189 |
numbers | +0.186 |
skills | +0.183 |
himself | +0.181 |
Neg logit contributions | |
bug | -0.171 |
chick | -0.171 |
shower | -0.163 |
lyss | -0.154 |
Lilly | -0.149 |
Token | watching |
Token ID | 4964 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
helmets | +0.088 |
ates | +0.087 |
skills | +0.084 |
numbers | +0.083 |
bled | +0.080 |
Neg logit contributions | |
chick | -0.122 |
shower | -0.120 |
bug | -0.117 |
heaven | -0.112 |
Lilly | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
chick | +0.126 |
bug | +0.125 |
shower | +0.122 |
Lilly | +0.114 |
heaven | +0.113 |
Neg logit contributions | |
helmets | -0.104 |
numbers | -0.098 |
skills | -0.097 |
ates | -0.096 |
himself | -0.094 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
helmets | +0.023 |
numbers | +0.022 |
skills | +0.022 |
ates | +0.021 |
himself | +0.021 |
Neg logit contributions | |
chick | -0.023 |
bug | -0.023 |
shower | -0.022 |
Lilly | -0.021 |
heaven | -0.021 |
Token | go |
Token ID | 467 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
helmets | +0.661 |
ates | +0.628 |
skills | +0.618 |
numbers | +0.615 |
himself | +0.596 |
Neg logit contributions | |
chick | -0.805 |
bug | -0.796 |
shower | -0.791 |
die | -0.727 |
heaven | -0.727 |
Token | up |
Token ID | 510 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
chick | +0.186 |
bug | +0.183 |
shower | +0.180 |
Lilly | +0.169 |
heaven | +0.169 |
Neg logit contributions | |
helmets | -0.126 |
numbers | -0.117 |
skills | -0.117 |
ates | -0.116 |
himself | -0.112 |
Token | on |
Token ID | 319 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
ates | +0.309 |
helmets | +0.308 |
bled | +0.292 |
skills | +0.286 |
himself | +0.284 |
Neg logit contributions | |
shower | -0.291 |
chick | -0.288 |
bug | -0.276 |
heaven | -0.260 |
Lilly | -0.259 |
Token | the |
Token ID | 262 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ates | +0.418 |
bled | +0.410 |
bles | +0.403 |
helmets | +0.397 |
hardest | +0.385 |
Neg logit contributions | |
shower | -0.416 |
chick | -0.408 |
heaven | -0.386 |
Lilly | -0.370 |
Nina | -0.367 |
Token | gas |
Token ID | 3623 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
helmets | +0.020 |
numbers | +0.019 |
skills | +0.018 |
hard | +0.017 |
ates | +0.017 |
Neg logit contributions | |
bug | -0.025 |
chick | -0.023 |
Lilly | -0.022 |
lyss | -0.021 |
heaven | -0.021 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
helmets | +0.044 |
ates | +0.041 |
numbers | +0.041 |
skills | +0.041 |
himself | +0.039 |
Neg logit contributions | |
chick | -0.048 |
bug | -0.047 |
shower | -0.046 |
Lilly | -0.043 |
heaven | -0.043 |
Token | liked |
Token ID | 8288 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
chick | +0.222 |
bug | +0.213 |
shower | +0.212 |
heaven | +0.197 |
Lilly | +0.196 |
Neg logit contributions | |
helmets | -0.227 |
numbers | -0.214 |
skills | -0.212 |
ates | -0.210 |
himself | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
helmets | +0.168 |
numbers | +0.160 |
skills | +0.157 |
himself | +0.150 |
ates | +0.148 |
Neg logit contributions | |
chick | -0.181 |
bug | -0.180 |
shower | -0.171 |
lyss | -0.162 |
Lilly | -0.162 |
Token | play |
Token ID | 711 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
chick | +0.014 |
bug | +0.013 |
shower | +0.013 |
Lilly | +0.012 |
lyss | +0.012 |
Neg logit contributions | |
helmets | -0.021 |
numbers | -0.020 |
skills | -0.020 |
ates | -0.020 |
himself | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
chick | +0.116 |
shower | +0.116 |
bug | +0.114 |
heaven | +0.106 |
Lilly | +0.104 |
Neg logit contributions | |
helmets | -0.118 |
numbers | -0.115 |
ates | -0.114 |
hardest | -0.111 |
skills | -0.110 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
ates | +0.058 |
helmets | +0.057 |
skills | +0.054 |
hardest | +0.054 |
numbers | +0.054 |
Neg logit contributions | |
chick | -0.098 |
shower | -0.096 |
bug | -0.095 |
heaven | -0.090 |
Lilly | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
helmets | +0.737 |
ates | +0.706 |
skills | +0.686 |
bled | +0.675 |
numbers | +0.674 |
Neg logit contributions | |
bug | -0.714 |
chick | -0.702 |
shower | -0.696 |
heaven | -0.637 |
Lilly | -0.632 |
Token | They |
Token ID | 1119 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
chick | +0.021 |
bug | +0.020 |
shower | +0.020 |
die | +0.019 |
lyss | +0.019 |
Neg logit contributions | |
helmets | -0.018 |
numbers | -0.017 |
skills | -0.017 |
ates | -0.017 |
himself | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
bug | +0.045 |
chick | +0.040 |
bloom | +0.038 |
shower | +0.038 |
Lilly | +0.038 |
Neg logit contributions | |
ates | -0.061 |
skills | -0.058 |
helmets | -0.057 |
bled | -0.056 |
himself | -0.055 |
Token | many |
Token ID | 867 |
Feature activation | +7.90e+00 |
Pos logit contributions | |
bled | +0.066 |
ates | +0.061 |
bles | +0.058 |
himself | +0.055 |
skills | +0.055 |
Neg logit contributions | |
bug | -0.110 |
shower | -0.108 |
chick | -0.107 |
heaven | -0.104 |
Lilly | -0.101 |
Token | cards |
Token ID | 4116 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
bled | +0.554 |
balls | +0.455 |
bles | +0.439 |
ble | +0.430 |
ates | +0.429 |
Neg logit contributions | |
else | -0.447 |
who | -0.423 |
shower | -0.416 |
party | -0.406 |
bug | -0.405 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
bug | +0.107 |
chick | +0.104 |
shower | +0.104 |
Lilly | +0.100 |
lyss | +0.099 |
Neg logit contributions | |
helmets | -0.108 |
ates | -0.104 |
skills | -0.099 |
numbers | -0.097 |
himself | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
numbers | +0.043 |
skills | +0.043 |
helmets | +0.042 |
himself | +0.040 |
hard | +0.038 |
Neg logit contributions | |
chick | -0.085 |
bug | -0.083 |
shower | -0.083 |
die | -0.082 |
sip | -0.080 |
Token | taught |
Token ID | 7817 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
helmets | +0.031 |
ates | +0.029 |
numbers | +0.029 |
skills | +0.029 |
himself | +0.028 |
Neg logit contributions | |
chick | -0.032 |
bug | -0.032 |
shower | -0.031 |
Lilly | -0.029 |
heaven | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
helmets | +0.122 |
numbers | +0.118 |
skills | +0.117 |
ates | +0.114 |
himself | +0.114 |
Neg logit contributions | |
chick | -0.110 |
bug | -0.107 |
shower | -0.104 |
lamb | -0.096 |
die | -0.096 |
Token | about |
Token ID | 546 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
bug | +0.008 |
shower | +0.008 |
chick | +0.007 |
heaven | +0.007 |
Lilly | +0.007 |
Neg logit contributions | |
helmets | -0.009 |
ates | -0.009 |
bled | -0.008 |
numbers | -0.008 |
skills | -0.008 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
chick | +0.124 |
bug | +0.122 |
shower | +0.121 |
Lilly | +0.113 |
heaven | +0.113 |
Neg logit contributions | |
helmets | -0.111 |
ates | -0.105 |
skills | -0.104 |
numbers | -0.103 |
himself | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
helmets | +0.744 |
ates | +0.703 |
skills | +0.690 |
numbers | +0.688 |
himself | +0.670 |
Neg logit contributions | |
bug | -0.720 |
chick | -0.716 |
shower | -0.702 |
heaven | -0.651 |
Lilly | -0.649 |
Token | letters |
Token ID | 7475 |
Feature activation | +8.28e+00 |
Pos logit contributions | |
helmets | +0.023 |
ates | +0.023 |
bled | +0.021 |
skills | +0.020 |
bles | +0.020 |
Neg logit contributions | |
bug | -0.038 |
chick | -0.037 |
shower | -0.037 |
Lilly | -0.035 |
heaven | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
helmets | +0.512 |
ates | +0.482 |
numbers | +0.478 |
skills | +0.478 |
himself | +0.462 |
Neg logit contributions | |
chick | -0.500 |
bug | -0.496 |
shower | -0.485 |
Lilly | -0.450 |
heaven | -0.449 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
chick | +0.020 |
bug | +0.020 |
shower | +0.020 |
Lilly | +0.019 |
heaven | +0.018 |
Neg logit contributions | |
helmets | -0.024 |
ates | -0.023 |
skills | -0.023 |
numbers | -0.023 |
himself | -0.022 |
Token | thought |
Token ID | 1807 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
bug | +0.223 |
chick | +0.205 |
shower | +0.197 |
lyss | +0.196 |
Lilly | +0.195 |
Neg logit contributions | |
helmets | -0.277 |
ates | -0.264 |
numbers | -0.247 |
skills | -0.244 |
himself | -0.242 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
chick | +0.022 |
bug | +0.022 |
shower | +0.021 |
heaven | +0.020 |
die | +0.020 |
Neg logit contributions | |
helmets | -0.020 |
numbers | -0.019 |
skills | -0.019 |
ates | -0.019 |
himself | -0.018 |
Token | watched |
Token ID | 7342 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
helmets | +0.144 |
numbers | +0.137 |
skills | +0.135 |
himself | +0.132 |
ates | +0.128 |
Neg logit contributions | |
chick | -0.177 |
shower | -0.170 |
bug | -0.166 |
heaven | -0.160 |
die | -0.159 |
Token | the |
Token ID | 262 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
chick | +0.042 |
bug | +0.041 |
shower | +0.040 |
lyss | +0.038 |
heaven | +0.038 |
Neg logit contributions | |
helmets | -0.032 |
numbers | -0.030 |
skills | -0.030 |
himself | -0.030 |
ates | -0.029 |
Token | colors |
Token ID | 7577 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
helmets | +0.030 |
numbers | +0.030 |
skills | +0.029 |
himself | +0.028 |
hard | +0.027 |
Neg logit contributions | |
bug | -0.030 |
chick | -0.029 |
Lilly | -0.027 |
shower | -0.027 |
lyss | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
helmets | +0.287 |
numbers | +0.273 |
skills | +0.272 |
himself | +0.267 |
ates | +0.261 |
Neg logit contributions | |
chick | -0.341 |
bug | -0.327 |
shower | -0.319 |
lyss | -0.308 |
heaven | -0.307 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
helmets | +0.031 |
numbers | +0.029 |
skills | +0.029 |
ates | +0.029 |
himself | +0.028 |
Neg logit contributions | |
chick | -0.032 |
bug | -0.031 |
shower | -0.031 |
heaven | -0.029 |
Lilly | -0.028 |
Token | go |
Token ID | 467 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
helmets | +0.629 |
numbers | +0.586 |
skills | +0.583 |
ates | +0.583 |
himself | +0.561 |
Neg logit contributions | |
chick | -0.848 |
bug | -0.835 |
shower | -0.824 |
Lilly | -0.770 |
heaven | -0.769 |
Token | by |
Token ID | 416 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
chick | +0.180 |
bug | +0.178 |
shower | +0.176 |
Lilly | +0.165 |
heaven | +0.163 |
Neg logit contributions | |
helmets | -0.137 |
ates | -0.129 |
numbers | -0.128 |
skills | -0.127 |
himself | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
shower | +0.082 |
chick | +0.082 |
bug | +0.081 |
Lilly | +0.075 |
heaven | +0.075 |
Neg logit contributions | |
helmets | -0.090 |
ates | -0.084 |
skills | -0.082 |
numbers | -0.081 |
hardest | -0.079 |
Token | He |
Token ID | 679 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
bug | +0.015 |
Lilly | +0.015 |
chick | +0.014 |
shower | +0.014 |
Nina | +0.014 |
Neg logit contributions | |
helmets | -0.017 |
ates | -0.016 |
skills | -0.016 |
bled | -0.016 |
numbers | -0.016 |
Token | hoped |
Token ID | 10719 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
helmets | +0.202 |
ates | +0.193 |
skills | +0.189 |
numbers | +0.188 |
himself | +0.184 |
Neg logit contributions | |
bug | -0.191 |
chick | -0.189 |
shower | -0.184 |
Lilly | -0.170 |
lyss | -0.169 |
Token | Sam |
Token ID | 3409 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
helmets | +0.036 |
himself | +0.035 |
numbers | +0.032 |
his | +0.031 |
skills | +0.031 |
Neg logit contributions | |
chick | -0.054 |
shower | -0.053 |
bug | -0.052 |
heaven | -0.049 |
lyss | -0.049 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
helmets | +0.174 |
numbers | +0.165 |
himself | +0.162 |
skills | +0.161 |
ates | +0.159 |
Neg logit contributions | |
chick | -0.187 |
shower | -0.176 |
bug | -0.174 |
lyss | -0.166 |
lamb | -0.163 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
helmets | +0.197 |
numbers | +0.186 |
skills | +0.185 |
ates | +0.182 |
himself | +0.179 |
Neg logit contributions | |
chick | -0.183 |
bug | -0.180 |
shower | -0.175 |
Lilly | -0.162 |
heaven | -0.162 |
Token | play |
Token ID | 711 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
chick | +0.010 |
bug | +0.010 |
shower | +0.010 |
heaven | +0.009 |
Lilly | +0.009 |
Neg logit contributions | |
helmets | -0.016 |
numbers | -0.015 |
skills | -0.015 |
ates | -0.015 |
himself | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
chick | +0.111 |
shower | +0.110 |
bug | +0.108 |
heaven | +0.101 |
Lilly | +0.099 |
Neg logit contributions | |
helmets | -0.117 |
numbers | -0.113 |
ates | -0.113 |
skills | -0.110 |
hardest | -0.109 |
Token | numbers |
Token ID | 3146 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
ates | +0.064 |
hardest | +0.062 |
bled | +0.062 |
helmets | +0.060 |
skills | +0.059 |
Neg logit contributions | |
shower | -0.096 |
chick | -0.096 |
bug | -0.093 |
heaven | -0.091 |
sip | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
helmets | +0.812 |
ates | +0.797 |
bled | +0.793 |
skills | +0.775 |
hardest | +0.769 |
Neg logit contributions | |
bug | -0.624 |
chick | -0.595 |
shower | -0.578 |
heaven | -0.545 |
bloom | -0.514 |
Token | They |
Token ID | 1119 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
chick | +0.005 |
bug | +0.005 |
shower | +0.005 |
heaven | +0.004 |
die | +0.004 |
Neg logit contributions | |
helmets | -0.005 |
numbers | -0.004 |
skills | -0.004 |
ates | -0.004 |
himself | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
bug | +0.029 |
chick | +0.027 |
shower | +0.026 |
Lilly | +0.025 |
bloom | +0.025 |
Neg logit contributions | |
ates | -0.036 |
skills | -0.035 |
helmets | -0.035 |
bled | -0.034 |
hardest | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
bled | +0.069 |
ates | +0.061 |
bles | +0.059 |
skills | +0.057 |
himself | +0.055 |
Neg logit contributions | |
bug | -0.136 |
chick | -0.133 |
shower | -0.132 |
heaven | -0.128 |
Lilly | -0.125 |
Token | big |
Token ID | 1263 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
himself | +0.105 |
ates | +0.105 |
bled | +0.102 |
helmets | +0.100 |
skills | +0.095 |
Neg logit contributions | |
shower | -0.117 |
chick | -0.116 |
bug | -0.112 |
sip | -0.104 |
lyss | -0.104 |
Token | to |
Token ID | 284 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
chick | +0.029 |
bug | +0.029 |
shower | +0.028 |
Lilly | +0.026 |
heaven | +0.026 |
Neg logit contributions | |
helmets | -0.031 |
skills | -0.029 |
numbers | -0.029 |
ates | -0.029 |
himself | -0.028 |
Token | nap |
Token ID | 25422 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
chick | +0.050 |
bug | +0.049 |
lyss | +0.045 |
lamb | +0.043 |
pillar | +0.042 |
Neg logit contributions | |
himself | -0.042 |
helmets | -0.041 |
skills | -0.039 |
hard | -0.039 |
numbers | -0.039 |
Token | without |
Token ID | 1231 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
shower | +0.275 |
chick | +0.268 |
Lilly | +0.256 |
heaven | +0.256 |
Nina | +0.251 |
Neg logit contributions | |
helmets | -0.319 |
numbers | -0.310 |
ates | -0.295 |
skills | -0.288 |
gears | -0.282 |
Token | taking |
Token ID | 2263 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
chick | +0.136 |
bug | +0.136 |
shower | +0.127 |
lyss | +0.123 |
lamb | +0.121 |
Neg logit contributions | |
helmets | -0.116 |
numbers | -0.109 |
himself | -0.109 |
skills | -0.107 |
ates | -0.106 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
helmets | +0.022 |
skills | +0.021 |
numbers | +0.021 |
ates | +0.020 |
himself | +0.020 |
Neg logit contributions | |
chick | -0.029 |
bug | -0.028 |
shower | -0.027 |
lyss | -0.026 |
lamb | -0.025 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
hard | +0.132 |
lesson | +0.122 |
skills | +0.111 |
top | +0.110 |
helmets | +0.108 |
Neg logit contributions | |
bug | -0.063 |
chick | -0.054 |
al | -0.048 |
heaven | -0.044 |
weet | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
chick | +1.055 |
bug | +1.034 |
lamb | +0.962 |
lyss | +0.962 |
fa | +0.922 |
Neg logit contributions | |
skills | -0.569 |
helmets | -0.546 |
hard | -0.538 |
himself | -0.527 |
numbers | -0.512 |
Token |
|
Token ID | 198 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
chick | +0.032 |
bug | +0.031 |
shower | +0.030 |
lamb | +0.028 |
die | +0.028 |
Neg logit contributions | |
helmets | -0.025 |
numbers | -0.024 |
skills | -0.023 |
himself | -0.023 |
ates | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
chick | +0.054 |
bug | +0.054 |
shower | +0.054 |
Lilly | +0.051 |
heaven | +0.049 |
Neg logit contributions | |
helmets | -0.061 |
numbers | -0.057 |
ates | -0.057 |
skills | -0.056 |
hardest | -0.054 |
Token | Unfortunately |
Token ID | 13898 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
chick | +0.057 |
bug | +0.057 |
shower | +0.057 |
Lilly | +0.053 |
heaven | +0.053 |
Neg logit contributions | |
helmets | -0.058 |
ates | -0.056 |
numbers | -0.055 |
skills | -0.055 |
himself | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
helmets | +0.069 |
ates | +0.067 |
skills | +0.065 |
numbers | +0.065 |
himself | +0.061 |
Neg logit contributions | |
chick | -0.072 |
bug | -0.071 |
shower | -0.071 |
Lilly | -0.068 |
Nina | -0.066 |
Token | you |
Token ID | 345 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
helmets | +0.030 |
himself | +0.029 |
numbers | +0.029 |
hard | +0.029 |
skills | +0.028 |
Neg logit contributions | |
chick | -0.027 |
bug | -0.027 |
ount | -0.024 |
lyss | -0.024 |
heaven | -0.024 |
Token | need |
Token ID | 761 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
chick | +0.195 |
bug | +0.187 |
shower | +0.178 |
lamb | +0.173 |
heaven | +0.172 |
Neg logit contributions | |
helmets | -0.211 |
numbers | -0.204 |
hard | -0.202 |
skills | -0.200 |
hardest | -0.199 |
Token | to |
Token ID | 284 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
bug | +0.102 |
chick | +0.100 |
lamb | +0.089 |
lyss | +0.088 |
shower | +0.088 |
Neg logit contributions | |
helmets | -0.076 |
skills | -0.072 |
numbers | -0.072 |
hard | -0.070 |
himself | -0.070 |
Token | take |
Token ID | 1011 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
bug | +0.040 |
chick | +0.040 |
lyss | +0.035 |
lamb | +0.034 |
shower | +0.033 |
Neg logit contributions | |
himself | -0.048 |
helmets | -0.047 |
skills | -0.046 |
hard | -0.045 |
numbers | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
helmets | +0.004 |
numbers | +0.004 |
skills | +0.004 |
ates | +0.004 |
himself | +0.004 |
Neg logit contributions | |
chick | -0.006 |
bug | -0.006 |
shower | -0.006 |
lyss | -0.005 |
Lilly | -0.005 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
hard | +0.131 |
lesson | +0.118 |
top | +0.107 |
helmets | +0.104 |
skills | +0.104 |
Neg logit contributions | |
bug | -0.065 |
al | -0.058 |
chick | -0.058 |
ring | -0.053 |
ount | -0.051 |
Token | before |
Token ID | 878 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
chick | +0.916 |
bug | +0.891 |
shower | +0.824 |
lamb | +0.820 |
lyss | +0.812 |
Neg logit contributions | |
helmets | -0.683 |
skills | -0.671 |
numbers | -0.638 |
hard | -0.631 |
himself | -0.627 |
Token | you |
Token ID | 345 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
bug | +0.116 |
chick | +0.110 |
lyss | +0.096 |
shower | +0.095 |
lamb | +0.094 |
Neg logit contributions | |
helmets | -0.156 |
skills | -0.150 |
numbers | -0.149 |
himself | -0.145 |
hard | -0.144 |
Token | can |
Token ID | 460 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
chick | +0.209 |
lyss | +0.192 |
bug | +0.187 |
lamb | +0.183 |
Lilly | +0.175 |
Neg logit contributions | |
hard | -0.193 |
skills | -0.186 |
helmets | -0.185 |
numbers | -0.181 |
hardest | -0.177 |
Token | nap |
Token ID | 25422 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
chick | +0.117 |
bug | +0.114 |
lamb | +0.101 |
heaven | +0.100 |
lyss | +0.099 |
Neg logit contributions | |
himself | -0.106 |
skills | -0.105 |
top | -0.104 |
hard | -0.103 |
helmets | -0.098 |
Token | ." |
Token ID | 526 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
chick | +0.279 |
shower | +0.278 |
bug | +0.265 |
heaven | +0.257 |
Lilly | +0.256 |
Neg logit contributions | |
helmets | -0.311 |
numbers | -0.297 |
skills | -0.287 |
ates | -0.285 |
himself | -0.273 |
Token | 't |
Token ID | 470 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
helmets | +0.034 |
ates | +0.032 |
numbers | +0.031 |
skills | +0.031 |
himself | +0.028 |
Neg logit contributions | |
shower | -0.034 |
chick | -0.032 |
bug | -0.032 |
Lilly | -0.031 |
die | -0.030 |
Token | want |
Token ID | 765 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
himself | +0.287 |
hard | +0.272 |
numbers | +0.270 |
helmets | +0.269 |
skills | +0.267 |
Neg logit contributions | |
chick | -0.271 |
bug | -0.250 |
shower | -0.232 |
lamb | -0.228 |
lyss | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
numbers | +0.013 |
helmets | +0.012 |
himself | +0.012 |
skills | +0.012 |
hard | +0.012 |
Neg logit contributions | |
chick | -0.020 |
bug | -0.019 |
lamb | -0.018 |
lyss | -0.017 |
plet | -0.017 |
Token | take |
Token ID | 1011 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
chick | +0.043 |
bug | +0.041 |
lyss | +0.037 |
lamb | +0.037 |
album | +0.036 |
Neg logit contributions | |
himself | -0.045 |
hard | -0.040 |
helmets | -0.039 |
skills | -0.038 |
top | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
helmets | +0.006 |
numbers | +0.006 |
ates | +0.006 |
skills | +0.006 |
himself | +0.006 |
Neg logit contributions | |
chick | -0.008 |
bug | -0.008 |
shower | -0.008 |
Lilly | -0.008 |
heaven | -0.008 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
hard | +0.111 |
lesson | +0.093 |
helmets | +0.086 |
on | +0.085 |
top | +0.085 |
Neg logit contributions | |
bug | -0.081 |
al | -0.081 |
chick | -0.078 |
ount | -0.075 |
ain | -0.073 |
Token | first |
Token ID | 717 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
chick | +0.995 |
bug | +0.938 |
lamb | +0.901 |
lyss | +0.893 |
fa | +0.866 |
Neg logit contributions | |
helmets | -0.617 |
skills | -0.613 |
hard | -0.600 |
himself | -0.584 |
numbers | -0.571 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
skills | +0.329 |
helmets | +0.326 |
himself | +0.324 |
numbers | +0.318 |
hard | +0.303 |
Neg logit contributions | |
chick | -0.499 |
bug | -0.482 |
shower | -0.453 |
lamb | -0.446 |
lyss | -0.443 |
Token | Her |
Token ID | 2332 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
chick | +0.021 |
bug | +0.020 |
shower | +0.020 |
die | +0.019 |
lamb | +0.018 |
Neg logit contributions | |
helmets | -0.020 |
numbers | -0.020 |
himself | -0.019 |
skills | -0.019 |
hard | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
chick | +0.350 |
bug | +0.349 |
shower | +0.338 |
heaven | +0.323 |
Lilly | +0.321 |
Neg logit contributions | |
helmets | -0.205 |
skills | -0.189 |
numbers | -0.189 |
ates | -0.185 |
himself | -0.178 |
Token | said |
Token ID | 531 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
helmets | +0.179 |
numbers | +0.170 |
skills | +0.167 |
hard | +0.166 |
himself | +0.162 |
Neg logit contributions | |
shower | -0.223 |
chick | -0.219 |
heaven | -0.210 |
die | -0.208 |
bug | -0.205 |
Token | she |
Token ID | 673 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
chick | +0.329 |
bug | +0.322 |
shower | +0.318 |
Lilly | +0.291 |
heaven | +0.290 |
Neg logit contributions | |
helmets | -0.409 |
ates | -0.387 |
numbers | -0.387 |
skills | -0.387 |
himself | -0.374 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
chick | +0.084 |
bug | +0.083 |
shower | +0.082 |
die | +0.077 |
heaven | +0.077 |
Neg logit contributions | |
helmets | -0.060 |
numbers | -0.058 |
himself | -0.057 |
skills | -0.057 |
hard | -0.056 |
Token | 't |
Token ID | 470 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
helmets | +0.029 |
ates | +0.026 |
numbers | +0.026 |
skills | +0.026 |
himself | +0.024 |
Neg logit contributions | |
shower | -0.031 |
chick | -0.030 |
bug | -0.029 |
die | -0.028 |
Lilly | -0.028 |
Token | take |
Token ID | 1011 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
himself | +0.264 |
hard | +0.256 |
helmets | +0.237 |
numbers | +0.235 |
skills | +0.233 |
Neg logit contributions | |
chick | -0.289 |
bug | -0.267 |
lyss | -0.256 |
lamb | -0.249 |
Lilly | -0.237 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
helmets | +0.002 |
numbers | +0.002 |
skills | +0.002 |
himself | +0.002 |
hard | +0.002 |
Neg logit contributions | |
chick | -0.003 |
bug | -0.003 |
shower | -0.002 |
lyss | -0.002 |
lamb | -0.002 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
hard | +0.127 |
lesson | +0.117 |
on | +0.102 |
top | +0.101 |
long | +0.100 |
Neg logit contributions | |
bug | -0.070 |
al | -0.057 |
chick | -0.056 |
oph | -0.055 |
weet | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
chick | +0.981 |
bug | +0.950 |
lyss | +0.884 |
lamb | +0.883 |
fa | +0.846 |
Neg logit contributions | |
skills | -0.619 |
hard | -0.617 |
helmets | -0.590 |
himself | -0.582 |
numbers | -0.567 |
Token | She |
Token ID | 1375 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
chick | +0.015 |
bug | +0.014 |
shower | +0.014 |
lamb | +0.013 |
die | +0.012 |
Neg logit contributions | |
helmets | -0.017 |
numbers | -0.017 |
skills | -0.016 |
himself | -0.016 |
ates | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
shower | +0.073 |
bug | +0.073 |
chick | +0.072 |
lyss | +0.068 |
heaven | +0.067 |
Neg logit contributions | |
helmets | -0.062 |
himself | -0.057 |
skills | -0.057 |
numbers | -0.057 |
hard | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
helmets | +0.087 |
numbers | +0.082 |
skills | +0.082 |
himself | +0.080 |
ates | +0.079 |
Neg logit contributions | |
chick | -0.093 |
bug | -0.092 |
shower | -0.089 |
lamb | -0.083 |
lyss | -0.082 |
Token | go |
Token ID | 467 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
bug | +0.040 |
chick | +0.039 |
lyss | +0.037 |
pillar | +0.034 |
lamb | +0.033 |
Neg logit contributions | |
himself | -0.050 |
helmets | -0.048 |
skills | -0.046 |
hard | -0.046 |
numbers | -0.045 |
Token | Tom |
Token ID | 13787 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
bug | +0.058 |
heaven | +0.054 |
Baby | +0.054 |
shower | +0.053 |
chick | +0.053 |
Neg logit contributions | |
ates | -0.074 |
hardest | -0.073 |
skills | -0.071 |
bled | -0.069 |
helmets | -0.067 |
Token | gets |
Token ID | 3011 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
helmets | +0.288 |
ates | +0.276 |
skills | +0.264 |
bled | +0.263 |
hardest | +0.261 |
Neg logit contributions | |
bug | -0.300 |
shower | -0.288 |
chick | -0.283 |
sip | -0.272 |
heaven | -0.262 |
Token | out |
Token ID | 503 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
chick | +0.049 |
bug | +0.048 |
shower | +0.048 |
Lilly | +0.044 |
heaven | +0.044 |
Neg logit contributions | |
helmets | -0.037 |
ates | -0.035 |
numbers | -0.035 |
skills | -0.034 |
himself | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
chick | +0.152 |
shower | +0.151 |
bug | +0.142 |
Lilly | +0.133 |
heaven | +0.131 |
Neg logit contributions | |
helmets | -0.245 |
ates | -0.233 |
skills | -0.229 |
numbers | -0.227 |
hardest | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
shower | +0.329 |
chick | +0.328 |
bug | +0.314 |
Lilly | +0.307 |
heaven | +0.303 |
Neg logit contributions | |
helmets | -0.284 |
ates | -0.270 |
skills | -0.267 |
numbers | -0.266 |
hardest | -0.256 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
helmets | +0.010 |
skills | +0.010 |
hard | +0.010 |
numbers | +0.010 |
top | +0.009 |
Neg logit contributions | |
bug | -0.008 |
chick | -0.006 |
weet | -0.006 |
ility | -0.006 |
oph | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
chick | +0.972 |
bug | +0.949 |
lamb | +0.893 |
lyss | +0.888 |
shower | +0.883 |
Neg logit contributions | |
helmets | -0.621 |
skills | -0.615 |
numbers | -0.598 |
ates | -0.573 |
himself | -0.566 |
Token | Mom |
Token ID | 11254 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
helmets | +0.011 |
numbers | +0.011 |
skills | +0.010 |
himself | +0.010 |
ates | +0.010 |
Neg logit contributions | |
chick | -0.012 |
bug | -0.012 |
shower | -0.012 |
lyss | -0.011 |
Lilly | -0.011 |
Token | wraps |
Token ID | 27521 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
chick | +0.036 |
lyss | +0.033 |
bug | +0.033 |
Lilly | +0.033 |
lamb | +0.033 |
Neg logit contributions | |
helmets | -0.028 |
numbers | -0.028 |
skills | -0.026 |
ates | -0.026 |
himself | -0.025 |
Token | him |
Token ID | 683 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
chick | +0.008 |
bug | +0.008 |
shower | +0.008 |
Lilly | +0.008 |
Nina | +0.007 |
Neg logit contributions | |
helmets | -0.008 |
ates | -0.008 |
numbers | -0.007 |
hardest | -0.007 |
skills | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
numbers | +0.014 |
ates | +0.014 |
helmets | +0.013 |
gears | +0.013 |
icycle | +0.013 |
Neg logit contributions | |
bug | -0.011 |
sip | -0.010 |
shower | -0.010 |
chick | -0.010 |
drink | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
helmets | +0.077 |
ates | +0.073 |
numbers | +0.072 |
skills | +0.072 |
himself | +0.071 |
Neg logit contributions | |
chick | -0.042 |
bug | -0.041 |
shower | -0.039 |
Lilly | -0.035 |
die | -0.035 |
Token | important |
Token ID | 1593 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
chick | +0.245 |
shower | +0.230 |
lamb | +0.228 |
heaven | +0.226 |
Honey | +0.223 |
Neg logit contributions | |
helmets | -0.240 |
ates | -0.238 |
icycle | -0.232 |
skills | -0.232 |
cast | -0.230 |
Token | to |
Token ID | 284 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
helmets | +0.257 |
ates | +0.249 |
bled | +0.240 |
bles | +0.239 |
ep | +0.235 |
Neg logit contributions | |
shower | -0.125 |
chick | -0.120 |
Lilly | -0.109 |
bug | -0.108 |
heaven | -0.107 |
Token | take |
Token ID | 1011 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
chick | +0.043 |
bug | +0.042 |
shower | +0.039 |
lyss | +0.037 |
lamb | +0.037 |
Neg logit contributions | |
helmets | -0.047 |
himself | -0.045 |
numbers | -0.045 |
skills | -0.045 |
ates | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
helmets | +0.004 |
skills | +0.004 |
numbers | +0.004 |
ates | +0.004 |
himself | +0.004 |
Neg logit contributions | |
chick | -0.003 |
bug | -0.003 |
shower | -0.003 |
Lilly | -0.003 |
lyss | -0.003 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
hard | +0.106 |
lesson | +0.097 |
many | +0.083 |
skills | +0.083 |
best | +0.083 |
Neg logit contributions | |
bug | -0.091 |
al | -0.078 |
chick | -0.078 |
ring | -0.070 |
ain | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
chick | +0.912 |
bug | +0.893 |
shower | +0.834 |
die | +0.816 |
lamb | +0.811 |
Neg logit contributions | |
helmets | -0.685 |
skills | -0.670 |
numbers | -0.637 |
ates | -0.629 |
himself | -0.628 |
Token | not |
Token ID | 407 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
helmets | +0.026 |
himself | +0.025 |
skills | +0.025 |
numbers | +0.024 |
hard | +0.024 |
Neg logit contributions | |
chick | -0.027 |
bug | -0.027 |
lyss | -0.024 |
lamb | -0.024 |
shower | -0.024 |
Token | be |
Token ID | 307 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
hard | +0.355 |
himself | +0.339 |
helmets | +0.325 |
numbers | +0.322 |
not | +0.319 |
Neg logit contributions | |
chick | -0.377 |
lyss | -0.351 |
bug | -0.350 |
oph | -0.349 |
Girl | -0.338 |
Token | selfish |
Token ID | 20363 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
chick | +0.162 |
shower | +0.160 |
bug | +0.153 |
lyss | +0.149 |
sip | +0.148 |
Neg logit contributions | |
helmets | -0.149 |
hard | -0.144 |
himself | -0.142 |
numbers | -0.142 |
skills | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
helmets | +0.007 |
numbers | +0.006 |
skills | +0.006 |
ates | +0.006 |
himself | +0.006 |
Neg logit contributions | |
chick | -0.007 |
bug | -0.007 |
shower | -0.007 |
die | -0.006 |
Lilly | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
helmets | +0.055 |
skills | +0.055 |
numbers | +0.055 |
hard | +0.053 |
hardest | +0.052 |
Neg logit contributions | |
bug | -0.080 |
chick | -0.079 |
shower | -0.075 |
heaven | -0.075 |
lamb | -0.073 |
Token | time |
Token ID | 640 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
chick | +0.017 |
bug | +0.017 |
shower | +0.017 |
Lilly | +0.016 |
heaven | +0.016 |
Neg logit contributions | |
helmets | -0.013 |
numbers | -0.012 |
ates | -0.012 |
skills | -0.012 |
himself | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
shower | +0.004 |
chick | +0.003 |
bug | +0.003 |
Lilly | +0.003 |
heaven | +0.003 |
Neg logit contributions | |
helmets | -0.005 |
ates | -0.004 |
skills | -0.004 |
numbers | -0.004 |
himself | -0.004 |
Token | take |
Token ID | 1011 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
bug | +0.039 |
chick | +0.037 |
pillar | +0.033 |
lyss | +0.033 |
lamb | +0.032 |
Neg logit contributions | |
skills | -0.037 |
helmets | -0.037 |
himself | -0.036 |
hard | -0.036 |
top | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
helmets | +0.009 |
skills | +0.009 |
numbers | +0.008 |
hard | +0.008 |
himself | +0.008 |
Neg logit contributions | |
bug | -0.017 |
chick | -0.016 |
die | -0.014 |
lyss | -0.014 |
lamb | -0.014 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
hard | +0.133 |
lesson | +0.116 |
helmets | +0.116 |
chores | +0.115 |
top | +0.112 |
Neg logit contributions | |
bug | -0.078 |
al | -0.068 |
chick | -0.068 |
ility | -0.059 |
ount | -0.059 |
Token | before |
Token ID | 878 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
bug | +1.054 |
chick | +1.053 |
lamb | +0.968 |
lyss | +0.955 |
die | +0.947 |
Neg logit contributions | |
skills | -0.556 |
helmets | -0.542 |
hard | -0.522 |
himself | -0.480 |
numbers | -0.479 |
Token | bed |
Token ID | 3996 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
bug | +0.142 |
chick | +0.135 |
lyss | +0.122 |
lamb | +0.120 |
shower | +0.119 |
Neg logit contributions | |
helmets | -0.124 |
numbers | -0.117 |
skills | -0.115 |
himself | -0.113 |
hard | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
bug | +0.199 |
chick | +0.195 |
lamb | +0.176 |
lyss | +0.170 |
shower | +0.167 |
Neg logit contributions | |
helmets | -0.122 |
skills | -0.121 |
numbers | -0.116 |
hard | -0.115 |
himself | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
chick | +0.012 |
bug | +0.012 |
lamb | +0.011 |
shower | +0.011 |
heaven | +0.010 |
Neg logit contributions | |
helmets | -0.012 |
numbers | -0.011 |
skills | -0.011 |
himself | -0.011 |
hard | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
chick | +0.048 |
bug | +0.047 |
shower | +0.046 |
heaven | +0.043 |
die | +0.043 |
Neg logit contributions | |
helmets | -0.037 |
numbers | -0.035 |
skills | -0.035 |
ates | -0.035 |
himself | -0.034 |
Token | makes |
Token ID | 1838 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
chick | +0.097 |
bug | +0.096 |
shower | +0.094 |
heaven | +0.088 |
Lilly | +0.088 |
Neg logit contributions | |
helmets | -0.072 |
ates | -0.068 |
skills | -0.067 |
numbers | -0.067 |
himself | -0.065 |
Token | them |
Token ID | 606 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
helmets | +0.193 |
numbers | +0.188 |
himself | +0.186 |
skills | +0.185 |
hard | +0.175 |
Neg logit contributions | |
chick | -0.249 |
bug | -0.247 |
shower | -0.230 |
lyss | -0.228 |
lamb | -0.223 |
Token | stay |
Token ID | 2652 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
chick | +0.159 |
bug | +0.156 |
shower | +0.155 |
heaven | +0.140 |
Lilly | +0.140 |
Neg logit contributions | |
helmets | -0.213 |
ates | -0.202 |
numbers | -0.202 |
skills | -0.201 |
himself | -0.195 |
Token | in |
Token ID | 287 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
chick | +0.264 |
shower | +0.255 |
bug | +0.254 |
heaven | +0.236 |
Lilly | +0.234 |
Neg logit contributions | |
helmets | -0.289 |
numbers | -0.279 |
skills | -0.275 |
ates | -0.274 |
himself | -0.266 |
Token | the |
Token ID | 262 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
chick | +0.042 |
bug | +0.041 |
shower | +0.040 |
lyss | +0.037 |
Lilly | +0.037 |
Neg logit contributions | |
helmets | -0.035 |
numbers | -0.033 |
skills | -0.033 |
ates | -0.032 |
himself | -0.032 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
bug | +0.003 |
chick | +0.002 |
weet | +0.002 |
ring | +0.002 |
oph | +0.002 |
Neg logit contributions | |
hard | -0.005 |
skills | -0.005 |
helmets | -0.005 |
top | -0.005 |
numbers | -0.005 |
Token | until |
Token ID | 1566 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
chick | +0.911 |
bug | +0.894 |
shower | +0.841 |
lyss | +0.830 |
lamb | +0.826 |
Neg logit contributions | |
helmets | -0.678 |
skills | -0.660 |
numbers | -0.643 |
ates | -0.630 |
himself | -0.615 |
Token | they |
Token ID | 484 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
helmets | +0.200 |
numbers | +0.188 |
skills | +0.184 |
himself | +0.181 |
ates | +0.179 |
Neg logit contributions | |
chick | -0.234 |
bug | -0.231 |
shower | -0.216 |
lyss | -0.209 |
lamb | -0.208 |
Token | are |
Token ID | 389 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
chick | +0.100 |
lyss | +0.093 |
Lilly | +0.092 |
bug | +0.088 |
lamb | +0.088 |
Neg logit contributions | |
helmets | -0.102 |
numbers | -0.097 |
hard | -0.096 |
skills | -0.095 |
top | -0.089 |
Token | clean |
Token ID | 3424 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
chick | +0.108 |
bug | +0.106 |
shower | +0.106 |
heaven | +0.098 |
die | +0.098 |
Neg logit contributions | |
helmets | -0.095 |
numbers | -0.089 |
skills | -0.089 |
ates | -0.089 |
himself | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
chick | +0.292 |
shower | +0.285 |
bug | +0.275 |
heaven | +0.266 |
Lilly | +0.264 |
Neg logit contributions | |
helmets | -0.354 |
ates | -0.342 |
numbers | -0.336 |
skills | -0.328 |
hardest | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
chick | +0.060 |
bug | +0.059 |
pillar | +0.056 |
storm | +0.054 |
plet | +0.053 |
Neg logit contributions | |
helmets | -0.031 |
himself | -0.031 |
his | -0.029 |
numbers | -0.029 |
hard | -0.028 |
Token | bathroom |
Token ID | 12436 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
helmets | +0.014 |
numbers | +0.014 |
skills | +0.013 |
top | +0.013 |
hard | +0.012 |
Neg logit contributions | |
bug | -0.014 |
chick | -0.013 |
Lilly | -0.012 |
lyss | -0.012 |
ility | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
chick | +0.425 |
bug | +0.417 |
shower | +0.410 |
Lilly | +0.380 |
heaven | +0.379 |
Neg logit contributions | |
helmets | -0.406 |
numbers | -0.382 |
skills | -0.381 |
ates | -0.380 |
himself | -0.368 |
Token | take |
Token ID | 1011 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
helmets | +0.011 |
himself | +0.010 |
hard | +0.009 |
his | +0.009 |
numbers | +0.009 |
Neg logit contributions | |
chick | -0.010 |
bug | -0.010 |
lyss | -0.009 |
pillar | -0.009 |
oph | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
chick | +0.003 |
bug | +0.003 |
shower | +0.003 |
lyss | +0.003 |
lamb | +0.003 |
Neg logit contributions | |
helmets | -0.002 |
skills | -0.002 |
numbers | -0.002 |
himself | -0.002 |
ates | -0.002 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
hard | +0.108 |
helmets | +0.096 |
lesson | +0.095 |
top | +0.090 |
skills | +0.089 |
Neg logit contributions | |
bug | -0.075 |
chick | -0.068 |
al | -0.066 |
ring | -0.061 |
heaven | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
chick | +0.921 |
bug | +0.889 |
lamb | +0.829 |
lyss | +0.826 |
die | +0.822 |
Neg logit contributions | |
helmets | -0.674 |
skills | -0.648 |
numbers | -0.627 |
ates | -0.616 |
hard | -0.615 |
Token | Then |
Token ID | 3244 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
chick | +0.028 |
bug | +0.027 |
shower | +0.025 |
die | +0.025 |
lyss | +0.025 |
Neg logit contributions | |
helmets | -0.029 |
ates | -0.027 |
himself | -0.026 |
numbers | -0.026 |
skills | -0.024 |
Token | put |
Token ID | 1234 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
helmets | +0.261 |
numbers | +0.247 |
skills | +0.246 |
ates | +0.243 |
himself | +0.242 |
Neg logit contributions | |
chick | -0.133 |
bug | -0.131 |
shower | -0.125 |
heaven | -0.111 |
lyss | -0.111 |
Token | your |
Token ID | 534 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
chick | +0.136 |
bug | +0.133 |
shower | +0.132 |
Lilly | +0.122 |
heaven | +0.122 |
Neg logit contributions | |
helmets | -0.133 |
numbers | -0.126 |
skills | -0.125 |
ates | -0.125 |
himself | -0.121 |
Token | clothes |
Token ID | 8242 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
chick | +0.084 |
bug | +0.083 |
shower | +0.081 |
Lilly | +0.076 |
heaven | +0.076 |
Neg logit contributions | |
helmets | -0.062 |
numbers | -0.058 |
skills | -0.058 |
ates | -0.058 |
himself | -0.055 |
Token | L |
Token ID | 43 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
chick | +0.035 |
bug | +0.034 |
shower | +0.032 |
die | +0.031 |
heaven | +0.030 |
Neg logit contributions | |
helmets | -0.050 |
numbers | -0.048 |
skills | -0.047 |
hard | -0.046 |
himself | -0.046 |
Token | ily |
Token ID | 813 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
chick | +0.190 |
shower | +0.179 |
bug | +0.174 |
lamb | +0.169 |
die | +0.166 |
Neg logit contributions | |
ates | -0.152 |
helmets | -0.151 |
skills | -0.151 |
numbers | -0.149 |
himself | -0.148 |
Token | got |
Token ID | 1392 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
helmets | +0.039 |
numbers | +0.037 |
skills | +0.037 |
ates | +0.037 |
himself | +0.036 |
Neg logit contributions | |
chick | -0.036 |
bug | -0.035 |
shower | -0.034 |
Lilly | -0.032 |
heaven | -0.032 |
Token | in |
Token ID | 287 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
chick | +0.211 |
bug | +0.207 |
shower | +0.205 |
Lilly | +0.190 |
heaven | +0.190 |
Neg logit contributions | |
helmets | -0.186 |
numbers | -0.174 |
ates | -0.174 |
skills | -0.173 |
himself | -0.167 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
chick | +0.034 |
bug | +0.033 |
shower | +0.033 |
Lilly | +0.030 |
heaven | +0.030 |
Neg logit contributions | |
helmets | -0.032 |
numbers | -0.030 |
skills | -0.030 |
ates | -0.030 |
himself | -0.029 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
hard | +0.014 |
best | +0.014 |
skills | +0.014 |
two | +0.013 |
top | +0.013 |
Neg logit contributions | |
bug | -0.008 |
weet | -0.007 |
believe | -0.006 |
chick | -0.006 |
ility | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
chick | +1.031 |
bug | +1.020 |
lamb | +0.938 |
die | +0.919 |
heaven | +0.915 |
Neg logit contributions | |
skills | -0.570 |
helmets | -0.558 |
numbers | -0.539 |
hard | -0.520 |
himself | -0.516 |
Token | started |
Token ID | 2067 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
helmets | +0.026 |
numbers | +0.023 |
skills | +0.023 |
himself | +0.022 |
hard | +0.022 |
Neg logit contributions | |
bug | -0.027 |
chick | -0.027 |
shower | -0.025 |
die | -0.024 |
lyss | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
bug | +0.014 |
chick | +0.014 |
die | +0.012 |
lyss | +0.012 |
heaven | +0.012 |
Neg logit contributions | |
helmets | -0.011 |
skills | -0.010 |
numbers | -0.010 |
hard | -0.010 |
himself | -0.010 |
Token | wash |
Token ID | 13502 |
Feature activation | -7.91e+00 |
Pos logit contributions | |
bug | +0.040 |
chick | +0.039 |
pillar | +0.036 |
lyss | +0.035 |
ount | +0.032 |
Neg logit contributions | |
helmets | -0.042 |
hard | -0.042 |
numbers | -0.040 |
skills | -0.039 |
himself | -0.039 |
Token | herself |
Token ID | 5223 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
chick | +0.506 |
bug | +0.493 |
shower | +0.492 |
Lilly | +0.458 |
heaven | +0.454 |
Neg logit contributions | |
helmets | -0.471 |
numbers | -0.442 |
ates | -0.441 |
skills | -0.440 |
himself | -0.422 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
helmets | +0.202 |
skills | +0.182 |
numbers | +0.171 |
ates | +0.170 |
himself | +0.166 |
Neg logit contributions | |
bug | -0.279 |
chick | -0.273 |
Lilly | -0.263 |
lyss | -0.259 |
Nina | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
chick | +0.088 |
bug | +0.086 |
shower | +0.085 |
heaven | +0.079 |
Lilly | +0.078 |
Neg logit contributions | |
helmets | -0.088 |
numbers | -0.083 |
ates | -0.082 |
skills | -0.082 |
himself | -0.079 |
Token | He |
Token ID | 679 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
chick | +0.053 |
bug | +0.051 |
shower | +0.051 |
lamb | +0.049 |
die | +0.048 |
Neg logit contributions | |
helmets | -0.018 |
himself | -0.017 |
numbers | -0.016 |
skills | -0.016 |
ates | -0.015 |
Token | used |
Token ID | 973 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
helmets | +0.170 |
numbers | +0.160 |
skills | +0.159 |
ates | +0.157 |
himself | +0.154 |
Neg logit contributions | |
chick | -0.170 |
bug | -0.166 |
shower | -0.164 |
heaven | -0.152 |
Lilly | -0.152 |
Token | the |
Token ID | 262 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
helmets | +0.103 |
ates | +0.100 |
skills | +0.094 |
numbers | +0.093 |
hardest | +0.088 |
Neg logit contributions | |
chick | -0.274 |
shower | -0.270 |
bug | -0.269 |
Lilly | -0.258 |
heaven | -0.255 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
bug | +0.002 |
chick | +0.002 |
heaven | +0.002 |
Lilly | +0.002 |
lyss | +0.002 |
Neg logit contributions | |
helmets | -0.004 |
numbers | -0.004 |
skills | -0.004 |
hard | -0.004 |
hardest | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
chick | +0.776 |
bug | +0.767 |
shower | +0.763 |
Lilly | +0.703 |
die | +0.694 |
Neg logit contributions | |
helmets | -0.769 |
ates | -0.729 |
numbers | -0.723 |
skills | -0.717 |
himself | -0.696 |
Token | spray |
Token ID | 11662 |
Feature activation | -8.24e+00 |
Pos logit contributions | |
bug | +0.050 |
chick | +0.049 |
lyss | +0.049 |
pillar | +0.046 |
album | +0.043 |
Neg logit contributions | |
himself | -0.044 |
helmets | -0.041 |
his | -0.040 |
numbers | -0.039 |
skills | -0.038 |
Token | water |
Token ID | 1660 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
chick | +0.517 |
bug | +0.510 |
shower | +0.493 |
lyss | +0.465 |
heaven | +0.464 |
Neg logit contributions | |
helmets | -0.504 |
numbers | -0.476 |
skills | -0.476 |
ates | -0.465 |
himself | -0.462 |
Token | at |
Token ID | 379 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
chick | +0.408 |
bug | +0.401 |
shower | +0.394 |
Lilly | +0.367 |
heaven | +0.367 |
Neg logit contributions | |
helmets | -0.369 |
numbers | -0.346 |
skills | -0.346 |
ates | -0.344 |
himself | -0.334 |
Token | the |
Token ID | 262 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
helmets | +0.081 |
numbers | +0.077 |
skills | +0.076 |
ates | +0.076 |
himself | +0.076 |
Neg logit contributions | |
chick | -0.088 |
bug | -0.086 |
shower | -0.084 |
lyss | -0.079 |
lamb | -0.078 |
Token | ily |
Token ID | 813 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
chick | +0.211 |
shower | +0.195 |
bug | +0.190 |
lamb | +0.188 |
die | +0.183 |
Neg logit contributions | |
ates | -0.149 |
himself | -0.142 |
skills | -0.141 |
helmets | -0.137 |
numbers | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
helmets | +0.024 |
numbers | +0.023 |
skills | +0.022 |
ates | +0.022 |
himself | +0.021 |
Neg logit contributions | |
chick | -0.035 |
bug | -0.034 |
shower | -0.034 |
heaven | -0.032 |
lyss | -0.032 |
Token | time |
Token ID | 640 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
helmets | +0.027 |
himself | +0.026 |
numbers | +0.026 |
his | +0.026 |
not | +0.026 |
Neg logit contributions | |
chick | -0.031 |
andel | -0.029 |
bug | -0.029 |
older | -0.029 |
lyss | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
shower | +0.007 |
bug | +0.007 |
chick | +0.007 |
Lilly | +0.007 |
die | +0.007 |
Neg logit contributions | |
helmets | -0.008 |
ates | -0.007 |
skills | -0.007 |
numbers | -0.007 |
himself | -0.007 |
Token | your |
Token ID | 534 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
helmets | +0.161 |
numbers | +0.150 |
skills | +0.149 |
ates | +0.149 |
himself | +0.144 |
Neg logit contributions | |
chick | -0.197 |
bug | -0.194 |
shower | -0.190 |
Lilly | -0.178 |
heaven | -0.177 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
chick | +0.072 |
shower | +0.072 |
bug | +0.065 |
lamb | +0.064 |
heaven | +0.063 |
Neg logit contributions | |
ates | -0.072 |
bled | -0.071 |
helmets | -0.070 |
himself | -0.068 |
bles | -0.066 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
chick | +0.854 |
bug | +0.831 |
shower | +0.793 |
lamb | +0.762 |
heaven | +0.757 |
Neg logit contributions | |
helmets | -0.726 |
skills | -0.696 |
numbers | -0.689 |
ates | -0.674 |
himself | -0.656 |
Token | Mom |
Token ID | 11254 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
helmets | +0.222 |
himself | +0.216 |
numbers | +0.212 |
skills | +0.210 |
hard | +0.205 |
Neg logit contributions | |
bug | -0.231 |
chick | -0.225 |
shower | -0.210 |
lyss | -0.199 |
lamb | -0.198 |
Token | says |
Token ID | 1139 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
bug | +0.022 |
chick | +0.022 |
shower | +0.022 |
Lilly | +0.020 |
die | +0.020 |
Neg logit contributions | |
helmets | -0.024 |
ates | -0.023 |
skills | -0.023 |
numbers | -0.022 |
himself | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
helmets | +0.087 |
hard | +0.084 |
himself | +0.083 |
numbers | +0.079 |
skills | +0.078 |
Neg logit contributions | |
chick | -0.161 |
bug | -0.157 |
lyss | -0.154 |
lamb | -0.150 |
shower | -0.147 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
bug | +0.016 |
chick | +0.015 |
heaven | +0.015 |
ility | +0.014 |
believe | +0.014 |
Neg logit contributions | |
helmets | -0.008 |
numbers | -0.007 |
hard | -0.007 |
skills | -0.007 |
himself | -0.007 |
Token | popped |
Token ID | 22928 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
helmets | +0.179 |
ates | +0.174 |
numbers | +0.168 |
skills | +0.165 |
himself | +0.161 |
Neg logit contributions | |
chick | -0.175 |
bug | -0.175 |
shower | -0.169 |
sip | -0.157 |
die | -0.156 |
Token | and |
Token ID | 290 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
chick | +0.094 |
bug | +0.092 |
shower | +0.090 |
Lilly | +0.084 |
die | +0.083 |
Neg logit contributions | |
helmets | -0.091 |
ates | -0.087 |
skills | -0.086 |
numbers | -0.086 |
himself | -0.081 |
Token | out |
Token ID | 503 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
helmets | +0.021 |
numbers | +0.020 |
skills | +0.020 |
ates | +0.020 |
himself | +0.019 |
Neg logit contributions | |
chick | -0.019 |
bug | -0.019 |
shower | -0.018 |
heaven | -0.017 |
Lilly | -0.017 |
Token | came |
Token ID | 1625 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
chick | +0.185 |
bug | +0.175 |
shower | +0.175 |
lamb | +0.172 |
heaven | +0.169 |
Neg logit contributions | |
helmets | -0.199 |
skills | -0.196 |
numbers | -0.196 |
himself | -0.191 |
hard | -0.190 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
chick | +0.204 |
bug | +0.204 |
shower | +0.193 |
Lilly | +0.179 |
die | +0.177 |
Neg logit contributions | |
helmets | -0.272 |
ates | -0.264 |
skills | -0.258 |
numbers | -0.256 |
bled | -0.235 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
hard | +0.068 |
numbers | +0.067 |
helmets | +0.066 |
top | +0.062 |
skills | +0.062 |
Neg logit contributions | |
bug | -0.097 |
chick | -0.091 |
heaven | -0.091 |
Nina | -0.089 |
Lilly | -0.089 |
Token | of |
Token ID | 286 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
chick | +0.999 |
lamb | +0.938 |
bug | +0.930 |
heaven | +0.919 |
Nina | +0.888 |
Neg logit contributions | |
skills | -0.594 |
numbers | -0.571 |
helmets | -0.566 |
hard | -0.561 |
top | -0.515 |
Token | pretty |
Token ID | 2495 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
bug | +0.298 |
chick | +0.293 |
shower | +0.271 |
lyss | +0.271 |
lamb | +0.258 |
Neg logit contributions | |
helmets | -0.332 |
numbers | -0.316 |
skills | -0.310 |
himself | -0.304 |
ates | -0.296 |
Token | , |
Token ID | 11 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
bug | +0.139 |
chick | +0.133 |
uf | +0.127 |
die | +0.126 |
itionally | +0.124 |
Neg logit contributions | |
skills | -0.126 |
numbers | -0.119 |
helmets | -0.118 |
top | -0.114 |
hard | -0.109 |
Token | shiny |
Token ID | 22441 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
helmets | +0.024 |
numbers | +0.022 |
skills | +0.022 |
himself | +0.021 |
hard | +0.021 |
Neg logit contributions | |
bug | -0.026 |
chick | -0.026 |
shower | -0.025 |
lyss | -0.024 |
heaven | -0.023 |
Token | things |
Token ID | 1243 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
helmets | +0.207 |
numbers | +0.196 |
skills | +0.196 |
ates | +0.189 |
himself | +0.186 |
Neg logit contributions | |
chick | -0.258 |
bug | -0.256 |
shower | -0.248 |
heaven | -0.235 |
Lilly | -0.233 |
Token | nearby |
Token ID | 6716 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
ates | +0.191 |
helmets | +0.184 |
bled | +0.177 |
numbers | +0.174 |
skills | +0.169 |
Neg logit contributions | |
bug | -0.136 |
shower | -0.133 |
chick | -0.131 |
lamb | -0.120 |
heaven | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
chick | +0.306 |
bug | +0.304 |
shower | +0.300 |
heaven | +0.285 |
Lilly | +0.273 |
Neg logit contributions | |
helmets | -0.339 |
ates | -0.332 |
numbers | -0.319 |
skills | -0.318 |
hardest | -0.310 |
Token | He |
Token ID | 679 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
chick | +0.055 |
bug | +0.054 |
shower | +0.053 |
lamb | +0.050 |
die | +0.050 |
Neg logit contributions | |
helmets | -0.019 |
numbers | -0.017 |
skills | -0.017 |
himself | -0.017 |
ates | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
helmets | +0.187 |
numbers | +0.177 |
skills | +0.176 |
ates | +0.175 |
himself | +0.171 |
Neg logit contributions | |
chick | -0.152 |
bug | -0.148 |
shower | -0.146 |
heaven | -0.134 |
Lilly | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ates | +0.068 |
skills | +0.065 |
hardest | +0.064 |
helmets | +0.063 |
bled | +0.063 |
Neg logit contributions | |
chick | -0.073 |
shower | -0.073 |
bug | -0.072 |
heaven | -0.070 |
bloom | -0.068 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
helmets | +0.069 |
ates | +0.069 |
skills | +0.065 |
numbers | +0.065 |
himself | +0.065 |
Neg logit contributions | |
chick | -0.089 |
shower | -0.088 |
bug | -0.085 |
die | -0.080 |
lamb | -0.080 |
Token | in |
Token ID | 287 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
chick | +0.941 |
bug | +0.913 |
shower | +0.880 |
heaven | +0.848 |
lamb | +0.847 |
Neg logit contributions | |
helmets | -0.651 |
skills | -0.607 |
numbers | -0.604 |
ates | -0.587 |
himself | -0.574 |
Token | his |
Token ID | 465 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
chick | +0.058 |
shower | +0.058 |
bug | +0.057 |
heaven | +0.056 |
Lilly | +0.055 |
Neg logit contributions | |
helmets | -0.017 |
ates | -0.016 |
skills | -0.015 |
numbers | -0.015 |
hardest | -0.014 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
helmets | +0.202 |
skills | +0.182 |
numbers | +0.171 |
ates | +0.170 |
himself | +0.166 |
Neg logit contributions | |
bug | -0.279 |
chick | -0.273 |
Lilly | -0.263 |
lyss | -0.259 |
Nina | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
chick | +0.088 |
bug | +0.086 |
shower | +0.085 |
heaven | +0.079 |
Lilly | +0.078 |
Neg logit contributions | |
helmets | -0.088 |
numbers | -0.083 |
ates | -0.082 |
skills | -0.082 |
himself | -0.079 |
Token | He |
Token ID | 679 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
chick | +0.053 |
bug | +0.051 |
shower | +0.051 |
lamb | +0.049 |
die | +0.048 |
Neg logit contributions | |
helmets | -0.018 |
himself | -0.017 |
numbers | -0.016 |
skills | -0.016 |
ates | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-04 |
Pos logit contributions | |
shower | +0.047 |
chick | +0.047 |
heaven | +0.046 |
bug | +0.046 |
Lilly | +0.044 |
Neg logit contributions | |
helmets | -0.031 |
ates | -0.030 |
skills | -0.028 |
bled | -0.028 |
numbers | -0.028 |
Token | bathroom |
Token ID | 12436 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
helmets | +0.000 |
numbers | +0.000 |
skills | +0.000 |
hard | +0.000 |
himself | +0.000 |
Neg logit contributions | |
bug | -0.000 |
chick | -0.000 |
lyss | -0.000 |
die | -0.000 |
Lilly | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
chick | +0.410 |
bug | +0.409 |
shower | +0.406 |
heaven | +0.378 |
Lilly | +0.373 |
Neg logit contributions | |
helmets | -0.405 |
ates | -0.380 |
numbers | -0.376 |
skills | -0.375 |
himself | -0.359 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
helmets | +0.018 |
ates | +0.017 |
skills | +0.017 |
numbers | +0.017 |
himself | +0.016 |
Neg logit contributions | |
chick | -0.016 |
bug | -0.015 |
shower | -0.015 |
heaven | -0.014 |
Lilly | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
helmets | +0.006 |
ates | +0.006 |
numbers | +0.006 |
skills | +0.006 |
himself | +0.005 |
Neg logit contributions | |
chick | -0.008 |
bug | -0.008 |
shower | -0.008 |
Lilly | -0.008 |
heaven | -0.007 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
bug | +0.002 |
chick | +0.002 |
lyss | +0.002 |
die | +0.002 |
Lilly | +0.002 |
Neg logit contributions | |
numbers | -0.002 |
helmets | -0.002 |
skills | -0.002 |
himself | -0.002 |
hard | -0.002 |
Token | curtain |
Token ID | 29461 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
chick | +0.879 |
bug | +0.854 |
shower | +0.835 |
lamb | +0.791 |
heaven | +0.788 |
Neg logit contributions | |
helmets | -0.693 |
numbers | -0.659 |
skills | -0.659 |
ates | -0.648 |
himself | -0.634 |
Token | . |
Token ID | 13 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
chick | +0.356 |
bug | +0.348 |
shower | +0.343 |
Lilly | +0.321 |
heaven | +0.319 |
Neg logit contributions | |
helmets | -0.295 |
numbers | -0.277 |
skills | -0.276 |
ates | -0.274 |
himself | -0.266 |
Token | He |
Token ID | 679 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
chick | +0.049 |
bug | +0.048 |
shower | +0.048 |
lamb | +0.045 |
die | +0.045 |
Neg logit contributions | |
helmets | -0.027 |
numbers | -0.025 |
ates | -0.024 |
himself | -0.024 |
skills | -0.024 |
Token | could |
Token ID | 714 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
helmets | +0.166 |
numbers | +0.156 |
skills | +0.154 |
ates | +0.153 |
himself | +0.150 |
Neg logit contributions | |
chick | -0.177 |
bug | -0.171 |
shower | -0.170 |
heaven | -0.159 |
Lilly | -0.158 |
Token | see |
Token ID | 766 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
chick | +0.228 |
bug | +0.226 |
shower | +0.224 |
Lilly | +0.211 |
heaven | +0.211 |
Neg logit contributions | |
helmets | -0.100 |
ates | -0.091 |
numbers | -0.091 |
skills | -0.090 |
himself | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
helmets | +0.390 |
numbers | +0.370 |
skills | +0.361 |
ates | +0.338 |
himself | +0.337 |
Neg logit contributions | |
chick | -0.594 |
bug | -0.588 |
shower | -0.573 |
Lilly | -0.545 |
heaven | -0.543 |
Token | They |
Token ID | 1119 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
chick | +0.018 |
shower | +0.018 |
bug | +0.017 |
die | +0.017 |
sip | +0.016 |
Neg logit contributions | |
helmets | -0.018 |
numbers | -0.017 |
himself | -0.017 |
ates | -0.016 |
skills | -0.015 |
Token | are |
Token ID | 389 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
chick | +0.068 |
bug | +0.064 |
shower | +0.064 |
lyss | +0.064 |
Lilly | +0.063 |
Neg logit contributions | |
helmets | -0.056 |
numbers | -0.055 |
skills | -0.052 |
hard | -0.051 |
himself | -0.049 |
Token | like |
Token ID | 588 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
chick | +0.099 |
bug | +0.098 |
shower | +0.097 |
lyss | +0.091 |
heaven | +0.090 |
Neg logit contributions | |
helmets | -0.083 |
numbers | -0.078 |
ates | -0.076 |
skills | -0.075 |
himself | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
bug | +0.227 |
chick | +0.220 |
shower | +0.213 |
lyss | +0.209 |
sip | +0.206 |
Neg logit contributions | |
helmets | -0.170 |
numbers | -0.160 |
skills | -0.150 |
hard | -0.144 |
himself | -0.143 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
helmets | +0.104 |
numbers | +0.100 |
skills | +0.097 |
hard | +0.096 |
hardest | +0.091 |
Neg logit contributions | |
bug | -0.085 |
chick | -0.082 |
shower | -0.079 |
heaven | -0.078 |
Lilly | -0.077 |
Token | ," |
Token ID | 553 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
chick | +0.950 |
bug | +0.927 |
lamb | +0.872 |
heaven | +0.860 |
shower | +0.860 |
Neg logit contributions | |
helmets | -0.635 |
numbers | -0.611 |
skills | -0.609 |
hard | -0.579 |
ates | -0.563 |
Token | Jen |
Token ID | 13364 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
helmets | +0.339 |
ates | +0.333 |
skills | +0.327 |
numbers | +0.323 |
bled | +0.315 |
Neg logit contributions | |
chick | -0.170 |
bug | -0.167 |
shower | -0.163 |
Lilly | -0.152 |
heaven | -0.146 |
Token | said |
Token ID | 531 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
helmets | +0.082 |
numbers | +0.077 |
skills | +0.077 |
ates | +0.077 |
himself | +0.075 |
Neg logit contributions | |
chick | -0.073 |
bug | -0.072 |
shower | -0.070 |
Lilly | -0.065 |
heaven | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
chick | +0.018 |
bug | +0.018 |
shower | +0.017 |
Lilly | +0.016 |
heaven | +0.016 |
Neg logit contributions | |
helmets | -0.021 |
ates | -0.020 |
numbers | -0.020 |
skills | -0.020 |
himself | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
chick | +0.019 |
bug | +0.019 |
shower | +0.019 |
Lilly | +0.018 |
Nina | +0.017 |
Neg logit contributions | |
helmets | -0.025 |
ates | -0.024 |
skills | -0.024 |
hardest | -0.023 |
numbers | -0.023 |
Token | outside |
Token ID | 2354 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
chick | +0.179 |
bug | +0.174 |
lyss | +0.162 |
shower | +0.158 |
heaven | +0.156 |
Neg logit contributions | |
helmets | -0.161 |
himself | -0.156 |
hard | -0.151 |
skills | -0.147 |
numbers | -0.146 |
Token | until |
Token ID | 1566 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
chick | +0.353 |
bug | +0.347 |
shower | +0.341 |
Lilly | +0.317 |
heaven | +0.316 |
Neg logit contributions | |
helmets | -0.308 |
numbers | -0.289 |
skills | -0.289 |
ates | -0.287 |
himself | -0.280 |
Token | he |
Token ID | 339 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
helmets | +0.179 |
ates | +0.168 |
numbers | +0.168 |
skills | +0.167 |
himself | +0.158 |
Neg logit contributions | |
chick | -0.247 |
bug | -0.243 |
shower | -0.243 |
Lilly | -0.228 |
heaven | -0.226 |
Token | took |
Token ID | 1718 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
skills | +0.135 |
himself | +0.134 |
helmets | +0.134 |
hard | +0.133 |
numbers | +0.129 |
Neg logit contributions | |
chick | -0.240 |
shower | -0.226 |
lamb | -0.222 |
heaven | -0.217 |
bug | -0.216 |
Token | a |
Token ID | 257 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
helmets | +0.035 |
numbers | +0.032 |
skills | +0.032 |
ates | +0.032 |
himself | +0.031 |
Neg logit contributions | |
chick | -0.073 |
bug | -0.073 |
shower | -0.071 |
heaven | -0.067 |
Lilly | -0.067 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
hard | +0.104 |
helmets | +0.097 |
helmet | +0.090 |
top | +0.089 |
sled | +0.087 |
Neg logit contributions | |
bug | -0.095 |
al | -0.091 |
chick | -0.088 |
ring | -0.088 |
ount | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
chick | +0.999 |
bug | +0.971 |
lamb | +0.912 |
lyss | +0.908 |
die | +0.900 |
Neg logit contributions | |
helmets | -0.617 |
skills | -0.609 |
hard | -0.570 |
himself | -0.559 |
numbers | -0.559 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
chick | +0.015 |
bug | +0.015 |
shower | +0.015 |
heaven | +0.014 |
lamb | +0.014 |
Neg logit contributions | |
helmets | -0.014 |
numbers | -0.013 |
skills | -0.013 |
ates | -0.013 |
himself | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
bug | +0.020 |
chick | +0.018 |
shower | +0.017 |
Lilly | +0.016 |
heaven | +0.015 |
Neg logit contributions | |
helmets | -0.041 |
numbers | -0.038 |
ates | -0.038 |
skills | -0.038 |
bled | -0.038 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
helmets | +0.166 |
skills | +0.155 |
numbers | +0.154 |
ates | +0.150 |
himself | +0.148 |
Neg logit contributions | |
chick | -0.191 |
bug | -0.188 |
shower | -0.185 |
heaven | -0.175 |
die | -0.173 |
Token | 't |
Token ID | 470 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
helmets | +0.035 |
ates | +0.032 |
numbers | +0.032 |
skills | +0.032 |
himself | +0.030 |
Neg logit contributions | |
shower | -0.039 |
chick | -0.037 |
bug | -0.037 |
Lilly | -0.035 |
die | -0.035 |
Token | You |
Token ID | 1639 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
helmets | +0.063 |
numbers | +0.059 |
skills | +0.059 |
ates | +0.059 |
himself | +0.058 |
Neg logit contributions | |
chick | -0.056 |
bug | -0.055 |
shower | -0.054 |
Lilly | -0.050 |
heaven | -0.050 |
Token | have |
Token ID | 423 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
helmets | +0.129 |
numbers | +0.123 |
hard | +0.117 |
skills | +0.116 |
hardest | +0.116 |
Neg logit contributions | |
chick | -0.129 |
bug | -0.128 |
shower | -0.118 |
heaven | -0.116 |
lyss | -0.116 |
Token | to |
Token ID | 284 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
helmets | +0.074 |
numbers | +0.070 |
skills | +0.068 |
ates | +0.066 |
himself | +0.066 |
Neg logit contributions | |
chick | -0.081 |
bug | -0.080 |
shower | -0.075 |
lamb | -0.072 |
die | -0.071 |
Token | take |
Token ID | 1011 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
bug | +0.050 |
chick | +0.050 |
lyss | +0.043 |
pillar | +0.043 |
lamb | +0.042 |
Neg logit contributions | |
helmets | -0.051 |
himself | -0.050 |
hard | -0.050 |
skills | -0.050 |
numbers | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
chick | +0.008 |
bug | +0.008 |
shower | +0.008 |
Lilly | +0.007 |
die | +0.007 |
Neg logit contributions | |
helmets | -0.006 |
numbers | -0.006 |
skills | -0.006 |
ates | -0.005 |
himself | -0.005 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
hard | +0.117 |
lesson | +0.107 |
top | +0.098 |
skills | +0.094 |
long | +0.093 |
Neg logit contributions | |
bug | -0.058 |
al | -0.048 |
chick | -0.048 |
ring | -0.044 |
ility | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
chick | +0.953 |
bug | +0.928 |
shower | +0.860 |
lamb | +0.859 |
lyss | +0.852 |
Neg logit contributions | |
helmets | -0.633 |
skills | -0.617 |
numbers | -0.599 |
ates | -0.578 |
himself | -0.577 |
Token | Mia |
Token ID | 32189 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
helmets | +0.016 |
numbers | +0.016 |
himself | +0.015 |
skills | +0.015 |
hard | +0.014 |
Neg logit contributions | |
chick | -0.015 |
bug | -0.014 |
shower | -0.014 |
lyss | -0.014 |
lamb | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
chick | +0.134 |
bug | +0.132 |
shower | +0.129 |
heaven | +0.120 |
Lilly | +0.120 |
Neg logit contributions | |
helmets | -0.125 |
numbers | -0.117 |
ates | -0.117 |
skills | -0.117 |
himself | -0.113 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
helmets | +0.008 |
numbers | +0.008 |
himself | +0.008 |
skills | +0.008 |
ates | +0.008 |
Neg logit contributions | |
chick | -0.007 |
shower | -0.006 |
bug | -0.006 |
lyss | -0.006 |
lamb | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
chick | +0.097 |
bug | +0.095 |
shower | +0.093 |
Lilly | +0.087 |
heaven | +0.087 |
Neg logit contributions | |
helmets | -0.076 |
numbers | -0.071 |
skills | -0.071 |
ates | -0.070 |
himself | -0.068 |
Token | bathroom |
Token ID | 12436 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
bug | +0.003 |
chick | +0.003 |
Lilly | +0.003 |
lyss | +0.003 |
Nina | +0.002 |
Neg logit contributions | |
helmets | -0.002 |
numbers | -0.002 |
skills | -0.002 |
himself | -0.002 |
hard | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
chick | +0.416 |
bug | +0.413 |
shower | +0.410 |
heaven | +0.381 |
die | +0.376 |
Neg logit contributions | |
helmets | -0.409 |
ates | -0.391 |
numbers | -0.384 |
skills | -0.381 |
himself | -0.366 |
Token | turned |
Token ID | 2900 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
helmets | +0.005 |
himself | +0.004 |
numbers | +0.004 |
his | +0.004 |
hard | +0.004 |
Neg logit contributions | |
chick | -0.006 |
shower | -0.005 |
bug | -0.005 |
lyss | -0.005 |
lamb | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
shower | +0.206 |
chick | +0.201 |
bug | +0.197 |
Lilly | +0.189 |
sip | +0.188 |
Neg logit contributions | |
ates | -0.183 |
helmets | -0.177 |
numbers | -0.168 |
skills | -0.167 |
bles | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
ates | +0.413 |
helmets | +0.405 |
skills | +0.388 |
bled | +0.383 |
numbers | +0.380 |
Neg logit contributions | |
chick | -0.383 |
shower | -0.383 |
bug | -0.367 |
Lilly | -0.358 |
heaven | -0.357 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
bug | +0.004 |
chick | +0.004 |
shower | +0.004 |
lyss | +0.004 |
Lilly | +0.004 |
Neg logit contributions | |
helmets | -0.004 |
numbers | -0.004 |
skills | -0.004 |
himself | -0.003 |
ates | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
chick | +0.906 |
bug | +0.877 |
shower | +0.834 |
lamb | +0.830 |
lyss | +0.822 |
Neg logit contributions | |
helmets | -0.682 |
skills | -0.660 |
numbers | -0.656 |
himself | -0.625 |
ates | -0.622 |
Token | She |
Token ID | 1375 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
chick | +0.032 |
bug | +0.031 |
shower | +0.030 |
lyss | +0.027 |
lamb | +0.027 |
Neg logit contributions | |
helmets | -0.044 |
numbers | -0.042 |
skills | -0.042 |
ates | -0.041 |
himself | -0.041 |
Token | put |
Token ID | 1234 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
chick | +0.101 |
bug | +0.099 |
shower | +0.098 |
Lilly | +0.091 |
heaven | +0.091 |
Neg logit contributions | |
helmets | -0.094 |
numbers | -0.088 |
skills | -0.088 |
ates | -0.088 |
himself | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
chick | +0.106 |
bug | +0.104 |
shower | +0.104 |
Lilly | +0.102 |
sip | +0.098 |
Neg logit contributions | |
icycle | -0.159 |
zag | -0.155 |
ates | -0.155 |
ikes | -0.154 |
helmets | -0.152 |
Token | spider |
Token ID | 19230 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
chick | +0.004 |
bug | +0.004 |
shower | +0.004 |
heaven | +0.004 |
Lilly | +0.004 |
Neg logit contributions | |
helmets | -0.008 |
ates | -0.007 |
numbers | -0.007 |
skills | -0.007 |
himself | -0.007 |
Token | No |
Token ID | 2949 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
helmets | +0.248 |
numbers | +0.230 |
skills | +0.224 |
himself | +0.222 |
ates | +0.219 |
Neg logit contributions | |
bug | -0.255 |
chick | -0.255 |
shower | -0.245 |
Lilly | -0.233 |
heaven | -0.232 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
helmets | +0.225 |
ates | +0.214 |
skills | +0.210 |
numbers | +0.209 |
himself | +0.203 |
Neg logit contributions | |
chick | -0.272 |
shower | -0.268 |
bug | -0.263 |
Lilly | -0.247 |
heaven | -0.245 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
helmets | +0.018 |
numbers | +0.017 |
hard | +0.016 |
himself | +0.016 |
skills | +0.015 |
Neg logit contributions | |
bug | -0.019 |
chick | -0.018 |
lyss | -0.018 |
heaven | -0.017 |
lamb | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
helmets | +0.168 |
numbers | +0.159 |
skills | +0.157 |
ates | +0.154 |
himself | +0.149 |
Neg logit contributions | |
chick | -0.238 |
bug | -0.232 |
shower | -0.231 |
lamb | -0.216 |
Lilly | -0.216 |
Token | no |
Token ID | 645 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
helmets | +0.019 |
hard | +0.018 |
numbers | +0.018 |
himself | +0.017 |
two | +0.017 |
Neg logit contributions | |
bug | -0.018 |
chick | -0.017 |
ount | -0.017 |
ilt | -0.016 |
lyss | -0.016 |
Token | shower |
Token ID | 14643 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
helmets | +0.167 |
numbers | +0.160 |
skills | +0.156 |
himself | +0.148 |
hard | +0.146 |
Neg logit contributions | |
chick | -0.228 |
bug | -0.227 |
shower | -0.209 |
lyss | -0.204 |
lamb | -0.204 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
chick | +0.848 |
bug | +0.830 |
shower | +0.805 |
heaven | +0.760 |
lamb | +0.755 |
Neg logit contributions | |
helmets | -0.722 |
numbers | -0.682 |
skills | -0.679 |
ates | -0.669 |
himself | -0.650 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
helmets | +0.199 |
numbers | +0.188 |
himself | +0.185 |
skills | +0.181 |
hard | +0.177 |
Neg logit contributions | |
chick | -0.231 |
bug | -0.228 |
shower | -0.212 |
lamb | -0.208 |
lyss | -0.207 |
Token | said |
Token ID | 531 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
chick | +0.086 |
bug | +0.084 |
shower | +0.084 |
heaven | +0.078 |
Lilly | +0.078 |
Neg logit contributions | |
helmets | -0.085 |
numbers | -0.080 |
skills | -0.079 |
ates | -0.078 |
himself | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
chick | +0.035 |
bug | +0.034 |
shower | +0.034 |
Lilly | +0.031 |
heaven | +0.031 |
Neg logit contributions | |
helmets | -0.037 |
ates | -0.035 |
numbers | -0.035 |
skills | -0.034 |
himself | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
chick | +0.032 |
shower | +0.032 |
bug | +0.031 |
Lilly | +0.029 |
sip | +0.029 |
Neg logit contributions | |
helmets | -0.046 |
ates | -0.046 |
skills | -0.043 |
hardest | -0.043 |
numbers | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
helmets | +0.127 |
numbers | +0.118 |
skills | +0.118 |
hardest | +0.113 |
ates | +0.112 |
Neg logit contributions | |
bug | -0.102 |
chick | -0.099 |
shower | -0.098 |
Lilly | -0.096 |
Nina | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
chick | +0.045 |
shower | +0.045 |
bug | +0.045 |
Lilly | +0.043 |
Nina | +0.042 |
Neg logit contributions | |
helmets | -0.053 |
numbers | -0.050 |
skills | -0.049 |
ates | -0.048 |
hardest | -0.048 |
Token | From |
Token ID | 4863 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
chick | +0.052 |
shower | +0.051 |
bug | +0.051 |
Lilly | +0.048 |
heaven | +0.047 |
Neg logit contributions | |
helmets | -0.044 |
numbers | -0.042 |
ates | -0.041 |
skills | -0.041 |
hardest | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
helmets | +0.371 |
numbers | +0.356 |
ates | +0.356 |
skills | +0.355 |
himself | +0.345 |
Neg logit contributions | |
chick | -0.177 |
bug | -0.171 |
shower | -0.168 |
Lilly | -0.149 |
heaven | -0.147 |
Token | day |
Token ID | 1110 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
shower | +0.335 |
chick | +0.324 |
Lilly | +0.298 |
bug | +0.294 |
sip | +0.286 |
Neg logit contributions | |
helmets | -0.394 |
ates | -0.372 |
bles | -0.357 |
numbers | -0.351 |
bled | -0.345 |
Token | on |
Token ID | 319 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
helmets | +0.083 |
numbers | +0.082 |
skills | +0.075 |
himself | +0.071 |
ates | +0.070 |
Neg logit contributions | |
shower | -0.162 |
chick | -0.153 |
Lilly | -0.149 |
bug | -0.147 |
ful | -0.146 |
Token | , |
Token ID | 11 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
helmets | +0.403 |
ates | +0.383 |
numbers | +0.380 |
skills | +0.372 |
himself | +0.359 |
Neg logit contributions | |
shower | -0.428 |
chick | -0.426 |
bug | -0.410 |
Lilly | -0.403 |
Nina | -0.387 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
helmets | +0.037 |
numbers | +0.035 |
skills | +0.035 |
ates | +0.034 |
himself | +0.034 |
Neg logit contributions | |
chick | -0.027 |
bug | -0.026 |
shower | -0.026 |
die | -0.023 |
heaven | -0.023 |
Token | made |
Token ID | 925 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
chick | +0.205 |
bug | +0.201 |
shower | +0.184 |
Lilly | +0.180 |
bloom | +0.178 |
Neg logit contributions | |
helmets | -0.304 |
ates | -0.273 |
numbers | -0.269 |
bled | -0.259 |
balls | -0.258 |
Token | sure |
Token ID | 1654 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
helmets | +0.061 |
ates | +0.059 |
numbers | +0.057 |
skills | +0.056 |
hardest | +0.055 |
Neg logit contributions | |
chick | -0.041 |
shower | -0.039 |
bug | -0.037 |
Lilly | -0.037 |
heaven | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
chick | +0.109 |
bug | +0.107 |
shower | +0.103 |
sip | +0.096 |
heaven | +0.096 |
Neg logit contributions | |
helmets | -0.109 |
numbers | -0.103 |
skills | -0.103 |
himself | -0.101 |
ates | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
helmets | +0.173 |
ates | +0.167 |
numbers | +0.164 |
skills | +0.159 |
hardest | +0.151 |
Neg logit contributions | |
chick | -0.158 |
bug | -0.154 |
shower | -0.145 |
Lilly | -0.142 |
Nina | -0.139 |
Token | said |
Token ID | 531 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
helmets | +0.027 |
numbers | +0.025 |
skills | +0.025 |
ates | +0.025 |
himself | +0.024 |
Neg logit contributions | |
chick | -0.026 |
bug | -0.025 |
shower | -0.025 |
heaven | -0.023 |
Lilly | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
bug | +0.014 |
chick | +0.013 |
Lilly | +0.012 |
ful | +0.012 |
Nina | +0.012 |
Neg logit contributions | |
helmets | -0.019 |
ates | -0.018 |
icycle | -0.017 |
numbers | -0.017 |
ep | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
helmets | +0.034 |
ates | +0.033 |
skills | +0.032 |
numbers | +0.032 |
gears | +0.030 |
Neg logit contributions | |
chick | -0.034 |
bug | -0.033 |
shower | -0.032 |
Lilly | -0.032 |
Nina | -0.031 |
Token | Good |
Token ID | 10248 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
helmets | +0.089 |
ates | +0.084 |
numbers | +0.084 |
skills | +0.083 |
himself | +0.080 |
Neg logit contributions | |
chick | -0.067 |
bug | -0.067 |
shower | -0.063 |
Lilly | -0.060 |
lyss | -0.060 |
Token | luck |
Token ID | 8458 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
helmets | +0.151 |
ates | +0.143 |
bled | +0.134 |
numbers | +0.134 |
skills | +0.131 |
Neg logit contributions | |
chick | -0.179 |
shower | -0.171 |
bug | -0.170 |
lamb | -0.160 |
Lilly | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
helmets | +0.461 |
numbers | +0.414 |
ates | +0.411 |
skills | +0.410 |
himself | +0.391 |
Neg logit contributions | |
chick | -0.315 |
bug | -0.311 |
shower | -0.307 |
Lilly | -0.276 |
Nina | -0.275 |
Token | little |
Token ID | 1310 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
helmets | +0.038 |
numbers | +0.037 |
himself | +0.036 |
skills | +0.036 |
ates | +0.035 |
Neg logit contributions | |
bug | -0.028 |
chick | -0.028 |
shower | -0.027 |
sip | -0.025 |
heaven | -0.025 |
Token | one |
Token ID | 530 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
chick | +0.252 |
bug | +0.236 |
shower | +0.229 |
lamb | +0.217 |
Lilly | +0.211 |
Neg logit contributions | |
helmets | -0.376 |
ates | -0.366 |
skills | -0.357 |
numbers | -0.357 |
bled | -0.345 |
Token | . |
Token ID | 13 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
helmets | +0.324 |
numbers | +0.304 |
skills | +0.303 |
ates | +0.303 |
himself | +0.294 |
Neg logit contributions | |
chick | -0.318 |
bug | -0.313 |
shower | -0.308 |
Lilly | -0.284 |
heaven | -0.284 |
Token | I |
Token ID | 314 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
chick | +0.014 |
bug | +0.013 |
shower | +0.013 |
heaven | +0.012 |
die | +0.012 |
Neg logit contributions | |
helmets | -0.022 |
numbers | -0.021 |
ates | -0.021 |
skills | -0.021 |
himself | -0.021 |
Token | he |
Token ID | 339 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
helmets | +0.032 |
ates | +0.030 |
numbers | +0.030 |
skills | +0.030 |
himself | +0.028 |
Neg logit contributions | |
chick | -0.032 |
bug | -0.032 |
shower | -0.031 |
Lilly | -0.029 |
heaven | -0.029 |
Token | 'd |
Token ID | 1549 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
helmets | +0.185 |
ates | +0.174 |
numbers | +0.174 |
skills | +0.172 |
himself | +0.167 |
Neg logit contributions | |
chick | -0.177 |
bug | -0.176 |
shower | -0.171 |
Lilly | -0.159 |
heaven | -0.157 |
Token | done |
Token ID | 1760 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
helmets | +0.066 |
numbers | +0.063 |
skills | +0.063 |
himself | +0.062 |
ates | +0.062 |
Neg logit contributions | |
chick | -0.065 |
bug | -0.062 |
shower | -0.060 |
lamb | -0.057 |
lyss | -0.056 |
Token | all |
Token ID | 477 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
helmets | +0.249 |
ates | +0.239 |
bles | +0.232 |
hardest | +0.227 |
numbers | +0.227 |
Neg logit contributions | |
shower | -0.201 |
Lilly | -0.200 |
Nina | -0.200 |
heaven | -0.191 |
lyss | -0.180 |
Token | his |
Token ID | 465 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
helmets | +0.207 |
skills | +0.197 |
numbers | +0.195 |
himself | +0.192 |
ates | +0.190 |
Neg logit contributions | |
chick | -0.338 |
bug | -0.327 |
shower | -0.321 |
lamb | -0.304 |
heaven | -0.303 |
Token | chores |
Token ID | 46173 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
helmets | +0.199 |
ates | +0.187 |
numbers | +0.179 |
bled | +0.178 |
himself | +0.177 |
Neg logit contributions | |
shower | -0.278 |
chick | -0.272 |
bug | -0.266 |
heaven | -0.253 |
sip | -0.251 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
helmets | +0.487 |
ates | +0.457 |
numbers | +0.456 |
skills | +0.451 |
himself | +0.434 |
Neg logit contributions | |
chick | -0.490 |
bug | -0.486 |
shower | -0.483 |
Lilly | -0.451 |
heaven | -0.445 |
Token | he |
Token ID | 339 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
helmets | +0.026 |
ates | +0.024 |
numbers | +0.024 |
skills | +0.024 |
himself | +0.023 |
Neg logit contributions | |
chick | -0.029 |
shower | -0.029 |
bug | -0.029 |
Lilly | -0.027 |
heaven | -0.026 |
Token | hadn |
Token ID | 8020 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
helmets | +0.190 |
ates | +0.179 |
numbers | +0.178 |
skills | +0.175 |
himself | +0.170 |
Neg logit contributions | |
chick | -0.170 |
bug | -0.170 |
shower | -0.164 |
Lilly | -0.153 |
heaven | -0.151 |
Token | 't |
Token ID | 470 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
chick | +0.084 |
bug | +0.084 |
shower | +0.083 |
Lilly | +0.078 |
heaven | +0.077 |
Neg logit contributions | |
helmets | -0.071 |
numbers | -0.066 |
skills | -0.066 |
ates | -0.065 |
himself | -0.062 |
Token | even |
Token ID | 772 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
numbers | +0.245 |
himself | +0.243 |
helmets | +0.240 |
skills | +0.238 |
hard | +0.233 |
Neg logit contributions | |
chick | -0.313 |
bug | -0.293 |
shower | -0.280 |
lamb | -0.276 |
kitten | -0.263 |
Token | came |
Token ID | 1625 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
chick | +0.051 |
Lilly | +0.048 |
heaven | +0.047 |
bug | +0.047 |
shower | +0.047 |
Neg logit contributions | |
helmets | -0.051 |
skills | -0.050 |
ates | -0.050 |
numbers | -0.049 |
bled | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
chick | +0.257 |
bug | +0.251 |
shower | +0.248 |
Lilly | +0.229 |
die | +0.229 |
Neg logit contributions | |
helmets | -0.237 |
ates | -0.223 |
numbers | -0.222 |
skills | -0.220 |
himself | -0.212 |
Token | blew |
Token ID | 17948 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
helmets | +0.007 |
ates | +0.006 |
skills | +0.006 |
numbers | +0.006 |
himself | +0.006 |
Neg logit contributions | |
chick | -0.007 |
bug | -0.007 |
shower | -0.007 |
Lilly | -0.006 |
heaven | -0.006 |
Token | away |
Token ID | 1497 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
chick | +0.000 |
shower | +0.000 |
bug | +0.000 |
Lilly | +0.000 |
heaven | +0.000 |
Neg logit contributions | |
helmets | -0.000 |
ates | -0.000 |
skills | -0.000 |
numbers | -0.000 |
himself | -0.000 |
Token | their |
Token ID | 511 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
chick | +0.239 |
bug | +0.236 |
shower | +0.231 |
heaven | +0.215 |
lyss | +0.215 |
Neg logit contributions | |
helmets | -0.188 |
numbers | -0.177 |
skills | -0.176 |
ates | -0.174 |
himself | -0.172 |
Token | structures |
Token ID | 8573 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
shower | +0.266 |
chick | +0.255 |
bug | +0.254 |
die | +0.247 |
sip | +0.242 |
Neg logit contributions | |
ates | -0.172 |
himself | -0.162 |
helmets | -0.161 |
bled | -0.158 |
numbers | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
helmets | +0.351 |
skills | +0.334 |
numbers | +0.327 |
himself | +0.317 |
ates | +0.317 |
Neg logit contributions | |
chick | -0.438 |
bug | -0.418 |
shower | -0.414 |
lyss | -0.402 |
Lilly | -0.399 |
Token | The |
Token ID | 383 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
bug | +0.045 |
chick | +0.044 |
lamb | +0.042 |
shower | +0.040 |
lyss | +0.038 |
Neg logit contributions | |
helmets | -0.035 |
himself | -0.034 |
numbers | -0.034 |
skills | -0.033 |
ates | -0.031 |
Token | sticks |
Token ID | 16461 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
shower | +0.060 |
bug | +0.058 |
chick | +0.057 |
die | +0.053 |
sip | +0.052 |
Neg logit contributions | |
ates | -0.065 |
helmets | -0.062 |
himself | -0.059 |
bled | -0.059 |
z | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
helmets | +0.380 |
skills | +0.358 |
numbers | +0.357 |
ates | +0.354 |
himself | +0.345 |
Neg logit contributions | |
chick | -0.394 |
bug | -0.386 |
shower | -0.380 |
Lilly | -0.354 |
heaven | -0.353 |
Token | stones |
Token ID | 14966 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
helmets | +0.014 |
numbers | +0.013 |
skills | +0.012 |
ates | +0.012 |
himself | +0.012 |
Neg logit contributions | |
chick | -0.019 |
bug | -0.018 |
shower | -0.018 |
heaven | -0.017 |
Lilly | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
chick | +0.070 |
bug | +0.069 |
shower | +0.068 |
lyss | +0.065 |
heaven | +0.064 |
Neg logit contributions | |
helmets | -0.039 |
numbers | -0.037 |
skills | -0.037 |
himself | -0.035 |
ates | -0.035 |
Token | big |
Token ID | 1263 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
helmets | +0.080 |
numbers | +0.078 |
skills | +0.076 |
hard | +0.076 |
hardest | +0.071 |
Neg logit contributions | |
bug | -0.101 |
chick | -0.098 |
heaven | -0.093 |
ount | -0.092 |
Lilly | -0.092 |
Token | rock |
Token ID | 3881 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
helmets | +0.056 |
numbers | +0.054 |
skills | +0.053 |
hard | +0.052 |
helmet | +0.047 |
Neg logit contributions | |
bug | -0.064 |
chick | -0.064 |
ount | -0.061 |
die | -0.058 |
heaven | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
helmets | +0.031 |
skills | +0.029 |
himself | +0.028 |
numbers | +0.027 |
ates | +0.027 |
Neg logit contributions | |
chick | -0.043 |
shower | -0.040 |
bug | -0.040 |
lyss | -0.040 |
Lilly | -0.040 |
Token | sit |
Token ID | 1650 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
chick | +0.030 |
bug | +0.029 |
shower | +0.027 |
lyss | +0.026 |
lamb | +0.026 |
Neg logit contributions | |
helmets | -0.041 |
skills | -0.039 |
numbers | -0.039 |
himself | -0.039 |
ates | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
chick | +0.213 |
bug | +0.212 |
shower | +0.199 |
lamb | +0.194 |
Lilly | +0.194 |
Neg logit contributions | |
numbers | -0.153 |
helmets | -0.153 |
skills | -0.145 |
ates | -0.137 |
hardest | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
helmets | +0.353 |
numbers | +0.330 |
skills | +0.330 |
himself | +0.326 |
ates | +0.317 |
Neg logit contributions | |
chick | -0.478 |
bug | -0.478 |
shower | -0.459 |
lyss | -0.441 |
die | -0.433 |
Token | She |
Token ID | 1375 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
bug | +0.006 |
chick | +0.005 |
shower | +0.005 |
die | +0.005 |
heaven | +0.005 |
Neg logit contributions | |
helmets | -0.005 |
numbers | -0.005 |
skills | -0.005 |
himself | -0.005 |
ates | -0.005 |
Token | put |
Token ID | 1234 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
bug | +0.054 |
chick | +0.054 |
shower | +0.052 |
Lilly | +0.048 |
lyss | +0.048 |
Neg logit contributions | |
helmets | -0.064 |
ates | -0.061 |
numbers | -0.061 |
skills | -0.061 |
himself | -0.058 |
Token | her |
Token ID | 607 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
chick | +0.130 |
bug | +0.129 |
shower | +0.127 |
Lilly | +0.127 |
Nina | +0.123 |
Neg logit contributions | |
helmets | -0.123 |
ates | -0.118 |
skills | -0.117 |
bles | -0.115 |
icycle | -0.113 |
Token | hands |
Token ID | 2832 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
shower | +0.020 |
chick | +0.020 |
bug | +0.019 |
lamb | +0.018 |
sip | +0.017 |
Neg logit contributions | |
helmets | -0.017 |
ates | -0.016 |
numbers | -0.016 |
bled | -0.015 |
bles | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
skills | +0.183 |
helmets | +0.180 |
himself | +0.174 |
ates | +0.172 |
numbers | +0.172 |
Neg logit contributions | |
shower | -0.256 |
chick | -0.254 |
bug | -0.254 |
lyss | -0.250 |
heaven | -0.240 |
Token | tasted |
Token ID | 29187 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
bug | +0.368 |
chick | +0.366 |
shower | +0.356 |
lamb | +0.350 |
heaven | +0.347 |
Neg logit contributions | |
numbers | -0.305 |
helmets | -0.301 |
skills | -0.301 |
hard | -0.301 |
hardest | -0.271 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
bug | +0.195 |
chick | +0.191 |
shower | +0.187 |
lyss | +0.181 |
lamb | +0.177 |
Neg logit contributions | |
hard | -0.152 |
himself | -0.151 |
helmets | -0.150 |
numbers | -0.148 |
skills | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
bug | +0.137 |
chick | +0.133 |
shower | +0.130 |
lyss | +0.130 |
lamb | +0.124 |
Neg logit contributions | |
skills | -0.086 |
numbers | -0.085 |
helmets | -0.083 |
himself | -0.082 |
hard | -0.078 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
chick | +0.022 |
bug | +0.021 |
lamb | +0.021 |
ful | +0.020 |
shower | +0.019 |
Neg logit contributions | |
helmets | -0.011 |
numbers | -0.011 |
skills | -0.010 |
top | -0.010 |
hard | -0.010 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
chick | +0.247 |
bug | +0.241 |
shower | +0.233 |
Lilly | +0.217 |
heaven | +0.216 |
Neg logit contributions | |
helmets | -0.265 |
ates | -0.251 |
numbers | -0.250 |
skills | -0.247 |
himself | -0.240 |
Token | 't |
Token ID | 470 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
helmets | +0.031 |
numbers | +0.028 |
ates | +0.028 |
skills | +0.028 |
himself | +0.027 |
Neg logit contributions | |
chick | -0.038 |
bug | -0.038 |
shower | -0.038 |
Lilly | -0.035 |
heaven | -0.035 |
Token | like |
Token ID | 588 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
himself | +0.296 |
helmets | +0.291 |
numbers | +0.288 |
hard | +0.287 |
skills | +0.282 |
Neg logit contributions | |
chick | -0.247 |
bug | -0.230 |
shower | -0.229 |
lyss | -0.215 |
lamb | -0.210 |
Token | it |
Token ID | 340 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
bug | +0.201 |
chick | +0.197 |
shower | +0.188 |
lamb | +0.177 |
lyss | +0.177 |
Neg logit contributions | |
helmets | -0.201 |
numbers | -0.194 |
skills | -0.191 |
himself | -0.187 |
hard | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
numbers | +0.059 |
helmets | +0.059 |
hard | +0.059 |
skills | +0.058 |
himself | +0.058 |
Neg logit contributions | |
chick | -0.061 |
bug | -0.058 |
shower | -0.056 |
lyss | -0.055 |
lamb | -0.054 |
Token | but |
Token ID | 475 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
helmets | +0.032 |
numbers | +0.031 |
hard | +0.030 |
himself | +0.030 |
skills | +0.029 |
Neg logit contributions | |
bug | -0.031 |
chick | -0.030 |
shower | -0.029 |
lyss | -0.029 |
heaven | -0.028 |
Token | an |
Token ID | 281 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
helmets | +0.072 |
ates | +0.068 |
skills | +0.067 |
numbers | +0.067 |
himself | +0.064 |
Neg logit contributions | |
chick | -0.092 |
bug | -0.090 |
shower | -0.089 |
heaven | -0.084 |
Lilly | -0.083 |
Token | idea |
Token ID | 2126 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
helmets | +0.167 |
ates | +0.150 |
numbers | +0.148 |
skills | +0.143 |
bled | +0.137 |
Neg logit contributions | |
chick | -0.357 |
bug | -0.348 |
shower | -0.344 |
die | -0.329 |
lamb | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
helmets | +0.370 |
numbers | +0.348 |
skills | +0.346 |
ates | +0.344 |
himself | +0.338 |
Neg logit contributions | |
chick | -0.417 |
bug | -0.407 |
shower | -0.401 |
Lilly | -0.374 |
lyss | -0.372 |
Token |
|
Token ID | 198 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
chick | +0.033 |
bug | +0.032 |
shower | +0.032 |
heaven | +0.030 |
Lilly | +0.030 |
Neg logit contributions | |
helmets | -0.021 |
skills | -0.020 |
ates | -0.020 |
numbers | -0.020 |
hardest | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
shower | +0.047 |
bug | +0.047 |
chick | +0.046 |
Lilly | +0.043 |
die | +0.042 |
Neg logit contributions | |
helmets | -0.073 |
ates | -0.070 |
skills | -0.069 |
numbers | -0.069 |
hardest | -0.069 |
Token | " |
Token ID | 1 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
bug | +0.061 |
chick | +0.060 |
shower | +0.058 |
ful | +0.057 |
Baby | +0.055 |
Neg logit contributions | |
skills | -0.058 |
helmets | -0.057 |
ates | -0.057 |
numbers | -0.055 |
hardest | -0.055 |
Token | I |
Token ID | 40 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
helmets | +0.271 |
ates | +0.263 |
skills | +0.259 |
numbers | +0.255 |
himself | +0.247 |
Neg logit contributions | |
chick | -0.266 |
bug | -0.258 |
shower | -0.252 |
lamb | -0.233 |
lyss | -0.233 |
Token | have |
Token ID | 423 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
chick | +0.080 |
bug | +0.078 |
shower | +0.077 |
heaven | +0.070 |
Lilly | +0.070 |
Neg logit contributions | |
helmets | -0.110 |
numbers | -0.105 |
skills | -0.104 |
ates | -0.104 |
himself | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
helmets | +0.066 |
numbers | +0.061 |
skills | +0.060 |
ates | +0.059 |
himself | +0.057 |
Neg logit contributions | |
chick | -0.107 |
bug | -0.106 |
shower | -0.105 |
Lilly | -0.098 |
die | -0.098 |
Token | better |
Token ID | 1365 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
hard | +0.081 |
helmets | +0.080 |
numbers | +0.079 |
skills | +0.079 |
hardest | +0.074 |
Neg logit contributions | |
bug | -0.087 |
chick | -0.085 |
heaven | -0.079 |
shower | -0.078 |
Lilly | -0.078 |
Token | idea |
Token ID | 2126 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
chick | +0.154 |
bug | +0.151 |
shower | +0.148 |
Lilly | +0.136 |
heaven | +0.136 |
Neg logit contributions | |
helmets | -0.177 |
numbers | -0.168 |
skills | -0.167 |
ates | -0.167 |
himself | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
helmets | +0.001 |
numbers | +0.001 |
skills | +0.001 |
ates | +0.001 |
himself | +0.001 |
Neg logit contributions | |
chick | -0.002 |
bug | -0.002 |
shower | -0.002 |
Lilly | -0.002 |
heaven | -0.002 |
Token | Sue |
Token ID | 26089 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
chick | +0.003 |
shower | +0.003 |
bug | +0.003 |
lamb | +0.003 |
heaven | +0.003 |
Neg logit contributions | |
helmets | -0.003 |
numbers | -0.003 |
himself | -0.003 |
skills | -0.003 |
ates | -0.003 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
helmets | +0.060 |
ates | +0.057 |
skills | +0.056 |
numbers | +0.056 |
himself | +0.055 |
Neg logit contributions | |
chick | -0.052 |
bug | -0.052 |
shower | -0.050 |
Lilly | -0.046 |
heaven | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ates | +0.236 |
helmets | +0.229 |
skills | +0.222 |
numbers | +0.222 |
bled | +0.211 |
Neg logit contributions | |
shower | -0.161 |
bug | -0.159 |
chick | -0.151 |
Lilly | -0.148 |
sip | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
chick | +0.023 |
bug | +0.023 |
shower | +0.023 |
Lilly | +0.021 |
heaven | +0.021 |
Neg logit contributions | |
helmets | -0.024 |
ates | -0.023 |
numbers | -0.023 |
skills | -0.023 |
himself | -0.022 |
Token | rail |
Token ID | 6787 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
helmets | +0.022 |
numbers | +0.021 |
skills | +0.020 |
hard | +0.019 |
himself | +0.019 |
Neg logit contributions | |
bug | -0.028 |
chick | -0.028 |
heaven | -0.027 |
Lilly | -0.026 |
shower | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
chick | +0.001 |
bug | +0.001 |
shower | +0.001 |
heaven | +0.001 |
Lilly | +0.001 |
Neg logit contributions | |
helmets | -0.001 |
ates | -0.001 |
numbers | -0.001 |
skills | -0.001 |
himself | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
helmets | +0.026 |
numbers | +0.024 |
skills | +0.024 |
himself | +0.023 |
ates | +0.023 |
Neg logit contributions | |
chick | -0.030 |
shower | -0.028 |
bug | -0.028 |
heaven | -0.027 |
die | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
helmets | +0.001 |
ates | +0.001 |
skills | +0.001 |
numbers | +0.001 |
himself | +0.001 |
Neg logit contributions | |
shower | -0.001 |
chick | -0.001 |
bug | -0.001 |
Lilly | -0.001 |
heaven | -0.001 |
Token | climb |
Token ID | 12080 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
chick | +0.029 |
bug | +0.028 |
lyss | +0.026 |
heaven | +0.026 |
shower | +0.025 |
Neg logit contributions | |
helmets | -0.029 |
numbers | -0.028 |
skills | -0.027 |
himself | -0.027 |
hard | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
ates | +0.331 |
helmets | +0.322 |
skills | +0.305 |
numbers | +0.305 |
bled | +0.303 |
Neg logit contributions | |
shower | -0.256 |
bug | -0.253 |
chick | -0.250 |
Lilly | -0.237 |
Nina | -0.231 |
Token |
|
Token ID | 198 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
chick | +0.008 |
bug | +0.008 |
shower | +0.007 |
lamb | +0.007 |
heaven | +0.007 |
Neg logit contributions | |
helmets | -0.004 |
numbers | -0.004 |
skills | -0.004 |
himself | -0.004 |
hard | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
chick | +0.047 |
bug | +0.046 |
shower | +0.045 |
heaven | +0.042 |
lamb | +0.042 |
Neg logit contributions | |
helmets | -0.036 |
numbers | -0.034 |
skills | -0.034 |
ates | -0.034 |
himself | -0.033 |
Token | L |
Token ID | 43 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
chick | +0.034 |
bug | +0.033 |
shower | +0.032 |
die | +0.029 |
heaven | +0.029 |
Neg logit contributions | |
helmets | -0.049 |
numbers | -0.047 |
skills | -0.046 |
ates | -0.046 |
himself | -0.045 |
Token | ily |
Token ID | 813 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
chick | +0.180 |
shower | +0.170 |
bug | +0.166 |
lamb | +0.159 |
die | +0.158 |
Neg logit contributions | |
helmets | -0.155 |
ates | -0.154 |
skills | -0.152 |
numbers | -0.152 |
himself | -0.151 |
Token | was |
Token ID | 373 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
helmets | +0.046 |
ates | +0.045 |
numbers | +0.044 |
skills | +0.044 |
himself | +0.043 |
Neg logit contributions | |
chick | -0.033 |
bug | -0.033 |
shower | -0.031 |
Lilly | -0.029 |
heaven | -0.028 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
chick | +0.014 |
bug | +0.014 |
shower | +0.014 |
heaven | +0.013 |
Lilly | +0.013 |
Neg logit contributions | |
helmets | -0.015 |
numbers | -0.014 |
skills | -0.014 |
ates | -0.014 |
himself | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
helmets | +0.029 |
ates | +0.027 |
numbers | +0.027 |
skills | +0.026 |
hardest | +0.026 |
Neg logit contributions | |
shower | -0.028 |
chick | -0.027 |
bug | -0.027 |
heaven | -0.026 |
sip | -0.025 |
Token | some |
Token ID | 617 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
helmets | +0.078 |
ates | +0.075 |
skills | +0.074 |
numbers | +0.073 |
hardest | +0.071 |
Neg logit contributions | |
chick | -0.067 |
shower | -0.066 |
bug | -0.065 |
heaven | -0.061 |
Lilly | -0.061 |
Token | glue |
Token ID | 22749 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
helmets | +0.198 |
ates | +0.190 |
skills | +0.183 |
numbers | +0.182 |
himself | +0.181 |
Neg logit contributions | |
chick | -0.297 |
shower | -0.294 |
bug | -0.291 |
heaven | -0.270 |
Lilly | -0.270 |
Token | and |
Token ID | 290 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
helmets | +0.050 |
ates | +0.046 |
numbers | +0.046 |
skills | +0.046 |
himself | +0.045 |
Neg logit contributions | |
chick | -0.059 |
bug | -0.058 |
shower | -0.057 |
Lilly | -0.053 |
heaven | -0.053 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ates | +0.034 |
helmets | +0.034 |
skills | +0.033 |
numbers | +0.031 |
hardest | +0.031 |
Neg logit contributions | |
bug | -0.026 |
chick | -0.026 |
shower | -0.026 |
Lilly | -0.025 |
Nina | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ates | +0.037 |
helmets | +0.036 |
bled | +0.035 |
skills | +0.035 |
numbers | +0.035 |
Neg logit contributions | |
chick | -0.029 |
shower | -0.028 |
bug | -0.027 |
heaven | -0.026 |
Lilly | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
helmets | +0.001 |
numbers | +0.001 |
ates | +0.001 |
skills | +0.001 |
himself | +0.001 |
Neg logit contributions | |
chick | -0.001 |
bug | -0.001 |
shower | -0.001 |
Lilly | -0.001 |
heaven | -0.001 |
Token | knew |
Token ID | 2993 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
helmets | +0.213 |
numbers | +0.200 |
skills | +0.199 |
ates | +0.197 |
himself | +0.194 |
Neg logit contributions | |
chick | -0.206 |
bug | -0.202 |
shower | -0.201 |
heaven | -0.186 |
Lilly | -0.185 |
Token | he |
Token ID | 339 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
chick | +0.052 |
bug | +0.051 |
shower | +0.050 |
Lilly | +0.048 |
Nina | +0.047 |
Neg logit contributions | |
helmets | -0.037 |
ates | -0.036 |
skills | -0.035 |
numbers | -0.035 |
hardest | -0.032 |
Token | should |
Token ID | 815 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
helmets | +0.209 |
ates | +0.200 |
skills | +0.197 |
numbers | +0.197 |
himself | +0.189 |
Neg logit contributions | |
chick | -0.194 |
bug | -0.190 |
shower | -0.185 |
Lilly | -0.171 |
lamb | -0.170 |
Token | speed |
Token ID | 2866 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
chick | +0.013 |
bug | +0.013 |
shower | +0.012 |
Lilly | +0.011 |
heaven | +0.011 |
Neg logit contributions | |
helmets | -0.015 |
numbers | -0.014 |
skills | -0.014 |
ates | -0.014 |
himself | -0.014 |
Token | up |
Token ID | 510 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
ates | +0.230 |
helmets | +0.223 |
numbers | +0.216 |
skills | +0.205 |
bled | +0.204 |
Neg logit contributions | |
shower | -0.233 |
bug | -0.219 |
Lilly | -0.217 |
chick | -0.214 |
Nina | -0.213 |
Token | to |
Token ID | 284 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ates | +0.310 |
helmets | +0.293 |
bled | +0.287 |
numbers | +0.282 |
bles | +0.278 |
Neg logit contributions | |
shower | -0.268 |
chick | -0.253 |
bug | -0.247 |
Lilly | -0.244 |
heaven | -0.241 |
Token | get |
Token ID | 651 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
chick | +0.035 |
bug | +0.034 |
shower | +0.033 |
lyss | +0.031 |
Lilly | +0.031 |
Neg logit contributions | |
helmets | -0.026 |
numbers | -0.024 |
skills | -0.024 |
himself | -0.024 |
ates | -0.023 |
Token | away |
Token ID | 1497 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
chick | +0.249 |
shower | +0.245 |
bug | +0.243 |
Lilly | +0.229 |
die | +0.227 |
Neg logit contributions | |
helmets | -0.194 |
ates | -0.188 |
numbers | -0.185 |
skills | -0.184 |
himself | -0.171 |
Token | from |
Token ID | 422 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
chick | +0.169 |
shower | +0.164 |
bug | +0.164 |
Lilly | +0.149 |
heaven | +0.149 |
Neg logit contributions | |
helmets | -0.242 |
ates | -0.232 |
numbers | -0.231 |
skills | -0.230 |
himself | -0.220 |
Token | their |
Token ID | 511 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
helmets | +0.055 |
ates | +0.053 |
skills | +0.052 |
himself | +0.051 |
numbers | +0.051 |
Neg logit contributions | |
chick | -0.078 |
bug | -0.076 |
shower | -0.076 |
heaven | -0.071 |
die | -0.070 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
chick | +0.250 |
shower | +0.250 |
bug | +0.235 |
kitten | +0.229 |
lamb | +0.228 |
Neg logit contributions | |
himself | -0.146 |
ates | -0.145 |
helmets | -0.139 |
bled | -0.138 |
skills | -0.128 |
Token | and |
Token ID | 290 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
helmets | +0.172 |
ates | +0.170 |
numbers | +0.167 |
himself | +0.162 |
bled | +0.160 |
Neg logit contributions | |
bug | -0.190 |
chick | -0.187 |
shower | -0.181 |
heaven | -0.166 |
sip | -0.165 |
Token | run |
Token ID | 1057 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ates | +0.034 |
helmets | +0.034 |
skills | +0.033 |
numbers | +0.032 |
bled | +0.032 |
Neg logit contributions | |
chick | -0.023 |
shower | -0.023 |
bug | -0.023 |
sip | -0.020 |
die | -0.020 |
Token | around |
Token ID | 1088 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ates | +0.129 |
helmets | +0.127 |
numbers | +0.123 |
skills | +0.120 |
bled | +0.119 |
Neg logit contributions | |
shower | -0.118 |
chick | -0.116 |
bug | -0.115 |
sip | -0.108 |
Lilly | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
helmets | +0.071 |
ates | +0.070 |
numbers | +0.067 |
skills | +0.066 |
bled | +0.066 |
Neg logit contributions | |
chick | -0.059 |
shower | -0.058 |
bug | -0.058 |
heaven | -0.054 |
sip | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
bug | +0.011 |
shower | +0.011 |
chick | +0.011 |
Lilly | +0.010 |
sip | +0.010 |
Neg logit contributions | |
helmets | -0.012 |
ates | -0.012 |
skills | -0.012 |
numbers | -0.012 |
bled | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
bug | +0.041 |
chick | +0.041 |
shower | +0.041 |
Lilly | +0.038 |
sip | +0.037 |
Neg logit contributions | |
helmets | -0.045 |
numbers | -0.042 |
ates | -0.042 |
skills | -0.042 |
hardest | -0.040 |
Token | One |
Token ID | 3198 |
Feature activation | +6.00e+00 |
Pos logit contributions | |
bug | +0.043 |
shower | +0.042 |
sip | +0.040 |
chick | +0.040 |
drink | +0.039 |
Neg logit contributions | |
ates | -0.042 |
skills | -0.039 |
bled | -0.039 |
hardest | -0.039 |
himself | -0.038 |
Token | day |
Token ID | 1110 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
helmets | +0.245 |
hard | +0.236 |
numbers | +0.229 |
skills | +0.228 |
himself | +0.217 |
Neg logit contributions | |
chick | -0.481 |
bug | -0.470 |
shower | -0.456 |
Nina | -0.454 |
die | -0.450 |
Token | , |
Token ID | 11 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
helmets | +0.129 |
ates | +0.127 |
skills | +0.125 |
numbers | +0.121 |
himself | +0.120 |
Neg logit contributions | |
shower | -0.109 |
bug | -0.105 |
chick | -0.104 |
Lilly | -0.099 |
sip | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
bug | +0.122 |
shower | +0.121 |
chick | +0.115 |
Lilly | +0.113 |
die | +0.109 |
Neg logit contributions | |
helmets | -0.131 |
ates | -0.125 |
skills | -0.120 |
numbers | -0.119 |
hardest | -0.114 |
Token | it |
Token ID | 340 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
ates | +0.047 |
skills | +0.046 |
helmets | +0.044 |
numbers | +0.044 |
icycle | +0.043 |
Neg logit contributions | |
Lilly | -0.023 |
shower | -0.022 |
bug | -0.022 |
chick | -0.021 |
Nina | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
helmets | +0.053 |
numbers | +0.050 |
skills | +0.050 |
ates | +0.049 |
himself | +0.048 |
Neg logit contributions | |
chick | -0.064 |
bug | -0.062 |
shower | -0.062 |
heaven | -0.057 |
Lilly | -0.057 |
Token | dark |
Token ID | 3223 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
shower | +0.028 |
chick | +0.027 |
Lilly | +0.026 |
bug | +0.026 |
heaven | +0.025 |
Neg logit contributions | |
ates | -0.034 |
skills | -0.033 |
helmets | -0.033 |
numbers | -0.032 |
ikes | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
chick | +0.079 |
bug | +0.078 |
shower | +0.076 |
lyss | +0.072 |
Lilly | +0.072 |
Neg logit contributions | |
helmets | -0.070 |
numbers | -0.066 |
skills | -0.065 |
ates | -0.064 |
himself | -0.063 |
Token | cold |
Token ID | 4692 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
ates | +0.033 |
helmets | +0.032 |
skills | +0.031 |
numbers | +0.031 |
himself | +0.030 |
Neg logit contributions | |
chick | -0.028 |
shower | -0.028 |
bug | -0.027 |
Lilly | -0.026 |
die | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
chick | +0.324 |
bug | +0.322 |
shower | +0.302 |
lyss | +0.296 |
lamb | +0.289 |
Neg logit contributions | |
helmets | -0.279 |
numbers | -0.264 |
skills | -0.260 |
himself | -0.259 |
ates | -0.254 |
Token | There |
Token ID | 1318 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
chick | +0.009 |
bug | +0.009 |
shower | +0.008 |
heaven | +0.008 |
lamb | +0.008 |
Neg logit contributions | |
helmets | -0.010 |
numbers | -0.010 |
skills | -0.009 |
ates | -0.009 |
himself | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
chick | +0.192 |
shower | +0.187 |
bug | +0.187 |
Lilly | +0.173 |
die | +0.170 |
Neg logit contributions | |
helmets | -0.264 |
ates | -0.256 |
numbers | -0.247 |
skills | -0.246 |
hardest | -0.232 |
Token | spiders |
Token ID | 26120 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
chick | +0.149 |
shower | +0.148 |
bug | +0.143 |
heaven | +0.134 |
die | +0.134 |
Neg logit contributions | |
ates | -0.104 |
helmets | -0.103 |
skills | -0.100 |
numbers | -0.096 |
bled | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
chick | +0.110 |
bug | +0.106 |
lyss | +0.103 |
shower | +0.102 |
Lilly | +0.102 |
Neg logit contributions | |
helmets | -0.072 |
numbers | -0.066 |
skills | -0.065 |
himself | -0.064 |
hard | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
bug | +0.007 |
shower | +0.007 |
chick | +0.007 |
Lilly | +0.006 |
lyss | +0.006 |
Neg logit contributions | |
helmets | -0.007 |
ates | -0.007 |
skills | -0.007 |
numbers | -0.007 |
himself | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
helmets | +0.038 |
skills | +0.036 |
numbers | +0.036 |
ates | +0.035 |
himself | +0.033 |
Neg logit contributions | |
chick | -0.044 |
bug | -0.044 |
shower | -0.043 |
Lilly | -0.040 |
heaven | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
helmets | +0.016 |
numbers | +0.015 |
skills | +0.015 |
ates | +0.014 |
himself | +0.014 |
Neg logit contributions | |
chick | -0.021 |
bug | -0.020 |
shower | -0.020 |
heaven | -0.019 |
lamb | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
chick | +0.026 |
bug | +0.026 |
shower | +0.025 |
die | +0.024 |
heaven | +0.024 |
Neg logit contributions | |
helmets | -0.013 |
numbers | -0.012 |
ates | -0.012 |
skills | -0.012 |
himself | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
hard | +0.087 |
helmets | +0.083 |
numbers | +0.079 |
best | +0.075 |
top | +0.074 |
Neg logit contributions | |
bug | -0.098 |
die | -0.094 |
ount | -0.093 |
ility | -0.093 |
heaven | -0.092 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
bug | +0.078 |
ount | +0.075 |
ility | +0.074 |
itionally | +0.073 |
die | +0.073 |
Neg logit contributions | |
hard | -0.054 |
numbers | -0.052 |
helmets | -0.052 |
his | -0.050 |
brothers | -0.049 |
Token | called |
Token ID | 1444 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
die | +0.186 |
renched | +0.182 |
itionally | +0.178 |
lyss | +0.173 |
ount | +0.172 |
Neg logit contributions | |
on | -0.135 |
hard | -0.128 |
his | -0.120 |
many | -0.114 |
helmets | -0.112 |
Token | Grace |
Token ID | 16156 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
chick | +0.335 |
bug | +0.306 |
lamb | +0.301 |
die | +0.298 |
shower | +0.291 |
Neg logit contributions | |
numbers | -0.320 |
hard | -0.302 |
helmets | -0.302 |
himself | -0.298 |
two | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
shower | +0.664 |
die | +0.647 |
lyss | +0.641 |
sip | +0.621 |
chick | +0.616 |
Neg logit contributions | |
hard | -0.262 |
helmets | -0.262 |
numbers | -0.249 |
ates | -0.248 |
skills | -0.242 |
Token | She |
Token ID | 1375 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
bug | +0.007 |
chick | +0.006 |
die | +0.006 |
shower | +0.006 |
sip | +0.005 |
Neg logit contributions | |
helmets | -0.009 |
hard | -0.009 |
himself | -0.009 |
skills | -0.009 |
numbers | -0.009 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
chick | +0.074 |
bug | +0.073 |
shower | +0.071 |
die | +0.068 |
heaven | +0.068 |
Neg logit contributions | |
helmets | -0.045 |
numbers | -0.042 |
skills | -0.041 |
himself | -0.041 |
ates | -0.040 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
ates | +0.227 |
helmets | +0.218 |
numbers | +0.216 |
himself | +0.214 |
bled | +0.212 |
Neg logit contributions | |
chick | -0.276 |
shower | -0.274 |
bug | -0.249 |
kitten | -0.246 |
lamb | -0.243 |
Token | . |
Token ID | 13 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
helmets | +0.195 |
numbers | +0.182 |
ates | +0.181 |
skills | +0.180 |
himself | +0.178 |
Neg logit contributions | |
chick | -0.235 |
shower | -0.232 |
bug | -0.229 |
die | -0.218 |
lyss | -0.217 |
Token | He |
Token ID | 679 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
chick | +0.026 |
bug | +0.026 |
shower | +0.025 |
die | +0.024 |
lamb | +0.024 |
Neg logit contributions | |
helmets | -0.013 |
numbers | -0.012 |
himself | -0.011 |
skills | -0.011 |
ates | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
helmets | +0.210 |
numbers | +0.202 |
ates | +0.202 |
skills | +0.201 |
himself | +0.195 |
Neg logit contributions | |
chick | -0.171 |
bug | -0.168 |
shower | -0.164 |
Lilly | -0.150 |
lamb | -0.148 |
Token | many |
Token ID | 867 |
Feature activation | +7.82e+00 |
Pos logit contributions | |
chick | +0.067 |
bug | +0.066 |
shower | +0.065 |
Lilly | +0.061 |
lamb | +0.061 |
Neg logit contributions | |
helmets | -0.038 |
ates | -0.036 |
skills | -0.035 |
numbers | -0.035 |
hardest | -0.032 |
Token | fish |
Token ID | 5916 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
helmets | +0.445 |
ates | +0.434 |
skills | +0.418 |
numbers | +0.415 |
himself | +0.407 |
Neg logit contributions | |
chick | -0.510 |
shower | -0.495 |
bug | -0.489 |
lamb | -0.459 |
Lilly | -0.452 |
Token | and |
Token ID | 290 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
chick | +0.213 |
bug | +0.207 |
shower | +0.206 |
Lilly | +0.195 |
heaven | +0.194 |
Neg logit contributions | |
helmets | -0.172 |
skills | -0.162 |
numbers | -0.161 |
ates | -0.161 |
himself | -0.157 |
Token | ducks |
Token ID | 39694 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
helmets | +0.025 |
ates | +0.024 |
skills | +0.024 |
numbers | +0.024 |
himself | +0.023 |
Neg logit contributions | |
chick | -0.022 |
bug | -0.021 |
shower | -0.021 |
Lilly | -0.019 |
sip | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
chick | +0.164 |
bug | +0.159 |
shower | +0.159 |
lyss | +0.152 |
Lilly | +0.151 |
Neg logit contributions | |
helmets | -0.128 |
skills | -0.120 |
ates | -0.120 |
numbers | -0.119 |
himself | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
chick | +0.031 |
bug | +0.031 |
shower | +0.030 |
heaven | +0.028 |
Lilly | +0.028 |
Neg logit contributions | |
helmets | -0.030 |
ates | -0.029 |
numbers | -0.028 |
skills | -0.028 |
bled | -0.027 |
Token | water |
Token ID | 1660 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
helmets | +0.028 |
skills | +0.025 |
himself | +0.025 |
numbers | +0.025 |
hard | +0.024 |
Neg logit contributions | |
bug | -0.025 |
chick | -0.023 |
heaven | -0.022 |
Lilly | -0.022 |
lyss | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
helmets | +0.129 |
numbers | +0.119 |
skills | +0.119 |
ates | +0.117 |
hardest | +0.113 |
Neg logit contributions | |
bug | -0.104 |
shower | -0.102 |
chick | -0.102 |
Lilly | -0.097 |
Nina | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
bug | +0.038 |
shower | +0.037 |
chick | +0.037 |
Lilly | +0.035 |
Nina | +0.034 |
Neg logit contributions | |
helmets | -0.048 |
ates | -0.044 |
numbers | -0.044 |
skills | -0.044 |
bled | -0.042 |
Token | She |
Token ID | 3347 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
bug | +0.046 |
shower | +0.044 |
chick | +0.044 |
sip | +0.041 |
Lilly | +0.041 |
Neg logit contributions | |
helmets | -0.042 |
ates | -0.041 |
skills | -0.039 |
numbers | -0.039 |
himself | -0.037 |
Token | went |
Token ID | 1816 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
helmets | +0.029 |
numbers | +0.027 |
skills | +0.026 |
himself | +0.026 |
hard | +0.026 |
Neg logit contributions | |
chick | -0.029 |
bug | -0.029 |
shower | -0.029 |
die | -0.026 |
Lilly | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
chick | +0.018 |
bug | +0.018 |
shower | +0.017 |
Lilly | +0.016 |
heaven | +0.016 |
Neg logit contributions | |
helmets | -0.019 |
numbers | -0.018 |
skills | -0.018 |
ates | -0.018 |
himself | -0.017 |
Token | sat |
Token ID | 3332 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
helmets | +0.028 |
himself | +0.025 |
numbers | +0.024 |
skills | +0.024 |
hard | +0.024 |
Neg logit contributions | |
chick | -0.033 |
bug | -0.032 |
shower | -0.031 |
lyss | -0.030 |
die | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
chick | +0.159 |
shower | +0.158 |
bug | +0.153 |
lamb | +0.151 |
heaven | +0.150 |
Neg logit contributions | |
helmets | -0.155 |
numbers | -0.154 |
skills | -0.144 |
gears | -0.144 |
ates | -0.143 |
Token | her |
Token ID | 607 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
chick | +0.038 |
bug | +0.037 |
shower | +0.037 |
heaven | +0.034 |
Lilly | +0.034 |
Neg logit contributions | |
helmets | -0.032 |
ates | -0.030 |
numbers | -0.030 |
skills | -0.030 |
himself | -0.029 |
Token | seat |
Token ID | 5852 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
bug | +0.022 |
chick | +0.022 |
Lilly | +0.020 |
shower | +0.020 |
die | +0.019 |
Neg logit contributions | |
helmets | -0.016 |
skills | -0.015 |
numbers | -0.014 |
ates | -0.014 |
hard | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
bug | +0.001 |
shower | +0.001 |
chick | +0.001 |
heaven | +0.001 |
Lilly | +0.001 |
Neg logit contributions | |
helmets | -0.001 |
numbers | -0.001 |
ates | -0.001 |
skills | -0.001 |
himself | -0.001 |
Token | closed |
Token ID | 4838 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
helmets | +0.030 |
numbers | +0.028 |
skills | +0.028 |
himself | +0.028 |
ates | +0.027 |
Neg logit contributions | |
chick | -0.029 |
bug | -0.028 |
shower | -0.028 |
lyss | -0.026 |
lamb | -0.026 |
Token | little |
Token ID | 1310 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
numbers | +0.084 |
hard | +0.084 |
helmets | +0.082 |
skills | +0.082 |
lesson | +0.074 |
Neg logit contributions | |
bug | -0.101 |
chick | -0.094 |
heaven | -0.090 |
Lilly | -0.090 |
shower | -0.089 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
shower | +0.297 |
die | +0.290 |
ount | +0.288 |
ilt | +0.283 |
heaven | +0.275 |
Neg logit contributions | |
hard | -0.287 |
helmets | -0.286 |
numbers | -0.285 |
skills | -0.279 |
himself | -0.275 |
Token | year |
Token ID | 614 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
chick | +0.170 |
bug | +0.169 |
shower | +0.158 |
heaven | +0.148 |
lyss | +0.147 |
Neg logit contributions | |
helmets | -0.202 |
ates | -0.192 |
numbers | -0.187 |
skills | -0.183 |
bled | -0.183 |
Token | old |
Token ID | 1468 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
chick | +0.048 |
bug | +0.048 |
shower | +0.047 |
Lilly | +0.044 |
heaven | +0.044 |
Neg logit contributions | |
helmets | -0.042 |
numbers | -0.040 |
skills | -0.040 |
ates | -0.039 |
himself | -0.038 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
chick | +0.028 |
bug | +0.027 |
shower | +0.026 |
Lilly | +0.024 |
heaven | +0.024 |
Neg logit contributions | |
helmets | -0.031 |
ates | -0.029 |
skills | -0.029 |
numbers | -0.029 |
himself | -0.028 |
Token | who |
Token ID | 508 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
helmets | +0.016 |
himself | +0.015 |
numbers | +0.015 |
skills | +0.015 |
ates | +0.015 |
Neg logit contributions | |
chick | -0.017 |
shower | -0.016 |
bug | -0.015 |
lyss | -0.015 |
die | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
bug | +0.534 |
chick | +0.532 |
shower | +0.494 |
Lilly | +0.468 |
die | +0.462 |
Neg logit contributions | |
helmets | -0.601 |
ates | -0.579 |
skills | -0.567 |
numbers | -0.554 |
himself | -0.540 |
Token | playing |
Token ID | 2712 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
chick | +0.016 |
bug | +0.016 |
shower | +0.016 |
sip | +0.015 |
lyss | +0.015 |
Neg logit contributions | |
helmets | -0.014 |
ates | -0.013 |
himself | -0.013 |
numbers | -0.013 |
skills | -0.013 |
Token | nearby |
Token ID | 6716 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
ates | +0.031 |
helmets | +0.031 |
numbers | +0.030 |
hardest | +0.030 |
bled | +0.030 |
Neg logit contributions | |
shower | -0.028 |
chick | -0.028 |
heaven | -0.027 |
bug | -0.027 |
Lilly | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
bug | +0.263 |
shower | +0.251 |
chick | +0.249 |
heaven | +0.247 |
Lilly | +0.230 |
Neg logit contributions | |
helmets | -0.360 |
ates | -0.354 |
bled | -0.350 |
numbers | -0.342 |
bles | -0.340 |
Token | Do |
Token ID | 5211 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
helmets | +0.100 |
numbers | +0.094 |
skills | +0.094 |
ates | +0.093 |
himself | +0.090 |
Neg logit contributions | |
chick | -0.081 |
bug | -0.081 |
shower | -0.077 |
Lilly | -0.071 |
heaven | -0.071 |
Token | there |
Token ID | 612 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
bug | +0.006 |
shower | +0.006 |
chick | +0.006 |
Lilly | +0.005 |
lyss | +0.005 |
Neg logit contributions | |
helmets | -0.006 |
ates | -0.006 |
skills | -0.006 |
numbers | -0.006 |
bled | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
helmets | +0.016 |
numbers | +0.015 |
skills | +0.015 |
ates | +0.015 |
himself | +0.015 |
Neg logit contributions | |
chick | -0.020 |
bug | -0.020 |
shower | -0.020 |
heaven | -0.018 |
Lilly | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
chick | +0.025 |
bug | +0.024 |
shower | +0.024 |
Lilly | +0.023 |
heaven | +0.023 |
Neg logit contributions | |
helmets | -0.016 |
skills | -0.015 |
numbers | -0.015 |
ates | -0.015 |
hardest | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
hard | +0.087 |
helmets | +0.087 |
numbers | +0.083 |
skills | +0.076 |
best | +0.076 |
Neg logit contributions | |
bug | -0.091 |
die | -0.086 |
chick | -0.085 |
heaven | -0.085 |
shower | -0.085 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ount | +0.308 |
die | +0.300 |
ility | +0.300 |
bug | +0.292 |
heaven | +0.288 |
Neg logit contributions | |
hard | -0.297 |
helmets | -0.290 |
numbers | -0.274 |
brothers | -0.265 |
best | -0.257 |
Token | who |
Token ID | 508 |
Feature activation | -9.15e+00 |
Pos logit contributions | |
die | +0.151 |
lyss | +0.145 |
shower | +0.143 |
ount | +0.141 |
renched | +0.139 |
Neg logit contributions | |
hard | -0.150 |
helmets | -0.146 |
ep | -0.139 |
his | -0.139 |
on | -0.139 |
Token | had |
Token ID | 550 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
chick | +0.668 |
bug | +0.653 |
shower | +0.646 |
Lilly | +0.602 |
die | +0.600 |
Neg logit contributions | |
helmets | -0.463 |
numbers | -0.430 |
skills | -0.430 |
ates | -0.420 |
himself | -0.419 |
Token | a |
Token ID | 257 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
helmets | +0.060 |
numbers | +0.054 |
skills | +0.051 |
ates | +0.051 |
himself | +0.051 |
Neg logit contributions | |
bug | -0.136 |
chick | -0.136 |
shower | -0.132 |
die | -0.127 |
sip | -0.126 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
helmets | +0.079 |
hard | +0.077 |
numbers | +0.074 |
skills | +0.072 |
best | +0.070 |
Neg logit contributions | |
bug | -0.108 |
chick | -0.101 |
ount | -0.100 |
ility | -0.099 |
ful | -0.097 |
Token | squeeze |
Token ID | 21229 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
bug | +0.106 |
ount | +0.100 |
chick | +0.097 |
lyss | +0.095 |
ility | +0.094 |
Neg logit contributions | |
skills | -0.099 |
helmets | -0.099 |
hard | -0.099 |
numbers | -0.099 |
best | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
bug | +0.175 |
chick | +0.173 |
shower | +0.169 |
lyss | +0.168 |
die | +0.167 |
Neg logit contributions | |
helmets | -0.125 |
skills | -0.122 |
ates | -0.119 |
numbers | -0.117 |
himself | -0.117 |
Token | " |
Token ID | 366 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
chick | +0.022 |
bug | +0.022 |
shower | +0.022 |
heaven | +0.021 |
die | +0.020 |
Neg logit contributions | |
helmets | -0.011 |
himself | -0.011 |
numbers | -0.011 |
skills | -0.010 |
ates | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
helmets | +0.078 |
numbers | +0.074 |
ates | +0.073 |
skills | +0.073 |
himself | +0.073 |
Neg logit contributions | |
chick | -0.074 |
shower | -0.072 |
bug | -0.072 |
die | -0.066 |
Lilly | -0.066 |
Token | ceiling |
Token ID | 13387 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
bug | +0.016 |
chick | +0.015 |
shower | +0.014 |
heaven | +0.014 |
Lilly | +0.013 |
Neg logit contributions | |
helmets | -0.033 |
numbers | -0.032 |
skills | -0.032 |
ates | -0.031 |
himself | -0.031 |
Token | won |
Token ID | 1839 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
chick | +0.184 |
bug | +0.176 |
shower | +0.174 |
Lilly | +0.172 |
lamb | +0.171 |
Neg logit contributions | |
helmets | -0.110 |
skills | -0.109 |
numbers | -0.106 |
hard | -0.101 |
ates | -0.098 |
Token | 't |
Token ID | 470 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
helmets | +0.154 |
numbers | +0.147 |
skills | +0.146 |
ates | +0.144 |
himself | +0.143 |
Neg logit contributions | |
chick | -0.251 |
bug | -0.247 |
shower | -0.240 |
lyss | -0.229 |
lamb | -0.228 |
Token | leak |
Token ID | 13044 |
Feature activation | -8.23e+00 |
Pos logit contributions | |
hard | +0.262 |
himself | +0.258 |
numbers | +0.245 |
skills | +0.237 |
helmets | +0.236 |
Neg logit contributions | |
bug | -0.305 |
chick | -0.303 |
lyss | -0.293 |
lamb | -0.279 |
Nina | -0.277 |
Token | any |
Token ID | 597 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
chick | +0.409 |
bug | +0.395 |
shower | +0.382 |
lamb | +0.348 |
lyss | +0.348 |
Neg logit contributions | |
helmets | -0.610 |
skills | -0.587 |
numbers | -0.586 |
ates | -0.578 |
himself | -0.575 |
Token | more |
Token ID | 517 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
bug | +0.084 |
chick | +0.083 |
lyss | +0.079 |
Lilly | +0.077 |
ada | +0.077 |
Neg logit contributions | |
helmets | -0.077 |
skills | -0.076 |
hard | -0.076 |
numbers | -0.075 |
hardest | -0.070 |
Token | ." |
Token ID | 526 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
bug | +0.097 |
chick | +0.097 |
lyss | +0.091 |
shower | +0.089 |
Lilly | +0.088 |
Neg logit contributions | |
helmets | -0.079 |
numbers | -0.076 |
skills | -0.076 |
hard | -0.074 |
himself | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
helmets | +0.070 |
numbers | +0.067 |
himself | +0.066 |
skills | +0.066 |
ates | +0.066 |
Neg logit contributions | |
chick | -0.103 |
bug | -0.099 |
shower | -0.098 |
heaven | -0.092 |
lamb | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
chick | +0.056 |
bug | +0.056 |
shower | +0.055 |
Lilly | +0.051 |
heaven | +0.051 |
Neg logit contributions | |
helmets | -0.054 |
numbers | -0.050 |
ates | -0.050 |
skills | -0.050 |
hardest | -0.047 |
Token | his |
Token ID | 465 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ates | +0.021 |
helmets | +0.021 |
skills | +0.020 |
numbers | +0.020 |
hardest | +0.018 |
Neg logit contributions | |
chick | -0.053 |
Lilly | -0.051 |
bug | -0.051 |
shower | -0.051 |
heaven | -0.050 |
Token | mummy |
Token ID | 38567 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
helmets | +0.224 |
ates | +0.215 |
skills | +0.210 |
numbers | +0.206 |
himself | +0.203 |
Neg logit contributions | |
chick | -0.288 |
shower | -0.282 |
bug | -0.278 |
lamb | -0.259 |
Lilly | -0.258 |
Token | were |
Token ID | 547 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
chick | +0.031 |
bug | +0.031 |
shower | +0.031 |
heaven | +0.029 |
die | +0.029 |
Neg logit contributions | |
helmets | -0.028 |
numbers | -0.027 |
ates | -0.026 |
himself | -0.026 |
skills | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
chick | +0.133 |
bug | +0.131 |
shower | +0.129 |
Lilly | +0.121 |
heaven | +0.121 |
Neg logit contributions | |
helmets | -0.101 |
numbers | -0.094 |
skills | -0.094 |
ates | -0.094 |
himself | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
bug | +0.047 |
chick | +0.046 |
shower | +0.044 |
die | +0.043 |
lyss | +0.043 |
Neg logit contributions | |
helmets | -0.026 |
numbers | -0.024 |
skills | -0.023 |
himself | -0.023 |
ates | -0.022 |
Token | living |
Token ID | 2877 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
helmets | +0.024 |
best | +0.022 |
two | +0.022 |
top | +0.022 |
numbers | +0.022 |
Neg logit contributions | |
bug | -0.032 |
chick | -0.030 |
die | -0.030 |
sip | -0.029 |
ring | -0.029 |
Token | room |
Token ID | 2119 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
chick | +0.459 |
bug | +0.449 |
shower | +0.440 |
die | +0.419 |
Lilly | +0.414 |
Neg logit contributions | |
helmets | -0.382 |
skills | -0.368 |
ates | -0.364 |
numbers | -0.359 |
himself | -0.347 |
Token | . |
Token ID | 13 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
chick | +0.144 |
bug | +0.138 |
shower | +0.131 |
lamb | +0.131 |
lyss | +0.130 |
Neg logit contributions | |
helmets | -0.098 |
numbers | -0.092 |
skills | -0.091 |
ates | -0.088 |
himself | -0.088 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
shower | +0.005 |
sip | +0.004 |
bug | +0.004 |
Lilly | +0.004 |
drink | +0.004 |
Neg logit contributions | |
ates | -0.005 |
skills | -0.005 |
helmets | -0.005 |
bles | -0.005 |
bled | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
helmets | +0.231 |
ates | +0.221 |
skills | +0.220 |
numbers | +0.217 |
himself | +0.210 |
Neg logit contributions | |
bug | -0.214 |
chick | -0.213 |
shower | -0.205 |
Lilly | -0.193 |
heaven | -0.189 |
Token | very |
Token ID | 845 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
chick | +0.022 |
bug | +0.022 |
shower | +0.021 |
Lilly | +0.020 |
heaven | +0.020 |
Neg logit contributions | |
helmets | -0.020 |
skills | -0.019 |
numbers | -0.019 |
ates | -0.018 |
himself | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
chick | +0.006 |
bug | +0.006 |
shower | +0.006 |
lyss | +0.006 |
lamb | +0.006 |
Neg logit contributions | |
helmets | -0.004 |
skills | -0.004 |
numbers | -0.004 |
himself | -0.004 |
hard | -0.004 |
Token | But |
Token ID | 887 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
chick | +0.038 |
bug | +0.036 |
shower | +0.036 |
lamb | +0.034 |
lyss | +0.033 |
Neg logit contributions | |
helmets | -0.029 |
numbers | -0.028 |
ates | -0.027 |
himself | -0.027 |
skills | -0.027 |
Token | only |
Token ID | 691 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
helmets | +0.070 |
ates | +0.068 |
skills | +0.067 |
numbers | +0.066 |
himself | +0.063 |
Neg logit contributions | |
chick | -0.064 |
bug | -0.064 |
shower | -0.063 |
Lilly | -0.058 |
die | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
helmets | +0.124 |
numbers | +0.119 |
skills | +0.115 |
ates | +0.113 |
himself | +0.113 |
Neg logit contributions | |
chick | -0.146 |
bug | -0.141 |
shower | -0.140 |
lyss | -0.131 |
heaven | -0.131 |
Token | little |
Token ID | 1310 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
helmets | +0.070 |
numbers | +0.069 |
hard | +0.068 |
skills | +0.068 |
hardest | +0.061 |
Neg logit contributions | |
bug | -0.077 |
chick | -0.076 |
shower | -0.071 |
Lilly | -0.071 |
heaven | -0.070 |
Token | bit |
Token ID | 1643 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
Lilly | +0.279 |
Nina | +0.277 |
ount | +0.276 |
iza | +0.274 |
ada | +0.273 |
Neg logit contributions | |
hard | -0.353 |
numbers | -0.335 |
skills | -0.327 |
helmets | -0.314 |
best | -0.302 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
chick | +0.541 |
lyss | +0.515 |
bug | +0.515 |
shower | +0.506 |
Lilly | +0.493 |
Neg logit contributions | |
hard | -0.376 |
numbers | -0.364 |
helmets | -0.360 |
skills | -0.359 |
himself | -0.321 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
chick | +0.040 |
bug | +0.038 |
shower | +0.038 |
lamb | +0.037 |
lyss | +0.035 |
Neg logit contributions | |
helmets | -0.026 |
numbers | -0.026 |
ates | -0.026 |
himself | -0.025 |
skills | -0.024 |
Token | L |
Token ID | 43 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
helmets | +0.046 |
numbers | +0.042 |
skills | +0.042 |
ates | +0.041 |
himself | +0.040 |
Neg logit contributions | |
bug | -0.052 |
chick | -0.052 |
shower | -0.051 |
Lilly | -0.047 |
heaven | -0.047 |
Token | ily |
Token ID | 813 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
chick | +0.172 |
bug | +0.168 |
shower | +0.166 |
Lilly | +0.153 |
heaven | +0.153 |
Neg logit contributions | |
helmets | -0.180 |
numbers | -0.170 |
skills | -0.169 |
ates | -0.169 |
himself | -0.164 |
Token | and |
Token ID | 290 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
helmets | +0.023 |
numbers | +0.021 |
skills | +0.021 |
ates | +0.021 |
himself | +0.020 |
Neg logit contributions | |
chick | -0.025 |
bug | -0.025 |
shower | -0.025 |
Lilly | -0.023 |
heaven | -0.023 |