Token | it |
Token ID | 340 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
� | +0.002 |
idents | +0.002 |
sack | +0.002 |
Dino | +0.002 |
cooler | +0.002 |
Neg logit contributions | |
Jo | -0.003 |
rum | -0.003 |
ud | -0.003 |
Jamie | -0.002 |
Pen | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Jo | +0.122 |
rum | +0.122 |
ud | +0.111 |
and | +0.106 |
Pen | +0.105 |
Neg logit contributions | |
� | -0.108 |
idents | -0.097 |
sack | -0.091 |
surely | -0.089 |
cooler | -0.088 |
Token | called |
Token ID | 1444 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
Jo | +0.046 |
rum | +0.046 |
Pen | +0.039 |
Ali | +0.038 |
Jacob | +0.038 |
Neg logit contributions | |
� | -0.059 |
idents | -0.051 |
ory | -0.047 |
hotter | -0.047 |
Sorry | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
� | +0.071 |
sack | +0.061 |
idents | +0.059 |
Dino | +0.059 |
cooler | +0.058 |
Neg logit contributions | |
Jo | -0.090 |
rum | -0.086 |
ud | -0.079 |
and | -0.076 |
jo | -0.075 |
Token | " |
Token ID | 366 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
Jo | +0.032 |
rum | +0.032 |
ud | +0.028 |
and | +0.028 |
Pen | +0.027 |
Neg logit contributions | |
� | -0.026 |
sack | -0.021 |
idents | -0.021 |
hotter | -0.020 |
cooler | -0.020 |
Token | gem |
Token ID | 24090 |
Feature activation | +8.68e+00 |
Pos logit contributions | |
Jo | +0.077 |
rum | +0.070 |
and | +0.067 |
ud | +0.064 |
jo | +0.062 |
Neg logit contributions | |
� | -0.063 |
idents | -0.058 |
hotter | -0.054 |
sack | -0.053 |
cooler | -0.052 |
Token | ". |
Token ID | 1911 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
� | +0.852 |
idents | +0.730 |
sack | +0.723 |
surely | +0.703 |
ory | +0.701 |
Neg logit contributions | |
Jo | -0.741 |
rum | -0.708 |
ud | -0.630 |
Pen | -0.620 |
Ali | -0.617 |
Token | She |
Token ID | 1375 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
Jo | +0.231 |
rum | +0.219 |
Pen | +0.194 |
Ali | +0.194 |
and | +0.192 |
Neg logit contributions | |
� | -0.232 |
idents | -0.197 |
hotter | -0.192 |
sack | -0.189 |
ory | -0.189 |
Token | explained |
Token ID | 4893 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Jo | +0.042 |
rum | +0.041 |
ud | +0.037 |
and | +0.036 |
Pen | +0.036 |
Neg logit contributions | |
� | -0.033 |
idents | -0.027 |
sack | -0.026 |
surely | -0.026 |
ory | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
� | +0.174 |
idents | +0.157 |
sack | +0.155 |
Dino | +0.152 |
cooler | +0.142 |
Neg logit contributions | |
Jo | -0.271 |
rum | -0.265 |
ud | -0.244 |
Pen | -0.234 |
jo | -0.231 |
Token | gems |
Token ID | 23685 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
rum | +0.085 |
Jo | +0.084 |
ud | +0.078 |
and | +0.073 |
Pen | +0.073 |
Neg logit contributions | |
� | -0.056 |
sack | -0.051 |
Dino | -0.049 |
idents | -0.048 |
Ros | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
� | +0.063 |
idents | +0.048 |
Dino | +0.048 |
sack | +0.046 |
hotter | +0.046 |
Neg logit contributions | |
Jo | -0.070 |
rum | -0.069 |
ud | -0.061 |
and | -0.060 |
jo | -0.059 |
Token | I |
Token ID | 40 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Jo | +0.017 |
rum | +0.016 |
ud | +0.015 |
Pen | +0.015 |
Ali | +0.014 |
Neg logit contributions | |
� | -0.012 |
idents | -0.009 |
hotter | -0.009 |
surely | -0.009 |
sack | -0.009 |
Token | want |
Token ID | 765 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
� | +0.208 |
idents | +0.175 |
surely | +0.169 |
sack | +0.168 |
ory | +0.168 |
Neg logit contributions | |
Jo | -0.215 |
rum | -0.209 |
Pen | -0.186 |
and | -0.185 |
Ali | -0.182 |
Token | to |
Token ID | 284 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Jo | +0.097 |
rum | +0.095 |
jo | +0.087 |
ud | +0.085 |
Jamie | +0.080 |
Neg logit contributions | |
� | -0.059 |
peanuts | -0.054 |
cooler | -0.053 |
sack | -0.052 |
Dino | -0.052 |
Token | eat |
Token ID | 4483 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Jo | +0.019 |
rum | +0.018 |
ud | +0.017 |
and | +0.016 |
Pen | +0.016 |
Neg logit contributions | |
� | -0.012 |
idents | -0.010 |
sack | -0.010 |
surely | -0.009 |
ory | -0.009 |
Token | peanuts |
Token ID | 45612 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
� | +0.070 |
idents | +0.060 |
hotter | +0.057 |
cooler | +0.057 |
sack | +0.057 |
Neg logit contributions | |
Jo | -0.083 |
rum | -0.078 |
jo | -0.071 |
ud | -0.070 |
Ali | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
� | +0.829 |
idents | +0.712 |
sack | +0.684 |
ory | +0.684 |
surely | +0.673 |
Neg logit contributions | |
Jo | -0.730 |
rum | -0.684 |
Pen | -0.590 |
ud | -0.589 |
Ali | -0.589 |
Token | but |
Token ID | 475 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
� | +0.035 |
idents | +0.030 |
sack | +0.028 |
hotter | +0.028 |
ory | +0.028 |
Neg logit contributions | |
Jo | -0.036 |
rum | -0.035 |
ud | -0.031 |
Pen | -0.030 |
and | -0.030 |
Token | I |
Token ID | 314 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Jo | +0.044 |
rum | +0.043 |
Pen | +0.038 |
ud | +0.037 |
Ali | +0.037 |
Neg logit contributions | |
� | -0.046 |
idents | -0.039 |
hotter | -0.037 |
sack | -0.037 |
surely | -0.037 |
Token | can |
Token ID | 460 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Jo | +0.127 |
rum | +0.122 |
Pen | +0.107 |
ud | +0.106 |
and | +0.106 |
Neg logit contributions | |
� | -0.130 |
idents | -0.110 |
sack | -0.105 |
surely | -0.105 |
hotter | -0.105 |
Token | 't |
Token ID | 470 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
� | +0.189 |
idents | +0.162 |
hotter | +0.158 |
sack | +0.152 |
ory | +0.150 |
Neg logit contributions | |
Jo | -0.214 |
rum | -0.209 |
Pen | -0.185 |
Jacob | -0.183 |
ud | -0.183 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Jo | +0.266 |
rum | +0.262 |
Pen | +0.233 |
Ali | +0.231 |
ud | +0.230 |
Neg logit contributions | |
� | -0.207 |
idents | -0.166 |
ory | -0.159 |
sack | -0.158 |
hotter | -0.154 |
Token | , |
Token ID | 11 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
idents | +0.079 |
� | +0.075 |
Ros | +0.064 |
ory | +0.064 |
sack | +0.061 |
Neg logit contributions | |
Jo | -0.148 |
rum | -0.140 |
ud | -0.132 |
Jamie | -0.129 |
and | -0.125 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
� | +0.002 |
idents | +0.002 |
sack | +0.002 |
hotter | +0.002 |
cooler | +0.002 |
Neg logit contributions | |
Jo | -0.004 |
rum | -0.004 |
ud | -0.004 |
jo | -0.003 |
and | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
� | +0.092 |
idents | +0.083 |
sack | +0.075 |
Dino | +0.073 |
surely | +0.070 |
Neg logit contributions | |
Jo | -0.141 |
rum | -0.130 |
and | -0.126 |
ud | -0.125 |
Pen | -0.123 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Jo | +0.005 |
rum | +0.005 |
ud | +0.004 |
and | +0.004 |
Pen | +0.004 |
Neg logit contributions | |
� | -0.005 |
idents | -0.004 |
surely | -0.004 |
Dino | -0.004 |
hotter | -0.004 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
Jo | +0.293 |
rum | +0.289 |
and | +0.270 |
jo | +0.268 |
Jacob | +0.266 |
Neg logit contributions | |
� | -0.057 |
surely | -0.025 |
sack | -0.025 |
hotter | -0.023 |
Dino | -0.018 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
� | +0.694 |
idents | +0.577 |
hotter | +0.547 |
sack | +0.546 |
surely | +0.540 |
Neg logit contributions | |
Jo | -0.851 |
rum | -0.822 |
Pen | -0.731 |
ud | -0.730 |
and | -0.722 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
� | +0.127 |
idents | +0.118 |
hotter | +0.106 |
surely | +0.103 |
sack | +0.103 |
Neg logit contributions | |
Jo | -0.149 |
rum | -0.142 |
ud | -0.127 |
Pen | -0.123 |
jo | -0.122 |
Token | Just |
Token ID | 2329 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Jo | +0.004 |
rum | +0.004 |
ud | +0.003 |
and | +0.003 |
Pen | +0.003 |
Neg logit contributions | |
� | -0.004 |
idents | -0.004 |
Dino | -0.004 |
surely | -0.004 |
hotter | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
� | +0.084 |
idents | +0.071 |
surely | +0.067 |
sack | +0.067 |
hotter | +0.067 |
Neg logit contributions | |
Jo | -0.102 |
rum | -0.098 |
ud | -0.088 |
Pen | -0.087 |
and | -0.087 |
Token | careful |
Token ID | 8161 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
Jo | +0.024 |
rum | +0.021 |
jo | +0.021 |
ud | +0.020 |
Pen | +0.020 |
Neg logit contributions | |
� | -0.023 |
hotter | -0.022 |
cooler | -0.022 |
ang | -0.021 |
prett | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
idents | +0.068 |
� | +0.064 |
ory | +0.053 |
cooler | +0.051 |
sack | +0.049 |
Neg logit contributions | |
Jo | -0.158 |
rum | -0.149 |
ud | -0.141 |
and | -0.139 |
Jamie | -0.134 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
idents | +0.008 |
� | +0.008 |
cooler | +0.008 |
sack | +0.007 |
surely | +0.007 |
Neg logit contributions | |
Jo | -0.009 |
rum | -0.009 |
jo | -0.008 |
and | -0.008 |
ud | -0.008 |
Token | ie |
Token ID | 494 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
rum | +0.129 |
Jo | +0.128 |
and | +0.119 |
Pen | +0.110 |
Jacob | +0.109 |
Neg logit contributions | |
ory | -0.068 |
� | -0.067 |
idents | -0.065 |
cooler | -0.060 |
sack | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
� | +0.014 |
sack | +0.012 |
idents | +0.012 |
cooler | +0.011 |
ory | +0.010 |
Neg logit contributions | |
Jo | -0.026 |
rum | -0.025 |
and | -0.025 |
Jamie | -0.024 |
ud | -0.024 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
� | +0.007 |
idents | +0.006 |
surely | +0.005 |
Dino | +0.005 |
sack | +0.005 |
Neg logit contributions | |
Jo | -0.008 |
rum | -0.007 |
ud | -0.007 |
and | -0.007 |
jo | -0.006 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
Jo | +0.270 |
rum | +0.270 |
and | +0.252 |
Pen | +0.250 |
Ali | +0.249 |
Neg logit contributions | |
� | -0.057 |
surely | -0.028 |
sack | -0.027 |
hotter | -0.024 |
Dino | -0.024 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
� | +0.580 |
idents | +0.509 |
sack | +0.453 |
hotter | +0.453 |
surely | +0.441 |
Neg logit contributions | |
Jo | -0.938 |
rum | -0.888 |
ud | -0.832 |
Ali | -0.817 |
Pen | -0.810 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
� | +0.110 |
idents | +0.108 |
hotter | +0.093 |
cooler | +0.093 |
sack | +0.090 |
Neg logit contributions | |
Jo | -0.159 |
rum | -0.151 |
ud | -0.141 |
Jamie | -0.132 |
Ali | -0.131 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
� | +0.006 |
idents | +0.006 |
Dino | +0.005 |
surely | +0.005 |
hotter | +0.005 |
Neg logit contributions | |
Jo | -0.007 |
rum | -0.007 |
ud | -0.006 |
and | -0.006 |
jo | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Jo | +0.185 |
rum | +0.175 |
Pen | +0.144 |
ud | +0.142 |
and | +0.140 |
Neg logit contributions | |
� | -0.352 |
idents | -0.310 |
hotter | -0.300 |
sack | -0.299 |
surely | -0.298 |
Token | clean |
Token ID | 3424 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
Jo | +0.260 |
rum | +0.252 |
Pen | +0.225 |
ud | +0.224 |
Ali | +0.222 |
Neg logit contributions | |
� | -0.194 |
idents | -0.159 |
hotter | -0.151 |
sack | -0.150 |
ory | -0.149 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
rum | +0.240 |
Jo | +0.229 |
Pen | +0.206 |
Ali | +0.203 |
ud | +0.200 |
Neg logit contributions | |
� | -0.242 |
ory | -0.192 |
idents | -0.188 |
trigger | -0.182 |
sack | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
idents | +0.064 |
� | +0.064 |
ory | +0.049 |
cooler | +0.048 |
sack | +0.048 |
Neg logit contributions | |
Jo | -0.153 |
rum | -0.142 |
ud | -0.132 |
jo | -0.129 |
Jamie | -0.128 |
Token | Anna |
Token ID | 11735 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
idents | +0.013 |
� | +0.013 |
cooler | +0.012 |
hotter | +0.012 |
surely | +0.011 |
Neg logit contributions | |
Jo | -0.014 |
rum | -0.014 |
jo | -0.013 |
ud | -0.012 |
and | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Jo | +0.555 |
rum | +0.503 |
Jamie | +0.482 |
and | +0.479 |
ud | +0.470 |
Neg logit contributions | |
� | -0.278 |
idents | -0.236 |
sack | -0.231 |
cooler | -0.210 |
still | -0.204 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
� | +0.013 |
idents | +0.011 |
sack | +0.011 |
surely | +0.010 |
hotter | +0.010 |
Neg logit contributions | |
Jo | -0.014 |
rum | -0.013 |
ud | -0.012 |
and | -0.012 |
jo | -0.011 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
rum | +0.290 |
Jo | +0.290 |
and | +0.270 |
Ali | +0.268 |
Jacob | +0.268 |
Neg logit contributions | |
� | -0.057 |
surely | -0.025 |
sack | -0.023 |
hotter | -0.018 |
Dino | -0.018 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
� | +0.640 |
idents | +0.547 |
hotter | +0.505 |
sack | +0.501 |
surely | +0.495 |
Neg logit contributions | |
Jo | -0.883 |
rum | -0.843 |
ud | -0.771 |
Pen | -0.763 |
Ali | -0.757 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
� | +0.097 |
idents | +0.091 |
hotter | +0.079 |
cooler | +0.077 |
sack | +0.075 |
Neg logit contributions | |
Jo | -0.162 |
rum | -0.151 |
ud | -0.138 |
jo | -0.136 |
Pen | -0.136 |
Token | I |
Token ID | 314 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
� | +0.013 |
idents | +0.011 |
Dino | +0.010 |
hotter | +0.010 |
sack | +0.010 |
Neg logit contributions | |
Jo | -0.015 |
rum | -0.014 |
ud | -0.013 |
and | -0.012 |
jo | -0.012 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Jo | +0.125 |
rum | +0.119 |
ud | +0.103 |
and | +0.101 |
Pen | +0.101 |
Neg logit contributions | |
� | -0.164 |
idents | -0.139 |
hotter | -0.137 |
sack | -0.135 |
ory | -0.134 |
Token | not |
Token ID | 407 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Jo | +0.022 |
rum | +0.021 |
ud | +0.019 |
jo | +0.019 |
and | +0.018 |
Neg logit contributions | |
� | -0.018 |
idents | -0.015 |
hotter | -0.014 |
surely | -0.014 |
sack | -0.014 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
rum | +0.236 |
Jo | +0.226 |
Pen | +0.204 |
Ali | +0.201 |
Jacob | +0.196 |
Neg logit contributions | |
� | -0.248 |
ory | -0.201 |
idents | -0.193 |
trigger | -0.190 |
sack | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
� | +0.078 |
idents | +0.076 |
ory | +0.063 |
sack | +0.062 |
Ros | +0.061 |
Neg logit contributions | |
Jo | -0.134 |
rum | -0.125 |
ud | -0.116 |
Jamie | -0.113 |
and | -0.112 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
� | +0.006 |
idents | +0.005 |
sack | +0.005 |
hotter | +0.005 |
surely | +0.005 |
Neg logit contributions | |
Jo | -0.010 |
rum | -0.009 |
ud | -0.008 |
jo | -0.008 |
and | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
� | +0.096 |
idents | +0.086 |
sack | +0.078 |
surely | +0.071 |
ory | +0.071 |
Neg logit contributions | |
Jo | -0.153 |
rum | -0.141 |
Jamie | -0.133 |
ud | -0.133 |
and | -0.132 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
� | +0.006 |
idents | +0.005 |
surely | +0.005 |
sack | +0.005 |
Dino | +0.005 |
Neg logit contributions | |
Jo | -0.005 |
rum | -0.005 |
ud | -0.004 |
and | -0.004 |
Pen | -0.004 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
rum | +0.298 |
Jo | +0.297 |
and | +0.275 |
Jacob | +0.274 |
Ali | +0.274 |
Neg logit contributions | |
� | -0.060 |
surely | -0.030 |
sack | -0.029 |
hotter | -0.024 |
cooler | -0.021 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
� | +0.724 |
idents | +0.594 |
ory | +0.575 |
sack | +0.572 |
hotter | +0.572 |
Neg logit contributions | |
Jo | -0.809 |
rum | -0.785 |
Pen | -0.689 |
and | -0.686 |
ud | -0.682 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
� | +0.120 |
idents | +0.109 |
hotter | +0.100 |
sack | +0.098 |
surely | +0.097 |
Neg logit contributions | |
Jo | -0.136 |
rum | -0.129 |
ud | -0.114 |
Pen | -0.114 |
Ali | -0.111 |
Token | It |
Token ID | 632 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
� | +0.003 |
idents | +0.002 |
Dino | +0.002 |
surely | +0.002 |
hotter | +0.002 |
Neg logit contributions | |
Jo | -0.002 |
rum | -0.002 |
ud | -0.002 |
and | -0.002 |
Pen | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
� | +0.045 |
idents | +0.039 |
ory | +0.039 |
sack | +0.038 |
hotter | +0.038 |
Neg logit contributions | |
Jo | -0.023 |
rum | -0.021 |
Pen | -0.018 |
Ali | -0.017 |
ud | -0.017 |
Token | not |
Token ID | 407 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
rum | +0.244 |
Jo | +0.242 |
Pen | +0.213 |
Ali | +0.208 |
ud | +0.206 |
Neg logit contributions | |
� | -0.242 |
idents | -0.193 |
ory | -0.191 |
sack | -0.181 |
trigger | -0.175 |
Token | where |
Token ID | 810 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
� | +0.062 |
sack | +0.061 |
cooler | +0.058 |
Dino | +0.057 |
hotter | +0.056 |
Neg logit contributions | |
Jo | -0.108 |
rum | -0.105 |
ud | -0.098 |
jo | -0.094 |
Jamie | -0.091 |
Token | it |
Token ID | 340 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
rum | +0.305 |
Jo | +0.297 |
ud | +0.280 |
and | +0.262 |
jo | +0.260 |
Neg logit contributions | |
� | -0.165 |
sack | -0.150 |
cooler | -0.142 |
idents | -0.140 |
hotter | -0.139 |
Token | was |
Token ID | 373 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
Jo | +0.111 |
rum | +0.105 |
Pen | +0.095 |
Ali | +0.093 |
and | +0.092 |
Neg logit contributions | |
� | -0.119 |
idents | -0.099 |
hotter | -0.095 |
ory | -0.095 |
sack | -0.093 |
Token | hiding |
Token ID | 11816 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Jo | +0.060 |
rum | +0.057 |
ud | +0.052 |
Ali | +0.051 |
Pen | +0.051 |
Neg logit contributions | |
� | -0.047 |
sack | -0.041 |
hotter | -0.041 |
cooler | -0.040 |
surely | -0.040 |
Token | its |
Token ID | 663 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Jo | +0.304 |
rum | +0.290 |
ud | +0.257 |
Pen | +0.254 |
Ali | +0.251 |
Neg logit contributions | |
� | -0.290 |
idents | -0.245 |
sack | -0.240 |
hotter | -0.235 |
surely | -0.234 |
Token | peanuts |
Token ID | 45612 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
Jo | +0.249 |
rum | +0.239 |
ud | +0.210 |
Pen | +0.210 |
and | +0.207 |
Neg logit contributions | |
� | -0.243 |
idents | -0.205 |
sack | -0.198 |
hotter | -0.196 |
surely | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
� | +0.779 |
idents | +0.659 |
sack | +0.639 |
hotter | +0.628 |
surely | +0.624 |
Neg logit contributions | |
Jo | -0.750 |
rum | -0.720 |
ud | -0.627 |
Pen | -0.627 |
Ali | -0.620 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
� | +0.005 |
idents | +0.004 |
Dino | +0.004 |
ory | +0.004 |
sack | +0.004 |
Neg logit contributions | |
rum | -0.007 |
Jo | -0.007 |
ud | -0.006 |
and | -0.006 |
jo | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
rum | +0.011 |
Jo | +0.011 |
ud | +0.009 |
and | +0.009 |
Pen | +0.009 |
Neg logit contributions | |
� | -0.008 |
sack | -0.006 |
idents | -0.006 |
Dino | -0.006 |
cooler | -0.006 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
� | +0.058 |
idents | +0.044 |
ory | +0.042 |
sack | +0.041 |
surely | +0.041 |
Neg logit contributions | |
Jo | -0.125 |
rum | -0.123 |
ud | -0.110 |
Pen | -0.110 |
and | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
� | +0.128 |
cooler | +0.107 |
sack | +0.099 |
Dino | +0.093 |
idents | +0.093 |
Neg logit contributions | |
rum | -0.254 |
Jo | -0.241 |
ud | -0.227 |
jo | -0.220 |
Ali | -0.211 |
Token | It |
Token ID | 632 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
� | +0.016 |
Dino | +0.013 |
idents | +0.013 |
surely | +0.012 |
sack | +0.012 |
Neg logit contributions | |
Jo | -0.019 |
rum | -0.018 |
ud | -0.016 |
and | -0.016 |
jo | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
� | +0.043 |
idents | +0.038 |
sack | +0.036 |
hotter | +0.036 |
surely | +0.036 |
Neg logit contributions | |
Jo | -0.037 |
rum | -0.036 |
ud | -0.031 |
and | -0.031 |
Ali | -0.030 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Jo | +0.274 |
rum | +0.262 |
ud | +0.234 |
and | +0.234 |
Pen | +0.233 |
Neg logit contributions | |
� | -0.199 |
idents | -0.166 |
hotter | -0.160 |
sack | -0.158 |
surely | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
idents | +0.067 |
� | +0.062 |
cooler | +0.059 |
still | +0.055 |
ory | +0.055 |
Neg logit contributions | |
Jo | -0.151 |
rum | -0.140 |
ud | -0.132 |
Jamie | -0.128 |
Jacob | -0.122 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
� | +0.017 |
idents | +0.014 |
Dino | +0.014 |
surely | +0.013 |
sack | +0.013 |
Neg logit contributions | |
Jo | -0.019 |
rum | -0.017 |
ud | -0.016 |
and | -0.015 |
jo | -0.015 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
rum | +0.279 |
Jo | +0.279 |
and | +0.262 |
Jacob | +0.259 |
Ali | +0.258 |
Neg logit contributions | |
� | -0.063 |
sack | -0.031 |
surely | -0.031 |
hotter | -0.027 |
Dino | -0.022 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
� | +0.690 |
idents | +0.574 |
hotter | +0.544 |
sack | +0.543 |
surely | +0.537 |
Neg logit contributions | |
Jo | -0.838 |
rum | -0.810 |
Pen | -0.719 |
ud | -0.717 |
and | -0.710 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
� | +0.095 |
idents | +0.092 |
cooler | +0.083 |
hotter | +0.082 |
ory | +0.080 |
Neg logit contributions | |
Jo | -0.158 |
rum | -0.150 |
ud | -0.138 |
Ali | -0.132 |
Pen | -0.132 |
Token | Just |
Token ID | 2329 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
� | +0.017 |
idents | +0.014 |
Dino | +0.014 |
surely | +0.013 |
hotter | +0.013 |
Neg logit contributions | |
Jo | -0.020 |
rum | -0.018 |
ud | -0.017 |
and | -0.016 |
jo | -0.016 |
Token | be |
Token ID | 307 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
� | +0.084 |
idents | +0.070 |
hotter | +0.067 |
surely | +0.067 |
sack | +0.067 |
Neg logit contributions | |
Jo | -0.103 |
rum | -0.099 |
ud | -0.088 |
Pen | -0.087 |
and | -0.087 |
Token | more |
Token ID | 517 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Jo | +0.018 |
rum | +0.016 |
jo | +0.015 |
ud | +0.015 |
Pen | +0.014 |
Neg logit contributions | |
� | -0.015 |
hotter | -0.015 |
cooler | -0.015 |
ang | -0.015 |
prett | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Jo | +0.333 |
rum | +0.331 |
ud | +0.297 |
jo | +0.294 |
and | +0.292 |
Neg logit contributions | |
� | -0.186 |
Dino | -0.155 |
surely | -0.153 |
sack | -0.147 |
hotter | -0.142 |
Token | story |
Token ID | 1621 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
� | +0.054 |
idents | +0.047 |
hotter | +0.045 |
surely | +0.045 |
ory | +0.044 |
Neg logit contributions | |
Jo | -0.035 |
rum | -0.033 |
Pen | -0.028 |
ud | -0.028 |
Ali | -0.028 |
Token | is |
Token ID | 318 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
� | +0.058 |
idents | +0.055 |
surely | +0.051 |
sack | +0.049 |
ols | +0.048 |
Neg logit contributions | |
Jo | -0.071 |
rum | -0.063 |
Pen | -0.056 |
Jamie | -0.056 |
ud | -0.055 |
Token | : |
Token ID | 25 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Jo | +0.096 |
rum | +0.092 |
Pen | +0.079 |
ud | +0.079 |
Ali | +0.078 |
Neg logit contributions | |
� | -0.127 |
idents | -0.109 |
hotter | -0.106 |
sack | -0.105 |
ory | -0.104 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
� | +0.155 |
idents | +0.135 |
surely | +0.132 |
Dino | +0.131 |
sack | +0.125 |
Neg logit contributions | |
Jo | -0.177 |
rum | -0.166 |
ud | -0.150 |
jo | -0.148 |
Pen | -0.144 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.22e+00 |
Pos logit contributions | |
Jo | +0.295 |
rum | +0.289 |
and | +0.275 |
Ali | +0.272 |
Jamie | +0.272 |
Neg logit contributions | |
� | -0.067 |
surely | -0.033 |
sack | -0.033 |
hotter | -0.031 |
cooler | -0.023 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
� | +0.636 |
idents | +0.540 |
surely | +0.502 |
sack | +0.498 |
hotter | +0.497 |
Neg logit contributions | |
Jo | -0.871 |
rum | -0.841 |
ud | -0.761 |
Pen | -0.757 |
Ali | -0.746 |
Token | , |
Token ID | 11 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
� | +0.104 |
idents | +0.097 |
sack | +0.087 |
surely | +0.086 |
ory | +0.085 |
Neg logit contributions | |
Jo | -0.155 |
rum | -0.145 |
Pen | -0.132 |
ud | -0.130 |
jo | -0.126 |
Token | but |
Token ID | 475 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Jo | +0.002 |
rum | +0.002 |
ud | +0.002 |
Pen | +0.002 |
jo | +0.002 |
Neg logit contributions | |
� | -0.002 |
idents | -0.002 |
Dino | -0.002 |
sack | -0.002 |
surely | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Jo | +0.082 |
rum | +0.079 |
ud | +0.069 |
Pen | +0.069 |
and | +0.068 |
Neg logit contributions | |
� | -0.078 |
idents | -0.066 |
sack | -0.063 |
hotter | -0.063 |
surely | -0.063 |
Token | should |
Token ID | 815 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
� | +0.143 |
hotter | +0.119 |
idents | +0.119 |
ory | +0.113 |
Sorry | +0.112 |
Neg logit contributions | |
Jo | -0.138 |
rum | -0.134 |
Pen | -0.119 |
ud | -0.117 |
Ali | -0.116 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rum | +0.201 |
Jo | +0.182 |
supposed | +0.164 |
about | +0.162 |
Pen | +0.162 |
Neg logit contributions | |
� | -0.274 |
ory | -0.230 |
trigger | -0.221 |
glers | -0.219 |
clips | -0.217 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
� | +0.087 |
idents | +0.083 |
ory | +0.071 |
sack | +0.071 |
Dino | +0.068 |
Neg logit contributions | |
Jo | -0.141 |
rum | -0.132 |
Jamie | -0.120 |
ud | -0.120 |
Jacob | -0.119 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
� | +0.012 |
idents | +0.010 |
hotter | +0.009 |
sack | +0.009 |
ory | +0.009 |
Neg logit contributions | |
Jo | -0.017 |
rum | -0.017 |
Pen | -0.015 |
ud | -0.015 |
and | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
� | +0.100 |
idents | +0.090 |
sack | +0.081 |
Dino | +0.074 |
hotter | +0.074 |
Neg logit contributions | |
Jo | -0.158 |
rum | -0.147 |
Jamie | -0.139 |
and | -0.137 |
ud | -0.136 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
� | +0.011 |
idents | +0.010 |
hotter | +0.009 |
sack | +0.009 |
surely | +0.009 |
Neg logit contributions | |
Jo | -0.009 |
rum | -0.009 |
Pen | -0.008 |
ud | -0.008 |
and | -0.008 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
rum | +0.288 |
Jo | +0.287 |
and | +0.269 |
jo | +0.265 |
Jacob | +0.261 |
Neg logit contributions | |
� | -0.066 |
surely | -0.035 |
sack | -0.034 |
hotter | -0.031 |
Dino | -0.026 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
� | +0.716 |
idents | +0.588 |
ory | +0.567 |
sack | +0.566 |
hotter | +0.566 |
Neg logit contributions | |
Jo | -0.810 |
rum | -0.787 |
Pen | -0.692 |
and | -0.688 |
ud | -0.687 |
Token | . |
Token ID | 13 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
� | +0.126 |
idents | +0.113 |
hotter | +0.104 |
sack | +0.102 |
surely | +0.101 |
Neg logit contributions | |
Jo | -0.139 |
rum | -0.132 |
Pen | -0.116 |
ud | -0.116 |
Ali | -0.114 |
Token | Just |
Token ID | 2329 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
� | +0.010 |
idents | +0.009 |
surely | +0.008 |
hotter | +0.008 |
Dino | +0.008 |
Neg logit contributions | |
Jo | -0.009 |
rum | -0.008 |
ud | -0.007 |
Pen | -0.007 |
and | -0.007 |
Token | remember |
Token ID | 3505 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
� | +0.091 |
idents | +0.076 |
hotter | +0.072 |
sack | +0.072 |
ory | +0.072 |
Neg logit contributions | |
Jo | -0.094 |
rum | -0.092 |
Pen | -0.081 |
ud | -0.080 |
and | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
� | +0.039 |
idents | +0.036 |
sack | +0.034 |
hotter | +0.032 |
cooler | +0.032 |
Neg logit contributions | |
Jo | -0.052 |
rum | -0.049 |
jo | -0.044 |
ud | -0.043 |
Jamie | -0.043 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Jo | +0.281 |
rum | +0.274 |
Pen | +0.247 |
Ali | +0.244 |
ud | +0.243 |
Neg logit contributions | |
� | -0.207 |
idents | -0.166 |
ory | -0.158 |
sack | -0.157 |
hotter | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
idents | +0.059 |
� | +0.054 |
ory | +0.044 |
cooler | +0.043 |
sack | +0.041 |
Neg logit contributions | |
Jo | -0.140 |
rum | -0.136 |
ud | -0.127 |
and | -0.123 |
old | -0.120 |
Token | Anna |
Token ID | 11735 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
idents | +0.004 |
� | +0.004 |
cooler | +0.004 |
surely | +0.004 |
hotter | +0.004 |
Neg logit contributions | |
Jo | -0.005 |
rum | -0.005 |
ud | -0.004 |
jo | -0.004 |
and | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
Jo | +0.546 |
rum | +0.507 |
and | +0.502 |
Jamie | +0.477 |
ud | +0.470 |
Neg logit contributions | |
� | -0.279 |
sack | -0.235 |
idents | -0.235 |
cooler | -0.215 |
Dino | -0.207 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
� | +0.007 |
idents | +0.006 |
Dino | +0.005 |
sack | +0.005 |
surely | +0.005 |
Neg logit contributions | |
Jo | -0.008 |
rum | -0.008 |
and | -0.007 |
ud | -0.007 |
jo | -0.006 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
Jo | +0.312 |
rum | +0.309 |
Jacob | +0.287 |
Pen | +0.287 |
Ali | +0.287 |
Neg logit contributions | |
� | -0.054 |
surely | -0.021 |
sack | -0.020 |
hotter | -0.017 |
Dino | -0.012 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
� | +0.617 |
idents | +0.528 |
hotter | +0.486 |
sack | +0.484 |
surely | +0.477 |
Neg logit contributions | |
Jo | -0.892 |
rum | -0.858 |
ud | -0.787 |
Pen | -0.771 |
Ali | -0.768 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
� | +0.108 |
idents | +0.100 |
hotter | +0.090 |
cooler | +0.088 |
sack | +0.088 |
Neg logit contributions | |
Jo | -0.141 |
rum | -0.134 |
ud | -0.121 |
Pen | -0.117 |
jo | -0.116 |
Token | You |
Token ID | 921 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
� | +0.005 |
idents | +0.005 |
Dino | +0.004 |
surely | +0.004 |
hotter | +0.004 |
Neg logit contributions | |
Jo | -0.006 |
rum | -0.006 |
ud | -0.005 |
and | -0.005 |
Jamie | -0.005 |
Token | don |
Token ID | 836 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Jo | +0.024 |
rum | +0.023 |
Pen | +0.021 |
Ali | +0.020 |
ud | +0.020 |
Neg logit contributions | |
� | -0.025 |
idents | -0.021 |
hotter | -0.020 |
ory | -0.020 |
Dino | -0.019 |
Token | 't |
Token ID | 470 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
� | +0.135 |
ory | +0.134 |
idents | +0.128 |
hotter | +0.123 |
cooler | +0.123 |
Neg logit contributions | |
Jo | -0.125 |
rum | -0.118 |
Pen | -0.101 |
ud | -0.101 |
Ali | -0.099 |
Token | � |
Token ID | 241 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Jo | +0.054 |
rum | +0.052 |
Pen | +0.046 |
ud | +0.046 |
and | +0.046 |
Neg logit contributions | |
� | -0.051 |
idents | -0.043 |
sack | -0.041 |
hotter | -0.041 |
surely | -0.040 |
Token | Its |
Token ID | 20459 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
� | +0.070 |
Sorry | +0.054 |
idents | +0.048 |
hotter | +0.046 |
ory | +0.044 |
Neg logit contributions | |
rum | -0.106 |
Jo | -0.099 |
Pen | -0.095 |
Ali | -0.094 |
abel | -0.093 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Jo | +0.135 |
rum | +0.129 |
ud | +0.117 |
Pen | +0.117 |
and | +0.116 |
Neg logit contributions | |
� | -0.106 |
idents | -0.090 |
hotter | -0.083 |
sack | -0.083 |
surely | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
� | +0.086 |
idents | +0.074 |
hotter | +0.067 |
sack | +0.067 |
ory | +0.067 |
Neg logit contributions | |
Jo | -0.128 |
rum | -0.118 |
Pen | -0.114 |
ud | -0.113 |
and | -0.110 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Jo | +0.011 |
rum | +0.011 |
ud | +0.010 |
Pen | +0.009 |
and | +0.009 |
Neg logit contributions | |
� | -0.012 |
idents | -0.010 |
sack | -0.009 |
hotter | -0.009 |
Dino | -0.009 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
Jo | +0.310 |
rum | +0.309 |
and | +0.285 |
jo | +0.284 |
Jacob | +0.283 |
Neg logit contributions | |
� | -0.057 |
surely | -0.026 |
sack | -0.025 |
hotter | -0.023 |
cooler | -0.017 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
� | +0.709 |
idents | +0.587 |
hotter | +0.562 |
sack | +0.561 |
ory | +0.559 |
Neg logit contributions | |
Jo | -0.814 |
rum | -0.789 |
Pen | -0.693 |
ud | -0.689 |
and | -0.688 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
� | +0.110 |
idents | +0.098 |
hotter | +0.087 |
sack | +0.087 |
surely | +0.087 |
Neg logit contributions | |
Jo | -0.145 |
rum | -0.137 |
ud | -0.126 |
Pen | -0.124 |
and | -0.121 |
Token | â |
Token ID | 22940 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Jo | +0.011 |
rum | +0.010 |
ud | +0.009 |
Pen | +0.009 |
jo | +0.009 |
Neg logit contributions | |
� | -0.010 |
idents | -0.008 |
Dino | -0.008 |
hotter | -0.008 |
sack | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
rum | +0.200 |
Jo | +0.199 |
jo | +0.169 |
rd | +0.167 |
old | +0.161 |
Neg logit contributions | |
� | -0.205 |
hotter | -0.175 |
ory | -0.174 |
idents | -0.171 |
cooler | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
� | +0.139 |
idents | +0.117 |
sack | +0.107 |
Dino | +0.103 |
surely | +0.100 |
Neg logit contributions | |
Jo | -0.151 |
rum | -0.146 |
Pen | -0.131 |
ud | -0.130 |
and | -0.127 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Jo | +0.272 |
rum | +0.270 |
Pen | +0.239 |
Ali | +0.237 |
ud | +0.237 |
Neg logit contributions | |
� | -0.214 |
idents | -0.173 |
ory | -0.164 |
sack | -0.163 |
hotter | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | -3.00e-04 |
Pos logit contributions | |
� | +0.080 |
idents | +0.077 |
ory | +0.066 |
cooler | +0.063 |
sack | +0.062 |
Neg logit contributions | |
Jo | -0.143 |
rum | -0.132 |
ud | -0.123 |
Jamie | -0.118 |
Pen | -0.117 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Jo | +0.000 |
rum | +0.000 |
ud | +0.000 |
jo | +0.000 |
and | +0.000 |
Neg logit contributions | |
� | -0.000 |
idents | -0.000 |
cooler | -0.000 |
Dino | -0.000 |
sack | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
� | +0.081 |
idents | +0.070 |
sack | +0.067 |
Dino | +0.065 |
cooler | +0.064 |
Neg logit contributions | |
Jo | -0.153 |
rum | -0.137 |
Jamie | -0.132 |
and | -0.131 |
ud | -0.130 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
� | +0.001 |
idents | +0.001 |
Dino | +0.001 |
surely | +0.001 |
sack | +0.001 |
Neg logit contributions | |
Jo | -0.002 |
rum | -0.001 |
ud | -0.001 |
and | -0.001 |
jo | -0.001 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
rum | +0.287 |
Jo | +0.286 |
and | +0.268 |
Ali | +0.266 |
Jacob | +0.266 |
Neg logit contributions | |
� | -0.061 |
surely | -0.031 |
sack | -0.030 |
hotter | -0.027 |
cooler | -0.020 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
� | +0.636 |
idents | +0.543 |
hotter | +0.505 |
sack | +0.497 |
surely | +0.495 |
Neg logit contributions | |
Jo | -0.872 |
rum | -0.835 |
ud | -0.759 |
Pen | -0.754 |
Ali | -0.747 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
� | +0.108 |
idents | +0.097 |
hotter | +0.089 |
cooler | +0.086 |
sack | +0.086 |
Neg logit contributions | |
Jo | -0.137 |
rum | -0.129 |
ud | -0.116 |
Pen | -0.115 |
jo | -0.113 |
Token | I |
Token ID | 314 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
� | +0.000 |
idents | +0.000 |
Dino | +0.000 |
surely | +0.000 |
hotter | +0.000 |
Neg logit contributions | |
Jo | -0.000 |
rum | -0.000 |
ud | -0.000 |
and | -0.000 |
Jamie | -0.000 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Jo | +0.141 |
rum | +0.134 |
ud | +0.117 |
and | +0.116 |
Pen | +0.114 |
Neg logit contributions | |
� | -0.163 |
idents | -0.135 |
hotter | -0.134 |
ory | -0.132 |
sack | -0.132 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Jo | +0.030 |
rum | +0.029 |
ud | +0.027 |
jo | +0.026 |
and | +0.026 |
Neg logit contributions | |
� | -0.020 |
idents | -0.017 |
hotter | -0.016 |
cooler | -0.016 |
surely | -0.016 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
rum | +0.191 |
Jo | +0.166 |
supposed | +0.160 |
about | +0.157 |
Pen | +0.149 |
Neg logit contributions | |
� | -0.277 |
ory | -0.233 |
glers | -0.226 |
trigger | -0.224 |
clips | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
� | +0.088 |
idents | +0.083 |
sack | +0.072 |
ory | +0.071 |
hotter | +0.068 |
Neg logit contributions | |
Jo | -0.137 |
rum | -0.126 |
Jamie | -0.115 |
ud | -0.115 |
Pen | -0.115 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
� | +0.016 |
idents | +0.013 |
hotter | +0.013 |
sack | +0.013 |
surely | +0.012 |
Neg logit contributions | |
Jo | -0.024 |
rum | -0.023 |
Pen | -0.021 |
ud | -0.021 |
and | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
� | +0.102 |
idents | +0.092 |
sack | +0.084 |
hotter | +0.079 |
Dino | +0.078 |
Neg logit contributions | |
Jo | -0.148 |
rum | -0.135 |
Jamie | -0.127 |
Jacob | -0.127 |
Pen | -0.126 |
Token | Acc |
Token ID | 6366 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
� | +0.009 |
idents | +0.007 |
hotter | +0.007 |
sack | +0.007 |
surely | +0.007 |
Neg logit contributions | |
Jo | -0.007 |
rum | -0.007 |
ud | -0.006 |
Pen | -0.006 |
and | -0.006 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
rum | +0.283 |
Jo | +0.281 |
and | +0.264 |
jo | +0.259 |
Jamie | +0.258 |
Neg logit contributions | |
� | -0.069 |
surely | -0.040 |
sack | -0.038 |
hotter | -0.033 |
cooler | -0.031 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
� | +0.744 |
idents | +0.603 |
ory | +0.602 |
sack | +0.590 |
hotter | +0.589 |
Neg logit contributions | |
Jo | -0.777 |
rum | -0.761 |
and | -0.663 |
Pen | -0.659 |
ud | -0.651 |
Token | . |
Token ID | 13 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
� | +0.127 |
idents | +0.114 |
hotter | +0.105 |
sack | +0.104 |
surely | +0.103 |
Neg logit contributions | |
Jo | -0.133 |
rum | -0.125 |
Pen | -0.110 |
ud | -0.110 |
Ali | -0.108 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
� | +0.008 |
idents | +0.007 |
surely | +0.007 |
hotter | +0.007 |
Dino | +0.007 |
Neg logit contributions | |
Jo | -0.006 |
rum | -0.006 |
ud | -0.005 |
Pen | -0.005 |
and | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Jo | +0.137 |
rum | +0.116 |
Pen | +0.096 |
ud | +0.092 |
and | +0.090 |
Neg logit contributions | |
� | -0.417 |
ory | -0.358 |
idents | -0.355 |
surely | -0.355 |
hotter | -0.351 |
Token | clean |
Token ID | 3424 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Jo | +0.250 |
rum | +0.241 |
Pen | +0.215 |
Ali | +0.214 |
ud | +0.212 |
Neg logit contributions | |
� | -0.207 |
idents | -0.170 |
hotter | -0.165 |
ory | -0.163 |
Dino | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
� | +0.000 |
idents | +0.000 |
sack | +0.000 |
surely | +0.000 |
ory | +0.000 |
Neg logit contributions | |
Jo | -0.000 |
rum | -0.000 |
ud | -0.000 |
and | -0.000 |
Pen | -0.000 |
Token | so |
Token ID | 523 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
� | +0.006 |
sack | +0.005 |
cooler | +0.005 |
idents | +0.005 |
hotter | +0.005 |
Neg logit contributions | |
Jo | -0.008 |
rum | -0.008 |
ud | -0.007 |
and | -0.007 |
jo | -0.007 |
Token | reluctantly |
Token ID | 35462 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Jo | +0.045 |
rum | +0.045 |
ud | +0.042 |
and | +0.041 |
jo | +0.039 |
Neg logit contributions | |
� | -0.024 |
surely | -0.019 |
cooler | -0.019 |
sack | -0.019 |
hotter | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Jo | +0.122 |
rum | +0.122 |
ud | +0.113 |
and | +0.110 |
jo | +0.106 |
Neg logit contributions | |
� | -0.082 |
ory | -0.067 |
surely | -0.067 |
sack | -0.066 |
idents | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
rum | +0.061 |
Jo | +0.059 |
ud | +0.055 |
and | +0.053 |
jo | +0.052 |
Neg logit contributions | |
� | -0.040 |
sack | -0.033 |
surely | -0.032 |
cooler | -0.032 |
hotter | -0.032 |
Token | peanuts |
Token ID | 45612 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
Jo | +0.002 |
rum | +0.002 |
Pen | +0.002 |
ud | +0.002 |
and | +0.002 |
Neg logit contributions | |
� | -0.002 |
idents | -0.002 |
sack | -0.002 |
hotter | -0.002 |
surely | -0.002 |
Token | agreed |
Token ID | 4987 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
� | +0.698 |
idents | +0.574 |
sack | +0.560 |
hotter | +0.548 |
surely | +0.547 |
Neg logit contributions | |
Jo | -0.818 |
rum | -0.794 |
ud | -0.700 |
Pen | -0.697 |
and | -0.693 |
Token | . |
Token ID | 13 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
rum | +0.074 |
Jo | +0.074 |
ud | +0.071 |
jo | +0.067 |
Pen | +0.064 |
Neg logit contributions | |
� | -0.049 |
idents | -0.041 |
surely | -0.040 |
sack | -0.040 |
cooler | -0.040 |
Token | In |
Token ID | 554 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Jo | +0.075 |
rum | +0.074 |
ud | +0.066 |
jo | +0.064 |
and | +0.063 |
Neg logit contributions | |
� | -0.061 |
idents | -0.045 |
Dino | -0.044 |
ory | -0.044 |
surely | -0.043 |
Token | return |
Token ID | 1441 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
� | +0.161 |
surely | +0.130 |
sack | +0.125 |
cooler | +0.120 |
Dino | +0.118 |
Neg logit contributions | |
Jo | -0.224 |
rum | -0.219 |
and | -0.208 |
ud | -0.197 |
jo | -0.195 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
� | +0.098 |
idents | +0.084 |
hotter | +0.080 |
sack | +0.079 |
surely | +0.079 |
Neg logit contributions | |
Jo | -0.094 |
rum | -0.090 |
Pen | -0.079 |
ud | -0.079 |
and | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
idents | +0.066 |
� | +0.061 |
sack | +0.052 |
cooler | +0.051 |
Ros | +0.050 |
Neg logit contributions | |
Jo | -0.136 |
rum | -0.129 |
ud | -0.126 |
and | -0.117 |
Jamie | -0.112 |
Token | sweet |
Token ID | 6029 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Jo | +0.021 |
rum | +0.021 |
ud | +0.021 |
jo | +0.019 |
and | +0.018 |
Neg logit contributions | |
idents | -0.015 |
� | -0.015 |
surely | -0.013 |
cooler | -0.013 |
hotter | -0.013 |
Token | ie |
Token ID | 494 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
Jo | +0.143 |
rum | +0.138 |
and | +0.126 |
ud | +0.125 |
Pen | +0.123 |
Neg logit contributions | |
� | -0.089 |
idents | -0.085 |
ory | -0.084 |
sack | -0.077 |
cooler | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Jo | +0.004 |
rum | +0.004 |
ud | +0.004 |
and | +0.004 |
Jamie | +0.004 |
Neg logit contributions | |
� | -0.003 |
idents | -0.003 |
sack | -0.002 |
cooler | -0.002 |
hotter | -0.002 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Jo | +0.026 |
rum | +0.025 |
ud | +0.023 |
and | +0.022 |
jo | +0.022 |
Neg logit contributions | |
� | -0.025 |
idents | -0.021 |
surely | -0.020 |
Dino | -0.019 |
hotter | -0.019 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
Jo | +0.338 |
rum | +0.333 |
Ali | +0.310 |
Pen | +0.309 |
Jacob | +0.308 |
Neg logit contributions | |
� | -0.050 |
sack | -0.014 |
surely | -0.014 |
hotter | -0.013 |
ory | -0.008 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
� | +0.636 |
idents | +0.540 |
hotter | +0.499 |
sack | +0.496 |
surely | +0.496 |
Neg logit contributions | |
Jo | -0.874 |
rum | -0.841 |
ud | -0.767 |
Pen | -0.755 |
Ali | -0.751 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
� | +0.119 |
idents | +0.110 |
hotter | +0.101 |
sack | +0.098 |
surely | +0.098 |
Neg logit contributions | |
Jo | -0.128 |
rum | -0.123 |
ud | -0.111 |
Pen | -0.106 |
Ali | -0.105 |
Token | Let |
Token ID | 3914 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Jo | +0.026 |
rum | +0.025 |
ud | +0.023 |
and | +0.022 |
jo | +0.022 |
Neg logit contributions | |
� | -0.027 |
idents | -0.023 |
surely | -0.021 |
Dino | -0.021 |
hotter | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Jo | +0.225 |
rum | +0.221 |
ud | +0.183 |
and | +0.178 |
Pen | +0.178 |
Neg logit contributions | |
� | -0.362 |
idents | -0.323 |
sack | -0.314 |
hotter | -0.310 |
surely | -0.307 |
Token | clean |
Token ID | 3424 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Jo | +0.303 |
rum | +0.295 |
ud | +0.265 |
Pen | +0.263 |
and | +0.263 |
Neg logit contributions | |
� | -0.211 |
idents | -0.172 |
sack | -0.166 |
surely | -0.163 |
hotter | -0.161 |
Token | cry |
Token ID | 3960 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
� | +0.190 |
idents | +0.160 |
hotter | +0.153 |
sack | +0.153 |
surely | +0.151 |
Neg logit contributions | |
Jo | -0.204 |
rum | -0.197 |
Pen | -0.173 |
ud | -0.173 |
and | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
Jo | +0.353 |
rum | +0.325 |
Jamie | +0.299 |
ud | +0.295 |
Pen | +0.293 |
Neg logit contributions | |
� | -0.240 |
idents | -0.220 |
ory | -0.206 |
Dino | -0.196 |
hotter | -0.195 |
Token | boys |
Token ID | 6510 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
� | +0.001 |
Dino | +0.001 |
idents | +0.001 |
sack | +0.001 |
cooler | +0.001 |
Neg logit contributions | |
Jo | -0.002 |
rum | -0.002 |
ud | -0.002 |
jo | -0.002 |
and | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
� | +0.081 |
idents | +0.071 |
sack | +0.071 |
ory | +0.068 |
cooler | +0.065 |
Neg logit contributions | |
Jo | -0.149 |
rum | -0.136 |
Jamie | -0.130 |
and | -0.128 |
Ali | -0.126 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Jo | +0.022 |
rum | +0.021 |
ud | +0.019 |
and | +0.018 |
Pen | +0.018 |
Neg logit contributions | |
� | -0.021 |
idents | -0.018 |
sack | -0.017 |
Dino | -0.017 |
surely | -0.017 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
rum | +0.282 |
Jo | +0.275 |
and | +0.258 |
Jamie | +0.258 |
Jacob | +0.257 |
Neg logit contributions | |
� | -0.086 |
surely | -0.058 |
sack | -0.046 |
cooler | -0.039 |
gem | -0.039 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
� | +0.608 |
idents | +0.529 |
hotter | +0.490 |
sack | +0.484 |
surely | +0.475 |
Neg logit contributions | |
Jo | -0.884 |
rum | -0.839 |
ud | -0.777 |
Pen | -0.775 |
Ali | -0.768 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
� | +0.111 |
idents | +0.096 |
hotter | +0.091 |
sack | +0.090 |
ory | +0.090 |
Neg logit contributions | |
Jo | -0.114 |
rum | -0.108 |
Pen | -0.096 |
ud | -0.096 |
Ali | -0.094 |
Token | I |
Token ID | 314 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Jo | +0.029 |
rum | +0.027 |
ud | +0.025 |
and | +0.024 |
Pen | +0.024 |
Neg logit contributions | |
� | -0.028 |
idents | -0.024 |
Dino | -0.022 |
hotter | -0.022 |
sack | -0.022 |
Token | have |
Token ID | 423 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
Jo | +0.142 |
rum | +0.137 |
ud | +0.119 |
and | +0.117 |
Pen | +0.115 |
Neg logit contributions | |
� | -0.160 |
idents | -0.132 |
hotter | -0.130 |
Dino | -0.130 |
ory | -0.129 |
Token | something |
Token ID | 1223 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
� | +0.044 |
idents | +0.037 |
sack | +0.037 |
hotter | +0.035 |
Dino | +0.035 |
Neg logit contributions | |
Jo | -0.054 |
rum | -0.052 |
jo | -0.047 |
Pen | -0.046 |
Ali | -0.046 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
rum | +0.236 |
Jo | +0.225 |
Pen | +0.199 |
Ali | +0.194 |
ud | +0.193 |
Neg logit contributions | |
� | -0.248 |
ory | -0.203 |
idents | -0.195 |
trigger | -0.189 |
sack | -0.189 |
Token | , |
Token ID | 11 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
� | +0.076 |
idents | +0.076 |
sack | +0.061 |
hotter | +0.060 |
ory | +0.059 |
Neg logit contributions | |
Jo | -0.138 |
rum | -0.129 |
ud | -0.120 |
and | -0.118 |
Jamie | -0.118 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
� | +0.003 |
idents | +0.003 |
cooler | +0.003 |
sack | +0.003 |
hotter | +0.003 |
Neg logit contributions | |
Jo | -0.006 |
rum | -0.006 |
ud | -0.005 |
jo | -0.005 |
and | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
� | +0.091 |
idents | +0.081 |
sack | +0.073 |
hotter | +0.068 |
surely | +0.067 |
Neg logit contributions | |
Jo | -0.143 |
rum | -0.132 |
Jamie | -0.125 |
Jacob | -0.123 |
and | -0.123 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Jo | +0.006 |
rum | +0.005 |
ud | +0.005 |
and | +0.005 |
Pen | +0.005 |
Neg logit contributions | |
� | -0.006 |
idents | -0.005 |
surely | -0.005 |
Dino | -0.005 |
sack | -0.005 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
Jo | +0.303 |
rum | +0.303 |
Ali | +0.279 |
and | +0.278 |
jo | +0.278 |
Neg logit contributions | |
� | -0.064 |
surely | -0.033 |
sack | -0.032 |
hotter | -0.025 |
cooler | -0.023 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
� | +0.718 |
idents | +0.593 |
ory | +0.570 |
sack | +0.569 |
hotter | +0.568 |
Neg logit contributions | |
Jo | -0.798 |
rum | -0.774 |
Pen | -0.680 |
and | -0.676 |
ud | -0.676 |
Token | . |
Token ID | 13 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
� | +0.119 |
idents | +0.105 |
hotter | +0.098 |
sack | +0.097 |
surely | +0.096 |
Neg logit contributions | |
Jo | -0.126 |
rum | -0.119 |
Pen | -0.105 |
ud | -0.105 |
Ali | -0.103 |
Token | Let |
Token ID | 3914 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Jo | +0.009 |
rum | +0.008 |
ud | +0.007 |
and | +0.007 |
Pen | +0.007 |
Neg logit contributions | |
� | -0.009 |
idents | -0.008 |
Dino | -0.008 |
surely | -0.008 |
hotter | -0.008 |
Token | 's |
Token ID | 338 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Jo | +0.160 |
rum | +0.142 |
Pen | +0.117 |
ud | +0.112 |
and | +0.111 |
Neg logit contributions | |
� | -0.410 |
idents | -0.354 |
ory | -0.350 |
surely | -0.348 |
hotter | -0.347 |
Token | clean |
Token ID | 3424 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Jo | +0.269 |
rum | +0.260 |
Pen | +0.231 |
Ali | +0.230 |
ud | +0.230 |
Neg logit contributions | |
� | -0.208 |
idents | -0.169 |
hotter | -0.162 |
ory | -0.161 |
Dino | -0.156 |
Token | was |
Token ID | 373 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
� | +0.037 |
idents | +0.033 |
hotter | +0.032 |
sack | +0.032 |
surely | +0.031 |
Neg logit contributions | |
Jo | -0.025 |
rum | -0.024 |
ud | -0.021 |
and | -0.020 |
Pen | -0.020 |
Token | an |
Token ID | 281 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Jo | +0.040 |
rum | +0.040 |
Pen | +0.036 |
Ali | +0.035 |
Jacob | +0.034 |
Neg logit contributions | |
� | -0.051 |
idents | -0.043 |
ory | -0.042 |
sack | -0.040 |
surely | -0.040 |
Token | accident |
Token ID | 5778 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
� | +0.040 |
idents | +0.035 |
sack | +0.034 |
hotter | +0.033 |
ory | +0.033 |
Neg logit contributions | |
Jo | -0.049 |
rum | -0.045 |
Pen | -0.042 |
Ali | -0.041 |
and | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
Jo | +0.357 |
rum | +0.343 |
Jamie | +0.306 |
ud | +0.306 |
Pen | +0.303 |
Neg logit contributions | |
� | -0.268 |
idents | -0.230 |
hotter | -0.224 |
sack | -0.217 |
cooler | -0.215 |
Token | Acc |
Token ID | 6366 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
� | +0.008 |
idents | +0.007 |
Dino | +0.006 |
surely | +0.006 |
hotter | +0.006 |
Neg logit contributions | |
Jo | -0.008 |
rum | -0.008 |
ud | -0.007 |
and | -0.007 |
jo | -0.007 |
Token | idents |
Token ID | 3231 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
Jo | +0.290 |
rum | +0.290 |
and | +0.272 |
Ali | +0.270 |
Jacob | +0.269 |
Neg logit contributions | |
� | -0.066 |
surely | -0.035 |
sack | -0.033 |
hotter | -0.029 |
Dino | -0.025 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
� | +0.670 |
idents | +0.559 |
hotter | +0.528 |
sack | +0.526 |
surely | +0.521 |
Neg logit contributions | |
Jo | -0.838 |
rum | -0.809 |
ud | -0.722 |
Pen | -0.721 |
Ali | -0.712 |
Token | . |
Token ID | 13 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
� | +0.101 |
idents | +0.092 |
hotter | +0.083 |
cooler | +0.082 |
sack | +0.081 |
Neg logit contributions | |
Jo | -0.143 |
rum | -0.134 |
ud | -0.121 |
Pen | -0.120 |
jo | -0.118 |
Token | I |
Token ID | 314 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
� | +0.006 |
idents | +0.006 |
Dino | +0.005 |
hotter | +0.005 |
surely | +0.005 |
Neg logit contributions | |
Jo | -0.007 |
rum | -0.007 |
ud | -0.006 |
and | -0.006 |
jo | -0.006 |
Token | 'm |
Token ID | 1101 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Jo | +0.129 |
rum | +0.120 |
ud | +0.105 |
and | +0.103 |
Pen | +0.101 |
Neg logit contributions | |
� | -0.174 |
idents | -0.148 |
hotter | -0.147 |
ory | -0.145 |
sack | -0.143 |
Token | not |
Token ID | 407 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Jo | +0.028 |
rum | +0.027 |
ud | +0.024 |
Pen | +0.024 |
and | +0.024 |
Neg logit contributions | |
� | -0.020 |
idents | -0.016 |
hotter | -0.015 |
sack | -0.015 |
surely | -0.015 |
Token | gives |
Token ID | 3607 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
� | +0.008 |
cooler | +0.007 |
sack | +0.007 |
idents | +0.006 |
surely | +0.006 |
Neg logit contributions | |
rum | -0.011 |
Jo | -0.010 |
and | -0.010 |
ud | -0.009 |
jo | -0.009 |
Token | Sara |
Token ID | 24799 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
� | +0.072 |
idents | +0.060 |
hotter | +0.057 |
sack | +0.057 |
surely | +0.057 |
Neg logit contributions | |
Jo | -0.080 |
rum | -0.077 |
Pen | -0.069 |
ud | -0.068 |
Ali | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
Jo | +0.237 |
rum | +0.232 |
ud | +0.202 |
and | +0.196 |
jo | +0.195 |
Neg logit contributions | |
� | -0.178 |
ory | -0.155 |
cooler | -0.154 |
sack | -0.154 |
idents | -0.154 |
Token | bowl |
Token ID | 9396 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
� | +0.002 |
idents | +0.002 |
hotter | +0.001 |
sack | +0.001 |
surely | +0.001 |
Neg logit contributions | |
Jo | -0.002 |
rum | -0.002 |
Pen | -0.002 |
ud | -0.002 |
and | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
� | +0.020 |
idents | +0.017 |
sack | +0.017 |
ory | +0.017 |
surely | +0.016 |
Neg logit contributions | |
Jo | -0.016 |
rum | -0.015 |
Pen | -0.013 |
ud | -0.013 |
Ali | -0.013 |
Token | peanuts |
Token ID | 45612 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
Jo | +0.260 |
rum | +0.253 |
Pen | +0.228 |
ud | +0.225 |
Ali | +0.224 |
Neg logit contributions | |
� | -0.193 |
idents | -0.159 |
surely | -0.149 |
hotter | -0.148 |
sack | -0.147 |
Token | and |
Token ID | 290 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
� | +0.816 |
idents | +0.713 |
hotter | +0.690 |
surely | +0.677 |
sack | +0.661 |
Neg logit contributions | |
Jo | -0.658 |
rum | -0.653 |
and | -0.569 |
Pen | -0.565 |
ud | -0.558 |
Token | Ben |
Token ID | 3932 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
� | +0.057 |
sack | +0.047 |
idents | +0.047 |
cooler | +0.045 |
Dino | +0.045 |
Neg logit contributions | |
Jo | -0.082 |
rum | -0.080 |
and | -0.073 |
ud | -0.072 |
jo | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
Jo | +0.055 |
rum | +0.051 |
ud | +0.046 |
and | +0.046 |
jo | +0.045 |
Neg logit contributions | |
� | -0.047 |
sack | -0.039 |
idents | -0.039 |
ory | -0.038 |
cooler | -0.038 |
Token | bowl |
Token ID | 9396 |
Feature activation | +9.83e-02 |
Pos logit contributions | |
Jo | +0.007 |
rum | +0.006 |
Pen | +0.006 |
ud | +0.006 |
Ali | +0.006 |
Neg logit contributions | |
� | -0.005 |
idents | -0.005 |
hotter | -0.004 |
surely | -0.004 |
ory | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
� | +0.009 |
cooler | +0.007 |
idents | +0.007 |
ory | +0.007 |
sack | +0.007 |
Neg logit contributions | |
Jo | -0.010 |
rum | -0.009 |
Ali | -0.008 |
Pen | -0.008 |
ud | -0.008 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
� | +0.169 |
sack | +0.147 |
cooler | +0.141 |
surely | +0.140 |
ory | +0.137 |
Neg logit contributions | |
rum | -0.207 |
Jo | -0.202 |
and | -0.177 |
ud | -0.177 |
jo | -0.170 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
rum | +0.126 |
Jo | +0.124 |
ud | +0.111 |
and | +0.111 |
Pen | +0.110 |
Neg logit contributions | |
� | -0.093 |
sack | -0.083 |
cooler | -0.077 |
surely | -0.074 |
idents | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Jo | +0.006 |
rum | +0.006 |
ud | +0.006 |
Jamie | +0.005 |
Pen | +0.005 |
Neg logit contributions | |
� | -0.005 |
surely | -0.004 |
Dino | -0.004 |
sack | -0.004 |
ory | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Jo | +0.015 |
rum | +0.014 |
ud | +0.013 |
Pen | +0.013 |
and | +0.012 |
Neg logit contributions | |
� | -0.011 |
Dino | -0.008 |
ory | -0.008 |
idents | -0.008 |
surely | -0.007 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.039 |
rum | +0.039 |
ud | +0.034 |
Pen | +0.034 |
and | +0.034 |
Neg logit contributions | |
� | -0.020 |
idents | -0.014 |
sack | -0.014 |
hotter | -0.013 |
ory | -0.013 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
rum | +1.049 |
and | +0.967 |
Jo | +0.925 |
ud | +0.893 |
Pen | +0.885 |
Neg logit contributions | |
� | -0.813 |
ory | -0.734 |
surely | -0.693 |
sack | -0.656 |
idents | -0.646 |
Token | was |
Token ID | 373 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
rum | +1.066 |
and | +0.981 |
Jo | +0.938 |
ud | +0.900 |
Pen | +0.897 |
Neg logit contributions | |
� | -0.808 |
ory | -0.712 |
surely | -0.677 |
sack | -0.645 |
continued | -0.638 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
rum | +0.086 |
Jo | +0.084 |
jo | +0.074 |
ud | +0.074 |
and | +0.073 |
Neg logit contributions | |
� | -0.060 |
surely | -0.051 |
hotter | -0.049 |
cooler | -0.049 |
prett | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
� | +0.092 |
idents | +0.078 |
sack | +0.075 |
cooler | +0.073 |
hotter | +0.071 |
Neg logit contributions | |
Jo | -0.118 |
rum | -0.115 |
Pen | -0.103 |
ud | -0.102 |
Ali | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rum | +0.017 |
ud | +0.016 |
e | +0.016 |
ggie | +0.016 |
Jo | +0.016 |
Neg logit contributions | |
� | -0.006 |
idents | -0.004 |
cooler | -0.004 |
surely | -0.003 |
still | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
� | +0.011 |
idents | +0.009 |
sack | +0.009 |
surely | +0.009 |
cooler | +0.008 |
Neg logit contributions | |
rum | -0.013 |
Jo | -0.013 |
and | -0.012 |
Pen | -0.011 |
ud | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
Jo | +0.066 |
rum | +0.065 |
Jamie | +0.060 |
Pen | +0.060 |
old | +0.059 |
Neg logit contributions | |
� | -0.027 |
cooler | -0.025 |
idents | -0.024 |
hotter | -0.023 |
sack | -0.022 |
Token | harder |
Token ID | 7069 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
� | +0.015 |
ory | +0.012 |
idents | +0.012 |
sack | +0.012 |
Dino | +0.011 |
Neg logit contributions | |
Jo | -0.016 |
rum | -0.015 |
Pen | -0.014 |
Ali | -0.014 |
Jacob | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Jo | +0.063 |
rum | +0.060 |
Jamie | +0.057 |
ud | +0.057 |
and | +0.055 |
Neg logit contributions | |
� | -0.031 |
idents | -0.029 |
cooler | -0.028 |
sack | -0.026 |
hotter | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
rum | +0.022 |
Jo | +0.021 |
ud | +0.019 |
and | +0.018 |
jo | +0.018 |
Neg logit contributions | |
� | -0.017 |
idents | -0.014 |
sack | -0.013 |
Dino | -0.013 |
hotter | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
� | +0.001 |
Dino | +0.001 |
Ros | +0.001 |
Sorry | +0.001 |
surely | +0.001 |
Neg logit contributions | |
rum | -0.004 |
Jo | -0.003 |
clim | -0.003 |
abel | -0.003 |
ud | -0.003 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
� | +0.000 |
Sorry | +0.000 |
sack | +0.000 |
Dino | +0.000 |
surely | +0.000 |
Neg logit contributions | |
rum | -0.001 |
Jo | -0.001 |
ud | -0.001 |
Pen | -0.001 |
abel | -0.001 |
Token | jo |
Token ID | 7639 |
Feature activation | -7.45e+00 |
Pos logit contributions | |
rum | +1.102 |
and | +0.947 |
Jo | +0.944 |
Jacob | +0.940 |
Pen | +0.911 |
Neg logit contributions | |
� | -0.762 |
ory | -0.675 |
ized | -0.653 |
surely | -0.648 |
sack | -0.637 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
rum | +0.889 |
Jo | +0.798 |
and | +0.777 |
ud | +0.723 |
Jacob | +0.722 |
Neg logit contributions | |
� | -0.469 |
sack | -0.406 |
continued | -0.384 |
ory | -0.373 |
surely | -0.368 |
Token | his |
Token ID | 465 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
sack | +0.009 |
� | +0.009 |
Dino | +0.009 |
idents | +0.009 |
cooler | +0.008 |
Neg logit contributions | |
rum | -0.015 |
Jo | -0.015 |
ud | -0.014 |
and | -0.014 |
rd | -0.013 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Jo | +0.132 |
rum | +0.125 |
Pen | +0.112 |
ud | +0.111 |
Ali | +0.110 |
Neg logit contributions | |
� | -0.128 |
idents | -0.109 |
hotter | -0.105 |
surely | -0.103 |
ory | -0.102 |
Token | were |
Token ID | 547 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
� | +0.087 |
sack | +0.069 |
idents | +0.068 |
hotter | +0.067 |
ory | +0.066 |
Neg logit contributions | |
rum | -0.142 |
Jo | -0.141 |
Pen | -0.125 |
and | -0.124 |
ud | -0.123 |
Token | lucky |
Token ID | 9670 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Jo | +0.041 |
rum | +0.039 |
Pen | +0.035 |
ud | +0.034 |
Ali | +0.034 |
Neg logit contributions | |
� | -0.039 |
idents | -0.033 |
hotter | -0.031 |
sack | -0.031 |
ory | -0.031 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
� | +0.169 |
sack | +0.147 |
cooler | +0.141 |
surely | +0.140 |
ory | +0.137 |
Neg logit contributions | |
rum | -0.207 |
Jo | -0.202 |
and | -0.177 |
ud | -0.177 |
jo | -0.170 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
rum | +0.126 |
Jo | +0.124 |
ud | +0.111 |
and | +0.111 |
Pen | +0.110 |
Neg logit contributions | |
� | -0.093 |
sack | -0.083 |
cooler | -0.077 |
surely | -0.074 |
idents | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Jo | +0.006 |
rum | +0.006 |
ud | +0.006 |
Jamie | +0.005 |
Pen | +0.005 |
Neg logit contributions | |
� | -0.005 |
surely | -0.004 |
Dino | -0.004 |
sack | -0.004 |
ory | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Jo | +0.015 |
rum | +0.014 |
ud | +0.013 |
Pen | +0.013 |
and | +0.012 |
Neg logit contributions | |
� | -0.011 |
Dino | -0.008 |
ory | -0.008 |
idents | -0.008 |
surely | -0.007 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.039 |
rum | +0.039 |
ud | +0.034 |
Pen | +0.034 |
and | +0.034 |
Neg logit contributions | |
� | -0.020 |
idents | -0.014 |
sack | -0.014 |
hotter | -0.013 |
ory | -0.013 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
rum | +1.049 |
and | +0.967 |
Jo | +0.925 |
ud | +0.893 |
Pen | +0.885 |
Neg logit contributions | |
� | -0.813 |
ory | -0.734 |
surely | -0.693 |
sack | -0.656 |
idents | -0.646 |
Token | was |
Token ID | 373 |
Feature activation | -7.78e-01 |
Pos logit contributions | |
rum | +1.066 |
and | +0.981 |
Jo | +0.938 |
ud | +0.900 |
Pen | +0.897 |
Neg logit contributions | |
� | -0.808 |
ory | -0.712 |
surely | -0.677 |
sack | -0.645 |
continued | -0.638 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
rum | +0.086 |
Jo | +0.084 |
jo | +0.074 |
ud | +0.074 |
and | +0.073 |
Neg logit contributions | |
� | -0.060 |
surely | -0.051 |
hotter | -0.049 |
cooler | -0.049 |
prett | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
� | +0.092 |
idents | +0.078 |
sack | +0.075 |
cooler | +0.073 |
hotter | +0.071 |
Neg logit contributions | |
Jo | -0.118 |
rum | -0.115 |
Pen | -0.103 |
ud | -0.102 |
Ali | -0.100 |
Token | He |
Token ID | 679 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
rum | +0.017 |
ud | +0.016 |
e | +0.016 |
ggie | +0.016 |
Jo | +0.016 |
Neg logit contributions | |
� | -0.006 |
idents | -0.004 |
cooler | -0.004 |
surely | -0.003 |
still | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
� | +0.085 |
idents | +0.073 |
hotter | +0.069 |
ory | +0.067 |
Sorry | +0.066 |
Neg logit contributions | |
Jo | -0.087 |
rum | -0.083 |
Pen | -0.073 |
and | -0.073 |
Ali | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
rum | +0.103 |
Jo | +0.100 |
ud | +0.097 |
and | +0.092 |
jo | +0.092 |
Neg logit contributions | |
� | -0.060 |
sack | -0.053 |
surely | -0.048 |
cooler | -0.047 |
Dino | -0.047 |
Token | village |
Token ID | 7404 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
� | +0.015 |
idents | +0.012 |
ory | +0.011 |
hotter | +0.011 |
surely | +0.011 |
Neg logit contributions | |
Jo | -0.019 |
rum | -0.018 |
Pen | -0.017 |
ud | -0.017 |
Jacob | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
rum | +0.059 |
Jo | +0.057 |
ud | +0.054 |
Pen | +0.051 |
Ali | +0.050 |
Neg logit contributions | |
� | -0.036 |
sack | -0.033 |
cooler | -0.032 |
surely | -0.031 |
ized | -0.030 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
rum | +0.047 |
ud | +0.043 |
Jo | +0.040 |
and | +0.040 |
rd | +0.039 |
Neg logit contributions | |
� | -0.029 |
idents | -0.020 |
Dino | -0.020 |
surely | -0.019 |
hotter | -0.018 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.329 |
and | +0.221 |
ud | +0.214 |
uzzle | +0.206 |
liar | +0.194 |
Neg logit contributions | |
� | -0.881 |
surely | -0.835 |
continued | -0.818 |
finally | -0.813 |
still | -0.811 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
rum | +1.046 |
and | +0.937 |
ud | +0.877 |
uzzle | +0.830 |
Jo | +0.826 |
Neg logit contributions | |
� | -0.835 |
surely | -0.732 |
ized | -0.713 |
ory | -0.706 |
continued | -0.699 |
Token | with |
Token ID | 351 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Jo | +0.015 |
rum | +0.014 |
Pen | +0.012 |
Ali | +0.012 |
Jacob | +0.012 |
Neg logit contributions | |
� | -0.018 |
idents | -0.015 |
sack | -0.014 |
hotter | -0.014 |
surely | -0.014 |
Token | anticipation |
Token ID | 24054 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
� | +0.001 |
idents | +0.001 |
sack | +0.001 |
surely | +0.001 |
hotter | +0.001 |
Neg logit contributions | |
Jo | -0.001 |
rum | -0.001 |
ud | -0.001 |
Pen | -0.001 |
and | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
Jo | +0.264 |
rum | +0.259 |
ud | +0.238 |
Pen | +0.237 |
Ali | +0.231 |
Neg logit contributions | |
� | -0.194 |
idents | -0.156 |
surely | -0.155 |
ory | -0.152 |
sack | -0.151 |
Token | asked |
Token ID | 1965 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
� | +0.000 |
surely | +0.000 |
idents | +0.000 |
sack | +0.000 |
Dino | +0.000 |
Neg logit contributions | |
rum | -0.001 |
Jo | -0.001 |
ud | -0.001 |
and | -0.001 |
jo | -0.001 |
Token | unloaded |
Token ID | 49975 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Jo | +0.064 |
rum | +0.062 |
ud | +0.056 |
and | +0.055 |
Pen | +0.055 |
Neg logit contributions | |
� | -0.053 |
hotter | -0.043 |
surely | -0.043 |
idents | -0.043 |
sack | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
� | +0.103 |
idents | +0.088 |
hotter | +0.083 |
ory | +0.083 |
sack | +0.083 |
Neg logit contributions | |
Jo | -0.091 |
rum | -0.088 |
Pen | -0.076 |
Ali | -0.076 |
ud | -0.076 |
Token | John |
Token ID | 1757 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
rum | +0.017 |
ud | +0.014 |
Jo | +0.014 |
and | +0.014 |
rd | +0.014 |
Neg logit contributions | |
� | -0.015 |
hotter | -0.013 |
surely | -0.013 |
cooler | -0.013 |
Dino | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
rum | +0.534 |
Jo | +0.510 |
and | +0.469 |
ud | +0.465 |
Pen | +0.458 |
Neg logit contributions | |
� | -0.379 |
surely | -0.310 |
sack | -0.304 |
ory | -0.299 |
idents | -0.292 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
surely | +0.020 |
� | +0.019 |
Dino | +0.019 |
Ros | +0.018 |
continued | +0.018 |
Neg logit contributions | |
rum | -0.014 |
ud | -0.013 |
and | -0.012 |
rd | -0.011 |
old | -0.011 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.622 |
and | +0.532 |
ud | +0.505 |
Pen | +0.474 |
Jo | +0.464 |
Neg logit contributions | |
� | -0.621 |
surely | -0.576 |
continued | -0.551 |
ory | -0.550 |
finally | -0.525 |
Token | started |
Token ID | 2067 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
rum | +1.155 |
and | +1.068 |
Jo | +1.006 |
ud | +0.987 |
Pen | +0.985 |
Neg logit contributions | |
� | -0.744 |
surely | -0.622 |
ory | -0.603 |
continued | -0.592 |
ized | -0.591 |
Token | to |
Token ID | 284 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
� | +0.239 |
sack | +0.196 |
hotter | +0.195 |
cooler | +0.191 |
idents | +0.188 |
Neg logit contributions | |
rum | -0.249 |
Jo | -0.243 |
jo | -0.222 |
ud | -0.222 |
Pen | -0.220 |
Token | make |
Token ID | 787 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
Jo | +0.101 |
rum | +0.100 |
ud | +0.093 |
and | +0.092 |
jo | +0.089 |
Neg logit contributions | |
� | -0.071 |
sack | -0.058 |
idents | -0.056 |
surely | -0.055 |
hotter | -0.054 |
Token | their |
Token ID | 511 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
� | +0.008 |
idents | +0.007 |
hotter | +0.007 |
sack | +0.007 |
cooler | +0.006 |
Neg logit contributions | |
rum | -0.009 |
Jo | -0.009 |
ud | -0.008 |
and | -0.008 |
Pen | -0.008 |
Token | way |
Token ID | 835 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Jo | +0.122 |
rum | +0.118 |
Pen | +0.105 |
ud | +0.104 |
and | +0.103 |
Neg logit contributions | |
� | -0.098 |
idents | -0.081 |
hotter | -0.077 |
sack | -0.077 |
surely | -0.076 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
rum | +0.074 |
Jo | +0.072 |
and | +0.065 |
ud | +0.065 |
Pen | +0.063 |
Neg logit contributions | |
� | -0.051 |
surely | -0.042 |
sack | -0.041 |
idents | -0.040 |
ory | -0.040 |
Token | so |
Token ID | 523 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
� | +0.118 |
idents | +0.098 |
surely | +0.097 |
hotter | +0.096 |
sack | +0.096 |
Neg logit contributions | |
Jo | -0.126 |
rum | -0.122 |
ud | -0.109 |
Pen | -0.106 |
Ali | -0.106 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Jo | +0.052 |
rum | +0.050 |
ud | +0.045 |
Pen | +0.045 |
Ali | +0.045 |
Neg logit contributions | |
� | -0.036 |
idents | -0.029 |
surely | -0.028 |
sack | -0.028 |
hotter | -0.027 |
Token | ! |
Token ID | 0 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
� | +0.314 |
cooler | +0.261 |
ory | +0.259 |
sack | +0.256 |
idents | +0.252 |
Neg logit contributions | |
rum | -0.354 |
Jo | -0.342 |
Pen | -0.304 |
Jamie | -0.296 |
jo | -0.296 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
� | +0.012 |
idents | +0.009 |
surely | +0.008 |
ory | +0.008 |
Dino | +0.008 |
Neg logit contributions | |
rum | -0.015 |
Jo | -0.015 |
ud | -0.014 |
and | -0.013 |
jo | -0.013 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.051 |
Jo | +0.051 |
ud | +0.045 |
Ali | +0.045 |
Pen | +0.045 |
Neg logit contributions | |
� | -0.024 |
sack | -0.016 |
idents | -0.016 |
hotter | -0.015 |
ory | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
rum | +1.016 |
and | +0.947 |
Jo | +0.915 |
ud | +0.868 |
Pen | +0.848 |
Neg logit contributions | |
� | -0.846 |
ory | -0.762 |
surely | -0.719 |
sack | -0.686 |
idents | -0.684 |
Token | a |
Token ID | 257 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
rum | +0.085 |
Jo | +0.081 |
jo | +0.072 |
ud | +0.072 |
and | +0.071 |
Neg logit contributions | |
� | -0.059 |
surely | -0.050 |
hotter | -0.049 |
cooler | -0.048 |
prett | -0.047 |
Token | lively |
Token ID | 29696 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Jo | +0.034 |
rum | +0.033 |
Pen | +0.029 |
ud | +0.029 |
Ali | +0.028 |
Neg logit contributions | |
� | -0.035 |
idents | -0.030 |
hotter | -0.028 |
sack | -0.028 |
surely | -0.028 |
Token | three |
Token ID | 1115 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
� | +0.105 |
sack | +0.091 |
ory | +0.088 |
cooler | +0.086 |
surely | +0.079 |
Neg logit contributions | |
rum | -0.154 |
Jo | -0.143 |
and | -0.133 |
ud | -0.126 |
jo | -0.122 |
Token | - |
Token ID | 12 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
rum | +0.383 |
Jo | +0.347 |
Pen | +0.329 |
Ali | +0.328 |
and | +0.326 |
Neg logit contributions | |
� | -0.376 |
ory | -0.352 |
sack | -0.337 |
cooler | -0.331 |
ized | -0.325 |
Token | friend |
Token ID | 1545 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
� | +0.027 |
sack | +0.025 |
ory | +0.023 |
cooler | +0.022 |
surely | +0.020 |
Neg logit contributions | |
rum | -0.039 |
Jo | -0.038 |
Pen | -0.035 |
Ali | -0.034 |
Jacob | -0.034 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
� | +0.006 |
sack | +0.005 |
Dino | +0.005 |
ory | +0.005 |
cooler | +0.005 |
Neg logit contributions | |
rum | -0.009 |
Jo | -0.008 |
ud | -0.008 |
Jamie | -0.007 |
Pen | -0.007 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.680 |
ud | +0.574 |
and | +0.549 |
Jo | +0.529 |
Jamie | +0.510 |
Neg logit contributions | |
� | -0.564 |
ory | -0.513 |
surely | -0.467 |
finally | -0.451 |
ized | -0.442 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
rum | +1.054 |
and | +0.946 |
ud | +0.897 |
Jo | +0.869 |
Ali | +0.841 |
Neg logit contributions | |
� | -0.842 |
surely | -0.696 |
ory | -0.685 |
ized | -0.662 |
continued | -0.652 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
rum | +0.036 |
ud | +0.033 |
ggie | +0.031 |
rd | +0.031 |
e | +0.030 |
Neg logit contributions | |
� | -0.025 |
surely | -0.018 |
Dino | -0.017 |
idents | -0.017 |
Ros | -0.017 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.371 |
and | +0.252 |
uzzle | +0.251 |
ud | +0.250 |
liar | +0.231 |
Neg logit contributions | |
� | -0.832 |
surely | -0.784 |
still | -0.772 |
continued | -0.769 |
finally | -0.769 |
Token | was |
Token ID | 373 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
rum | +1.099 |
and | +0.984 |
ud | +0.928 |
uzzle | +0.887 |
Jo | +0.885 |
Neg logit contributions | |
� | -0.810 |
surely | -0.691 |
ized | -0.686 |
continued | -0.648 |
ory | -0.645 |
Token | thrilled |
Token ID | 20536 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
rum | +0.094 |
Jo | +0.086 |
ud | +0.084 |
jo | +0.082 |
and | +0.080 |
Neg logit contributions | |
� | -0.055 |
surely | -0.051 |
still | -0.048 |
cooler | -0.046 |
hotter | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
rum | +0.110 |
Jo | +0.108 |
ud | +0.098 |
Pen | +0.095 |
Ali | +0.092 |
Neg logit contributions | |
� | -0.091 |
idents | -0.080 |
ory | -0.073 |
surely | -0.072 |
sack | -0.072 |
Token | see |
Token ID | 766 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Jo | +0.096 |
rum | +0.093 |
ud | +0.086 |
and | +0.083 |
Pen | +0.083 |
Neg logit contributions | |
� | -0.076 |
idents | -0.060 |
surely | -0.060 |
sack | -0.060 |
ory | -0.057 |
Token | Big |
Token ID | 4403 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Dino | +0.025 |
cooler | +0.024 |
prett | +0.024 |
brand | +0.023 |
Ros | +0.022 |
Neg logit contributions | |
rum | -0.069 |
ud | -0.062 |
rd | -0.060 |
and | -0.057 |
anne | -0.057 |
Token | 've |
Token ID | 1053 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
� | +0.139 |
idents | +0.113 |
surely | +0.113 |
sack | +0.111 |
ory | +0.108 |
Neg logit contributions | |
Jo | -0.154 |
rum | -0.152 |
and | -0.138 |
Pen | -0.137 |
Ali | -0.133 |
Token | got |
Token ID | 1392 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
� | +0.068 |
surely | +0.058 |
sack | +0.058 |
idents | +0.056 |
cooler | +0.055 |
Neg logit contributions | |
rum | -0.064 |
Jo | -0.063 |
jo | -0.056 |
and | -0.056 |
Ali | -0.056 |
Token | an |
Token ID | 281 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
� | +0.173 |
idents | +0.147 |
sack | +0.139 |
hotter | +0.138 |
ory | +0.138 |
Neg logit contributions | |
Jo | -0.162 |
rum | -0.156 |
Pen | -0.136 |
ud | -0.135 |
and | -0.134 |
Token | idea |
Token ID | 2126 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
� | +0.029 |
idents | +0.024 |
sack | +0.023 |
surely | +0.023 |
hotter | +0.023 |
Neg logit contributions | |
Jo | -0.036 |
rum | -0.035 |
Pen | -0.031 |
Ali | -0.031 |
ud | -0.031 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
� | +0.084 |
sack | +0.075 |
surely | +0.073 |
cooler | +0.072 |
reward | +0.068 |
Neg logit contributions | |
Jo | -0.136 |
ud | -0.134 |
rum | -0.121 |
jo | -0.119 |
Pen | -0.119 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
ud | +0.619 |
rum | +0.613 |
Jo | +0.556 |
and | +0.534 |
Jamie | +0.526 |
Neg logit contributions | |
� | -0.566 |
surely | -0.513 |
ory | -0.497 |
sack | -0.473 |
idents | -0.460 |
Token | . |
Token ID | 13 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ud | +0.942 |
rum | +0.936 |
Jo | +0.894 |
and | +0.892 |
Jamie | +0.851 |
Neg logit contributions | |
� | -0.885 |
surely | -0.770 |
sack | -0.740 |
ory | -0.719 |
idents | -0.697 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Jo | +0.033 |
rum | +0.033 |
ud | +0.032 |
and | +0.030 |
jo | +0.028 |
Neg logit contributions | |
� | -0.030 |
Dino | -0.024 |
surely | -0.024 |
idents | -0.024 |
sack | -0.023 |
Token | next |
Token ID | 1306 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
� | +0.012 |
Dino | +0.011 |
cooler | +0.011 |
surely | +0.011 |
sack | +0.010 |
Neg logit contributions | |
rum | -0.025 |
ud | -0.024 |
Jo | -0.023 |
jo | -0.022 |
and | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
� | +0.253 |
surely | +0.219 |
idents | +0.209 |
cooler | +0.208 |
sack | +0.202 |
Neg logit contributions | |
rum | -0.277 |
Jo | -0.267 |
and | -0.252 |
Pen | -0.244 |
ud | -0.242 |
Token | we |
Token ID | 356 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
rum | +0.115 |
Jo | +0.111 |
ud | +0.110 |
and | +0.099 |
jo | +0.097 |
Neg logit contributions | |
� | -0.073 |
surely | -0.067 |
idents | -0.067 |
Dino | -0.066 |
sack | -0.066 |
Token | Don |
Token ID | 3987 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
rum | +0.087 |
Jo | +0.072 |
Jacob | +0.072 |
ud | +0.071 |
Pen | +0.071 |
Neg logit contributions | |
� | -0.072 |
Sorry | -0.070 |
hotter | -0.069 |
idents | -0.065 |
surely | -0.064 |
Token | 't |
Token ID | 470 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
� | +0.143 |
idents | +0.114 |
surely | +0.110 |
sack | +0.106 |
hotter | +0.105 |
Neg logit contributions | |
Jo | -0.207 |
rum | -0.206 |
ud | -0.186 |
and | -0.183 |
Pen | -0.182 |
Token | worry |
Token ID | 5490 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
� | +0.135 |
idents | +0.120 |
sack | +0.115 |
hotter | +0.110 |
ory | +0.110 |
Neg logit contributions | |
Jo | -0.180 |
rum | -0.174 |
ud | -0.161 |
Pen | -0.157 |
jo | -0.154 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
rum | +0.140 |
ud | +0.137 |
Jo | +0.136 |
e | +0.135 |
old | +0.131 |
Neg logit contributions | |
idents | -0.082 |
cooler | -0.069 |
� | -0.064 |
Dino | -0.062 |
ory | -0.062 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
rum | +0.009 |
ud | +0.009 |
old | +0.008 |
anne | +0.008 |
e | +0.008 |
Neg logit contributions | |
idents | -0.008 |
cooler | -0.008 |
surely | -0.007 |
hotter | -0.007 |
� | -0.007 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
and | +0.562 |
ud | +0.547 |
rum | +0.531 |
Jo | +0.518 |
Jacob | +0.485 |
Neg logit contributions | |
� | -0.567 |
idents | -0.512 |
Dino | -0.508 |
surely | -0.503 |
ory | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
and | +1.017 |
Jo | +1.007 |
rum | +0.982 |
ud | +0.958 |
Jamie | +0.917 |
Neg logit contributions | |
� | -0.831 |
idents | -0.710 |
sack | -0.701 |
surely | -0.678 |
ory | -0.663 |
Token | I |
Token ID | 314 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Jo | +0.018 |
rum | +0.018 |
ud | +0.016 |
and | +0.015 |
Pen | +0.015 |
Neg logit contributions | |
� | -0.018 |
idents | -0.015 |
Dino | -0.015 |
surely | -0.014 |
sack | -0.014 |
Token | can |
Token ID | 460 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Jo | +0.168 |
rum | +0.162 |
ud | +0.142 |
Pen | +0.142 |
and | +0.140 |
Neg logit contributions | |
� | -0.162 |
idents | -0.137 |
hotter | -0.131 |
sack | -0.130 |
ory | -0.129 |
Token | help |
Token ID | 1037 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
� | +0.137 |
idents | +0.112 |
sack | +0.105 |
hotter | +0.105 |
surely | +0.104 |
Neg logit contributions | |
Jo | -0.192 |
rum | -0.187 |
ud | -0.167 |
Pen | -0.167 |
and | -0.165 |
Token | you |
Token ID | 345 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
� | +0.063 |
idents | +0.057 |
sack | +0.053 |
Dino | +0.050 |
hotter | +0.049 |
Neg logit contributions | |
Jo | -0.126 |
rum | -0.123 |
ud | -0.120 |
jo | -0.115 |
rd | -0.113 |
Token | into |
Token ID | 656 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
Jo | +0.221 |
rum | +0.215 |
ud | +0.191 |
Pen | +0.191 |
Ali | +0.188 |
Neg logit contributions | |
� | -0.163 |
idents | -0.134 |
sack | -0.127 |
hotter | -0.126 |
surely | -0.126 |
Token | his |
Token ID | 465 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
� | +0.193 |
sack | +0.169 |
cooler | +0.161 |
Dino | +0.143 |
hotter | +0.137 |
Neg logit contributions | |
rum | -0.344 |
Jo | -0.329 |
jo | -0.315 |
ud | -0.309 |
and | -0.308 |
Token | best |
Token ID | 1266 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Jo | +0.139 |
rum | +0.136 |
ud | +0.119 |
and | +0.118 |
Pen | +0.115 |
Neg logit contributions | |
� | -0.121 |
sack | -0.102 |
idents | -0.099 |
cooler | -0.096 |
surely | -0.094 |
Token | friend |
Token ID | 1545 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
� | +0.027 |
sack | +0.025 |
ory | +0.023 |
cooler | +0.022 |
surely | +0.020 |
Neg logit contributions | |
rum | -0.039 |
Jo | -0.038 |
Pen | -0.035 |
Ali | -0.034 |
Jacob | -0.034 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
� | +0.006 |
sack | +0.005 |
Dino | +0.005 |
ory | +0.005 |
cooler | +0.005 |
Neg logit contributions | |
rum | -0.009 |
Jo | -0.008 |
ud | -0.008 |
Jamie | -0.007 |
Pen | -0.007 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.680 |
ud | +0.574 |
and | +0.549 |
Jo | +0.529 |
Jamie | +0.510 |
Neg logit contributions | |
� | -0.564 |
ory | -0.513 |
surely | -0.467 |
finally | -0.451 |
ized | -0.442 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
rum | +1.054 |
and | +0.946 |
ud | +0.897 |
Jo | +0.869 |
Ali | +0.841 |
Neg logit contributions | |
� | -0.842 |
surely | -0.696 |
ory | -0.685 |
ized | -0.662 |
continued | -0.652 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
rum | +0.036 |
ud | +0.033 |
ggie | +0.031 |
rd | +0.031 |
e | +0.030 |
Neg logit contributions | |
� | -0.025 |
surely | -0.018 |
Dino | -0.017 |
idents | -0.017 |
Ros | -0.017 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.371 |
and | +0.252 |
uzzle | +0.251 |
ud | +0.250 |
liar | +0.231 |
Neg logit contributions | |
� | -0.832 |
surely | -0.784 |
still | -0.772 |
continued | -0.769 |
finally | -0.769 |
Token | was |
Token ID | 373 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
rum | +1.099 |
and | +0.984 |
ud | +0.928 |
uzzle | +0.887 |
Jo | +0.885 |
Neg logit contributions | |
� | -0.810 |
surely | -0.691 |
ized | -0.686 |
continued | -0.648 |
ory | -0.645 |
Token | thrilled |
Token ID | 20536 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
rum | +0.094 |
Jo | +0.086 |
ud | +0.084 |
jo | +0.082 |
and | +0.080 |
Neg logit contributions | |
� | -0.055 |
surely | -0.051 |
still | -0.048 |
cooler | -0.046 |
hotter | -0.046 |
Token | His |
Token ID | 6653 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
� | +0.011 |
Sorry | +0.010 |
surely | +0.010 |
hotter | +0.009 |
still | +0.009 |
Neg logit contributions | |
rum | -0.013 |
Pen | -0.012 |
Jacob | -0.012 |
ud | -0.012 |
Mae | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
� | +0.000 |
idents | +0.000 |
hotter | +0.000 |
surely | +0.000 |
ory | +0.000 |
Neg logit contributions | |
Jo | -0.000 |
rum | -0.000 |
Pen | -0.000 |
Ali | -0.000 |
ud | -0.000 |
Token | looked |
Token ID | 3114 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
� | +0.087 |
sack | +0.075 |
hotter | +0.070 |
ory | +0.069 |
surely | +0.069 |
Neg logit contributions | |
rum | -0.162 |
Jo | -0.148 |
and | -0.139 |
Pen | -0.136 |
ud | -0.135 |
Token | at |
Token ID | 379 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
� | +0.065 |
idents | +0.054 |
hotter | +0.051 |
sack | +0.051 |
surely | +0.051 |
Neg logit contributions | |
Jo | -0.073 |
rum | -0.070 |
Pen | -0.062 |
ud | -0.062 |
and | -0.062 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
rum | +0.008 |
and | +0.008 |
Jo | +0.007 |
rd | +0.007 |
ud | +0.007 |
Neg logit contributions | |
� | -0.003 |
Dino | -0.003 |
idents | -0.003 |
sack | -0.003 |
surely | -0.003 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.721 |
Jo | +0.691 |
ud | +0.690 |
Jamie | +0.639 |
and | +0.638 |
Neg logit contributions | |
� | -0.451 |
idents | -0.377 |
ory | -0.371 |
sack | -0.370 |
surely | -0.361 |
Token | and |
Token ID | 290 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
rum | +1.115 |
Jo | +1.030 |
ud | +1.017 |
and | +0.984 |
Jamie | +0.966 |
Neg logit contributions | |
� | -0.733 |
idents | -0.625 |
sack | -0.620 |
ized | -0.606 |
ory | -0.598 |
Token | said |
Token ID | 531 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
� | +0.017 |
idents | +0.014 |
sack | +0.013 |
hotter | +0.013 |
ory | +0.013 |
Neg logit contributions | |
rum | -0.029 |
Jo | -0.029 |
ud | -0.026 |
and | -0.026 |
Pen | -0.025 |
Token | " |
Token ID | 366 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
� | +0.041 |
idents | +0.034 |
sack | +0.032 |
cooler | +0.030 |
surely | +0.030 |
Neg logit contributions | |
Jo | -0.072 |
rum | -0.070 |
ud | -0.069 |
and | -0.064 |
jo | -0.064 |
Token | Don |
Token ID | 3987 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
rum | +0.087 |
Jo | +0.072 |
Jacob | +0.072 |
ud | +0.071 |
Pen | +0.071 |
Neg logit contributions | |
� | -0.072 |
Sorry | -0.070 |
hotter | -0.069 |
idents | -0.065 |
surely | -0.064 |
Token | 't |
Token ID | 470 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
� | +0.143 |
idents | +0.114 |
surely | +0.110 |
sack | +0.106 |
hotter | +0.105 |
Neg logit contributions | |
Jo | -0.207 |
rum | -0.206 |
ud | -0.186 |
and | -0.183 |
Pen | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Jo | +0.005 |
rum | +0.004 |
ud | +0.004 |
and | +0.004 |
jo | +0.004 |
Neg logit contributions | |
� | -0.004 |
surely | -0.003 |
sack | -0.003 |
cooler | -0.003 |
idents | -0.003 |
Token | same |
Token ID | 976 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
� | +0.033 |
idents | +0.028 |
sack | +0.027 |
hotter | +0.026 |
cooler | +0.026 |
Neg logit contributions | |
Jo | -0.042 |
rum | -0.042 |
ud | -0.037 |
Pen | -0.036 |
and | -0.036 |
Token | time |
Token ID | 640 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rum | +0.087 |
Jo | +0.085 |
Pen | +0.078 |
ud | +0.075 |
and | +0.075 |
Neg logit contributions | |
� | -0.074 |
sack | -0.065 |
cooler | -0.064 |
surely | -0.060 |
idents | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
rum | +0.110 |
Jo | +0.108 |
Pen | +0.098 |
ud | +0.095 |
Ali | +0.093 |
Neg logit contributions | |
� | -0.079 |
surely | -0.061 |
cooler | -0.061 |
idents | -0.060 |
sack | -0.060 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Jo | +0.025 |
rum | +0.024 |
ud | +0.022 |
Pen | +0.022 |
and | +0.022 |
Neg logit contributions | |
� | -0.016 |
idents | -0.012 |
Dino | -0.011 |
surely | -0.011 |
sack | -0.011 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.030 |
rum | +0.030 |
ud | +0.026 |
Pen | +0.026 |
and | +0.026 |
Neg logit contributions | |
� | -0.018 |
idents | -0.013 |
sack | -0.013 |
hotter | -0.013 |
ory | -0.013 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +1.057 |
and | +0.973 |
Jo | +0.955 |
ud | +0.900 |
Pen | +0.899 |
Neg logit contributions | |
� | -0.835 |
ory | -0.737 |
surely | -0.686 |
sack | -0.667 |
idents | -0.650 |
Token | was |
Token ID | 373 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
rum | +1.072 |
and | +0.984 |
Jo | +0.970 |
Pen | +0.908 |
ud | +0.907 |
Neg logit contributions | |
� | -0.833 |
ory | -0.715 |
surely | -0.674 |
sack | -0.662 |
idents | -0.641 |
Token | a |
Token ID | 257 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
rum | +0.072 |
Jo | +0.071 |
jo | +0.063 |
and | +0.062 |
ud | +0.062 |
Neg logit contributions | |
� | -0.049 |
surely | -0.041 |
hotter | -0.041 |
cooler | -0.041 |
prett | -0.038 |
Token | clever |
Token ID | 14169 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Jo | +0.028 |
rum | +0.027 |
ud | +0.023 |
Pen | +0.023 |
and | +0.023 |
Neg logit contributions | |
� | -0.026 |
idents | -0.022 |
sack | -0.021 |
hotter | -0.021 |
surely | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
� | +0.140 |
sack | +0.122 |
ory | +0.122 |
cooler | +0.118 |
surely | +0.109 |
Neg logit contributions | |
rum | -0.213 |
Jo | -0.200 |
and | -0.188 |
ud | -0.173 |
rd | -0.171 |
Token | same |
Token ID | 976 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
� | +0.033 |
idents | +0.028 |
sack | +0.027 |
hotter | +0.026 |
cooler | +0.026 |
Neg logit contributions | |
Jo | -0.042 |
rum | -0.042 |
ud | -0.037 |
Pen | -0.036 |
and | -0.036 |
Token | time |
Token ID | 640 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rum | +0.087 |
Jo | +0.085 |
Pen | +0.078 |
ud | +0.075 |
and | +0.075 |
Neg logit contributions | |
� | -0.074 |
sack | -0.065 |
cooler | -0.064 |
surely | -0.060 |
idents | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
rum | +0.110 |
Jo | +0.108 |
Pen | +0.098 |
ud | +0.095 |
Ali | +0.093 |
Neg logit contributions | |
� | -0.079 |
surely | -0.061 |
cooler | -0.061 |
idents | -0.060 |
sack | -0.060 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Jo | +0.025 |
rum | +0.024 |
ud | +0.022 |
Pen | +0.022 |
and | +0.022 |
Neg logit contributions | |
� | -0.016 |
idents | -0.012 |
Dino | -0.011 |
surely | -0.011 |
sack | -0.011 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.030 |
rum | +0.030 |
ud | +0.026 |
Pen | +0.026 |
and | +0.026 |
Neg logit contributions | |
� | -0.018 |
idents | -0.013 |
sack | -0.013 |
hotter | -0.013 |
ory | -0.013 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +1.057 |
and | +0.973 |
Jo | +0.955 |
ud | +0.900 |
Pen | +0.899 |
Neg logit contributions | |
� | -0.835 |
ory | -0.737 |
surely | -0.686 |
sack | -0.667 |
idents | -0.650 |
Token | was |
Token ID | 373 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
rum | +1.072 |
and | +0.984 |
Jo | +0.970 |
Pen | +0.908 |
ud | +0.907 |
Neg logit contributions | |
� | -0.833 |
ory | -0.715 |
surely | -0.674 |
sack | -0.662 |
idents | -0.641 |
Token | a |
Token ID | 257 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
rum | +0.072 |
Jo | +0.071 |
jo | +0.063 |
and | +0.062 |
ud | +0.062 |
Neg logit contributions | |
� | -0.049 |
surely | -0.041 |
hotter | -0.041 |
cooler | -0.041 |
prett | -0.038 |
Token | clever |
Token ID | 14169 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Jo | +0.028 |
rum | +0.027 |
ud | +0.023 |
Pen | +0.023 |
and | +0.023 |
Neg logit contributions | |
� | -0.026 |
idents | -0.022 |
sack | -0.021 |
hotter | -0.021 |
surely | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
� | +0.140 |
sack | +0.122 |
ory | +0.122 |
cooler | +0.118 |
surely | +0.109 |
Neg logit contributions | |
rum | -0.213 |
Jo | -0.200 |
and | -0.188 |
ud | -0.173 |
rd | -0.171 |
Token | boy |
Token ID | 2933 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
rum | +0.226 |
Jo | +0.223 |
and | +0.196 |
ud | +0.194 |
Jamie | +0.191 |
Neg logit contributions | |
� | -0.137 |
sack | -0.111 |
idents | -0.109 |
ory | -0.109 |
cooler | -0.109 |
Token | â |
Token ID | 22940 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Jo | +0.033 |
rum | +0.032 |
ud | +0.029 |
and | +0.028 |
jo | +0.027 |
Neg logit contributions | |
� | -0.027 |
idents | -0.021 |
Dino | -0.020 |
surely | -0.019 |
sack | -0.019 |
Token | € |
Token ID | 26391 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Jo | +0.234 |
rum | +0.219 |
jo | +0.194 |
Pen | +0.190 |
Ali | +0.186 |
Neg logit contributions | |
� | -0.215 |
idents | -0.183 |
sack | -0.179 |
ory | -0.177 |
hotter | -0.177 |
Token | |
Token ID | 220 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
� | +0.136 |
idents | +0.104 |
Dino | +0.091 |
sack | +0.088 |
� | +0.088 |
Neg logit contributions | |
rum | -0.160 |
Jo | -0.149 |
and | -0.142 |
ud | -0.139 |
Pen | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Jo | +0.147 |
rum | +0.145 |
ud | +0.127 |
Pen | +0.125 |
jo | +0.123 |
Neg logit contributions | |
� | -0.119 |
idents | -0.094 |
hotter | -0.089 |
Dino | -0.089 |
surely | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
� | +0.011 |
Dino | +0.008 |
Sorry | +0.007 |
ory | +0.007 |
surely | +0.007 |
Neg logit contributions | |
rum | -0.016 |
Jo | -0.015 |
ud | -0.014 |
Pen | -0.014 |
Jacob | -0.014 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
� | +0.006 |
Sorry | +0.004 |
surely | +0.004 |
Dino | +0.004 |
Ros | +0.004 |
Neg logit contributions | |
rum | -0.008 |
Jo | -0.007 |
ud | -0.007 |
Jacob | -0.007 |
Pen | -0.007 |
Token | hopped |
Token ID | 45230 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
rum | +0.816 |
and | +0.727 |
ud | +0.666 |
uzzle | +0.649 |
Jo | +0.642 |
Neg logit contributions | |
� | -1.000 |
surely | -0.948 |
ory | -0.890 |
ized | -0.882 |
idents | -0.870 |
Token | on |
Token ID | 319 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
Jo | +0.091 |
rum | +0.087 |
Pen | +0.079 |
and | +0.078 |
Ali | +0.077 |
Neg logit contributions | |
� | -0.073 |
idents | -0.062 |
hotter | -0.057 |
sack | -0.057 |
ory | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
� | +0.044 |
sack | +0.036 |
cooler | +0.036 |
idents | +0.035 |
surely | +0.034 |
Neg logit contributions | |
rum | -0.058 |
Jo | -0.055 |
ud | -0.051 |
jo | -0.050 |
and | -0.049 |
Token | bike |
Token ID | 7161 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
� | +0.022 |
sack | +0.019 |
idents | +0.018 |
cooler | +0.018 |
hotter | +0.018 |
Neg logit contributions | |
rum | -0.026 |
Jo | -0.025 |
ud | -0.023 |
and | -0.022 |
Pen | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
rum | +0.009 |
Jo | +0.009 |
ud | +0.008 |
Jamie | +0.008 |
Pen | +0.007 |
Neg logit contributions | |
� | -0.006 |
sack | -0.005 |
surely | -0.005 |
cooler | -0.005 |
idents | -0.005 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
rum | +0.334 |
ud | +0.310 |
and | +0.288 |
Jo | +0.283 |
rd | +0.269 |
Neg logit contributions | |
� | -0.202 |
idents | -0.179 |
sack | -0.170 |
cooler | -0.165 |
Dino | -0.162 |
Token | shouted |
Token ID | 17293 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
rum | +0.537 |
ud | +0.498 |
lions | +0.468 |
living | +0.439 |
and | +0.431 |
Neg logit contributions | |
� | -0.581 |
finally | -0.555 |
surely | -0.540 |
ory | -0.538 |
continued | -0.531 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Jo | +0.257 |
rum | +0.247 |
ud | +0.224 |
Pen | +0.215 |
and | +0.215 |
Neg logit contributions | |
� | -0.239 |
idents | -0.203 |
sack | -0.194 |
surely | -0.193 |
hotter | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
rum | +0.021 |
ud | +0.019 |
rd | +0.017 |
Jo | +0.017 |
old | +0.017 |
Neg logit contributions | |
� | -0.012 |
idents | -0.009 |
sack | -0.008 |
surely | -0.008 |
Dino | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
� | +0.007 |
Sorry | +0.005 |
Dino | +0.005 |
Ros | +0.004 |
surely | +0.004 |
Neg logit contributions | |
rum | -0.018 |
ud | -0.016 |
rd | -0.015 |
abel | -0.015 |
ounces | -0.015 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
� | +0.010 |
Sorry | +0.010 |
surely | +0.008 |
Ros | +0.008 |
There | +0.008 |
Neg logit contributions | |
rum | -0.012 |
ud | -0.011 |
supposed | -0.010 |
eer | -0.010 |
Jacob | -0.009 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
rum | +1.128 |
Jo | +1.015 |
and | +0.990 |
ud | +0.975 |
Pen | +0.939 |
Neg logit contributions | |
� | -0.785 |
surely | -0.645 |
ory | -0.642 |
sack | -0.641 |
idents | -0.629 |
Token | the |
Token ID | 262 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
� | +0.149 |
idents | +0.124 |
sack | +0.123 |
surely | +0.120 |
hotter | +0.119 |
Neg logit contributions | |
Jo | -0.210 |
rum | -0.208 |
and | -0.192 |
ud | -0.190 |
jo | -0.182 |
Token | book |
Token ID | 1492 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
� | +0.050 |
idents | +0.044 |
sack | +0.043 |
surely | +0.042 |
hotter | +0.042 |
Neg logit contributions | |
Jo | -0.033 |
rum | -0.031 |
ud | -0.027 |
Pen | -0.026 |
and | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Jo | +0.078 |
rum | +0.077 |
ud | +0.067 |
Pen | +0.066 |
and | +0.065 |
Neg logit contributions | |
� | -0.075 |
idents | -0.062 |
sack | -0.061 |
surely | -0.060 |
hotter | -0.058 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
� | +0.021 |
idents | +0.017 |
sack | +0.017 |
hotter | +0.016 |
surely | +0.016 |
Neg logit contributions | |
Jo | -0.024 |
rum | -0.024 |
ud | -0.021 |
Pen | -0.021 |
and | -0.021 |
Token | thing |
Token ID | 1517 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
sack | +0.168 |
cooler | +0.150 |
gem | +0.144 |
idents | +0.134 |
� | +0.133 |
Neg logit contributions | |
Jo | -0.262 |
Jamie | -0.248 |
ud | -0.247 |
and | -0.237 |
rum | -0.237 |
Token | to |
Token ID | 284 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
Jo | +0.043 |
rum | +0.041 |
ud | +0.038 |
Jamie | +0.038 |
Pen | +0.036 |
Neg logit contributions | |
� | -0.027 |
sack | -0.023 |
idents | -0.023 |
Dino | -0.022 |
surely | -0.022 |
Token | do |
Token ID | 466 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Jo | +0.082 |
rum | +0.079 |
ud | +0.073 |
Pen | +0.071 |
and | +0.071 |
Neg logit contributions | |
� | -0.068 |
idents | -0.057 |
sack | -0.056 |
surely | -0.053 |
ory | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
� | +0.009 |
idents | +0.008 |
sack | +0.008 |
surely | +0.008 |
hotter | +0.007 |
Neg logit contributions | |
Jo | -0.011 |
rum | -0.010 |
Pen | -0.009 |
ud | -0.009 |
Ali | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Jo | +0.025 |
rum | +0.024 |
ud | +0.023 |
Pen | +0.022 |
isa | +0.021 |
Neg logit contributions | |
� | -0.013 |
idents | -0.010 |
Dino | -0.009 |
surely | -0.009 |
sack | -0.008 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.037 |
rum | +0.036 |
Pen | +0.032 |
ud | +0.032 |
Ali | +0.032 |
Neg logit contributions | |
� | -0.024 |
idents | -0.019 |
sack | -0.018 |
hotter | -0.018 |
ory | -0.018 |
Token | el |
Token ID | 417 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
rum | +1.010 |
Jo | +0.960 |
and | +0.925 |
Pen | +0.884 |
ud | +0.878 |
Neg logit contributions | |
� | -0.861 |
ory | -0.747 |
surely | -0.709 |
sack | -0.703 |
idents | -0.700 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
� | +0.112 |
sack | +0.101 |
ory | +0.099 |
Dino | +0.099 |
idents | +0.097 |
Neg logit contributions | |
rum | -0.154 |
Jo | -0.151 |
and | -0.138 |
Pen | -0.134 |
ud | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
rum | +0.036 |
Jo | +0.035 |
ud | +0.032 |
and | +0.032 |
jo | +0.031 |
Neg logit contributions | |
� | -0.022 |
sack | -0.020 |
cooler | -0.019 |
Dino | -0.019 |
hotter | -0.019 |
Token | banana |
Token ID | 25996 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Jo | +0.031 |
rum | +0.028 |
Pen | +0.027 |
Ali | +0.026 |
Jacob | +0.026 |
Neg logit contributions | |
� | -0.032 |
idents | -0.027 |
surely | -0.026 |
hotter | -0.025 |
ory | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
Jo | +0.179 |
rum | +0.172 |
Pen | +0.151 |
ud | +0.150 |
and | +0.149 |
Neg logit contributions | |
� | -0.181 |
idents | -0.154 |
hotter | -0.147 |
sack | -0.146 |
surely | -0.145 |
Token | 't |
Token ID | 470 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
� | +0.211 |
idents | +0.192 |
ory | +0.191 |
sack | +0.182 |
hotter | +0.181 |
Neg logit contributions | |
Jo | -0.217 |
rum | -0.207 |
Pen | -0.187 |
Ali | -0.181 |
ud | -0.181 |
Token | bud |
Token ID | 3600 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
� | +0.152 |
idents | +0.124 |
ory | +0.119 |
hotter | +0.117 |
Dino | +0.113 |
Neg logit contributions | |
Jo | -0.182 |
rum | -0.179 |
Pen | -0.157 |
Ali | -0.155 |
and | -0.153 |
Token | ge |
Token ID | 469 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
� | +0.090 |
idents | +0.075 |
ory | +0.073 |
hotter | +0.073 |
sack | +0.072 |
Neg logit contributions | |
Jo | -0.113 |
rum | -0.107 |
Pen | -0.100 |
Jacob | -0.098 |
Ali | -0.097 |
Token | ! |
Token ID | 0 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Jo | +0.169 |
rum | +0.154 |
Jamie | +0.146 |
Pen | +0.144 |
ud | +0.143 |
Neg logit contributions | |
� | -0.094 |
sack | -0.081 |
idents | -0.079 |
cooler | -0.075 |
surely | -0.074 |
Token | Jo |
Token ID | 5302 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
� | +0.018 |
idents | +0.015 |
surely | +0.013 |
sack | +0.013 |
hotter | +0.013 |
Neg logit contributions | |
rum | -0.021 |
Jo | -0.018 |
ud | -0.017 |
and | -0.016 |
Jacob | -0.016 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.438 |
uzzle | +0.334 |
and | +0.334 |
lions | +0.317 |
weet | +0.312 |
Neg logit contributions | |
� | -0.761 |
still | -0.690 |
ized | -0.690 |
surely | -0.686 |
finally | -0.682 |
Token | was |
Token ID | 373 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
rum | +1.165 |
and | +1.050 |
Jo | +1.044 |
Pen | +0.973 |
Jacob | +0.968 |
Neg logit contributions | |
� | -0.764 |
surely | -0.601 |
idents | -0.595 |
ized | -0.593 |
ory | -0.588 |
Token | getting |
Token ID | 1972 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Jo | +0.085 |
rum | +0.084 |
jo | +0.076 |
ud | +0.075 |
and | +0.074 |
Neg logit contributions | |
� | -0.051 |
surely | -0.042 |
hotter | -0.041 |
cooler | -0.040 |
sack | -0.039 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
Jo | +0.040 |
and | +0.039 |
old | +0.038 |
Pen | +0.038 |
rum | +0.037 |
Neg logit contributions | |
� | -0.065 |
idents | -0.058 |
actus | -0.051 |
ory | -0.051 |
ols | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +0.334 |
idents | +0.274 |
hotter | +0.264 |
sack | +0.263 |
cooler | +0.260 |
Neg logit contributions | |
Jo | -0.413 |
rum | -0.406 |
Pen | -0.364 |
Ali | -0.353 |
Jamie | -0.349 |
Token | She |
Token ID | 1375 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
rum | +0.024 |
Jo | +0.021 |
ud | +0.021 |
e | +0.020 |
and | +0.019 |
Neg logit contributions | |
� | -0.015 |
idents | -0.011 |
surely | -0.010 |
hotter | -0.010 |
sack | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Jo | +0.328 |
rum | +0.328 |
ud | +0.304 |
jo | +0.301 |
Ali | +0.281 |
Neg logit contributions | |
� | -0.245 |
cooler | -0.210 |
hotter | -0.210 |
surely | -0.208 |
sack | -0.203 |
Token | reliable |
Token ID | 9314 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
� | +0.083 |
idents | +0.069 |
surely | +0.068 |
ory | +0.067 |
hotter | +0.067 |
Neg logit contributions | |
Jo | -0.094 |
rum | -0.090 |
ud | -0.081 |
Pen | -0.079 |
Ali | -0.079 |
Token | ." |
Token ID | 526 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
� | +0.127 |
sack | +0.112 |
ory | +0.111 |
cooler | +0.108 |
idents | +0.107 |
Neg logit contributions | |
Jo | -0.181 |
rum | -0.162 |
jo | -0.153 |
Ali | -0.153 |
Jamie | -0.151 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Jo | +0.237 |
rum | +0.230 |
ud | +0.203 |
Pen | +0.201 |
and | +0.198 |
Neg logit contributions | |
� | -0.211 |
idents | -0.172 |
sack | -0.161 |
Dino | -0.159 |
ory | -0.158 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.046 |
rum | +0.045 |
Pen | +0.040 |
ud | +0.040 |
and | +0.040 |
Neg logit contributions | |
� | -0.027 |
idents | -0.020 |
sack | -0.019 |
hotter | -0.019 |
ory | -0.019 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +1.062 |
Jo | +0.988 |
and | +0.987 |
ud | +0.919 |
Pen | +0.904 |
Neg logit contributions | |
� | -0.824 |
ory | -0.711 |
surely | -0.672 |
sack | -0.657 |
idents | -0.652 |
Token | was |
Token ID | 373 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
rum | +1.062 |
Jo | +0.985 |
and | +0.984 |
ud | +0.915 |
Pen | +0.905 |
Neg logit contributions | |
� | -0.830 |
ory | -0.704 |
surely | -0.673 |
sack | -0.660 |
idents | -0.654 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
rum | +0.084 |
Jo | +0.082 |
ud | +0.072 |
jo | +0.071 |
and | +0.071 |
Neg logit contributions | |
� | -0.061 |
surely | -0.051 |
cooler | -0.050 |
hotter | -0.050 |
prett | -0.048 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Jo | +0.270 |
rum | +0.266 |
jo | +0.238 |
ud | +0.235 |
Pen | +0.228 |
Neg logit contributions | |
� | -0.203 |
sack | -0.168 |
idents | -0.159 |
cooler | -0.158 |
surely | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
rum | +0.014 |
Jo | +0.013 |
ud | +0.013 |
jo | +0.012 |
and | +0.012 |
Neg logit contributions | |
� | -0.005 |
sack | -0.004 |
cooler | -0.004 |
golf | -0.004 |
surely | -0.003 |
Token | park |
Token ID | 3952 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
� | +0.030 |
sack | +0.027 |
cooler | +0.026 |
hotter | +0.025 |
idents | +0.024 |
Neg logit contributions | |
rum | -0.047 |
Jo | -0.045 |
ud | -0.040 |
jo | -0.040 |
and | -0.039 |
Token | been |
Token ID | 587 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
� | +0.078 |
surely | +0.068 |
sack | +0.067 |
idents | +0.065 |
cooler | +0.063 |
Neg logit contributions | |
rum | -0.077 |
Jo | -0.074 |
ud | -0.068 |
and | -0.066 |
Ali | -0.066 |
Token | very |
Token ID | 845 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
Jo | +0.328 |
rum | +0.328 |
ud | +0.304 |
jo | +0.301 |
Ali | +0.281 |
Neg logit contributions | |
� | -0.245 |
cooler | -0.210 |
hotter | -0.210 |
surely | -0.208 |
sack | -0.203 |
Token | reliable |
Token ID | 9314 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
� | +0.083 |
idents | +0.069 |
surely | +0.068 |
ory | +0.067 |
hotter | +0.067 |
Neg logit contributions | |
Jo | -0.094 |
rum | -0.090 |
ud | -0.081 |
Pen | -0.079 |
Ali | -0.079 |
Token | ." |
Token ID | 526 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
� | +0.127 |
sack | +0.112 |
ory | +0.111 |
cooler | +0.108 |
idents | +0.107 |
Neg logit contributions | |
Jo | -0.181 |
rum | -0.162 |
jo | -0.153 |
Ali | -0.153 |
Jamie | -0.151 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Jo | +0.237 |
rum | +0.230 |
ud | +0.203 |
Pen | +0.201 |
and | +0.198 |
Neg logit contributions | |
� | -0.211 |
idents | -0.172 |
sack | -0.161 |
Dino | -0.159 |
ory | -0.158 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Jo | +0.046 |
rum | +0.045 |
Pen | +0.040 |
ud | +0.040 |
and | +0.040 |
Neg logit contributions | |
� | -0.027 |
idents | -0.020 |
sack | -0.019 |
hotter | -0.019 |
ory | -0.019 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +1.062 |
Jo | +0.988 |
and | +0.987 |
ud | +0.919 |
Pen | +0.904 |
Neg logit contributions | |
� | -0.824 |
ory | -0.711 |
surely | -0.672 |
sack | -0.657 |
idents | -0.652 |
Token | was |
Token ID | 373 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
rum | +1.062 |
Jo | +0.985 |
and | +0.984 |
ud | +0.915 |
Pen | +0.905 |
Neg logit contributions | |
� | -0.830 |
ory | -0.704 |
surely | -0.673 |
sack | -0.660 |
idents | -0.654 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
rum | +0.084 |
Jo | +0.082 |
ud | +0.072 |
jo | +0.071 |
and | +0.071 |
Neg logit contributions | |
� | -0.061 |
surely | -0.051 |
cooler | -0.050 |
hotter | -0.050 |
prett | -0.048 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Jo | +0.270 |
rum | +0.266 |
jo | +0.238 |
ud | +0.235 |
Pen | +0.228 |
Neg logit contributions | |
� | -0.203 |
sack | -0.168 |
idents | -0.159 |
cooler | -0.158 |
surely | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
rum | +0.014 |
Jo | +0.013 |
ud | +0.013 |
jo | +0.012 |
and | +0.012 |
Neg logit contributions | |
� | -0.005 |
sack | -0.004 |
cooler | -0.004 |
golf | -0.004 |
surely | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
� | +0.066 |
sack | +0.053 |
idents | +0.053 |
ory | +0.052 |
surely | +0.051 |
Neg logit contributions | |
Jo | -0.106 |
rum | -0.105 |
ud | -0.094 |
and | -0.093 |
Pen | -0.092 |
Token | together |
Token ID | 1978 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
� | +0.037 |
surely | +0.030 |
idents | +0.028 |
sack | +0.028 |
hotter | +0.027 |
Neg logit contributions | |
Jo | -0.051 |
rum | -0.051 |
ud | -0.049 |
jo | -0.045 |
and | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
rum | +0.027 |
Jo | +0.026 |
ud | +0.024 |
Pen | +0.023 |
jo | +0.023 |
Neg logit contributions | |
� | -0.019 |
surely | -0.016 |
sack | -0.015 |
idents | -0.015 |
cooler | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
rum | +0.037 |
Jo | +0.033 |
ud | +0.032 |
and | +0.030 |
rd | +0.030 |
Neg logit contributions | |
� | -0.031 |
surely | -0.022 |
idents | -0.022 |
Dino | -0.021 |
ols | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
rum | +0.008 |
ud | +0.007 |
clim | +0.007 |
Jo | +0.007 |
Pen | +0.007 |
Neg logit contributions | |
� | -0.005 |
surely | -0.003 |
Sorry | -0.003 |
Dino | -0.003 |
Ros | -0.003 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
rum | +0.006 |
ud | +0.005 |
Pen | +0.005 |
jo | +0.005 |
eer | +0.005 |
Neg logit contributions | |
� | -0.005 |
Sorry | -0.004 |
surely | -0.004 |
Ros | -0.004 |
Dino | -0.004 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
rum | +1.074 |
Jo | +0.985 |
and | +0.948 |
ud | +0.934 |
Pen | +0.930 |
Neg logit contributions | |
� | -0.825 |
ory | -0.696 |
surely | -0.693 |
idents | -0.678 |
ized | -0.647 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
Jo | +0.014 |
rum | +0.013 |
Pen | +0.012 |
Ali | +0.011 |
Jacob | +0.011 |
Neg logit contributions | |
� | -0.016 |
idents | -0.014 |
hotter | -0.013 |
sack | -0.013 |
surely | -0.013 |
Token | took |
Token ID | 1718 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
� | +0.002 |
idents | +0.002 |
surely | +0.002 |
sack | +0.002 |
ory | +0.002 |
Neg logit contributions | |
rum | -0.003 |
Jo | -0.003 |
ud | -0.003 |
and | -0.003 |
Pen | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
rum | +0.044 |
Jo | +0.042 |
ud | +0.038 |
and | +0.037 |
Pen | +0.036 |
Neg logit contributions | |
� | -0.031 |
surely | -0.026 |
sack | -0.026 |
Dino | -0.025 |
ory | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
� | +0.037 |
idents | +0.030 |
sack | +0.029 |
surely | +0.028 |
ory | +0.028 |
Neg logit contributions | |
Jo | -0.057 |
rum | -0.056 |
ud | -0.050 |
Pen | -0.049 |
Ali | -0.048 |
Token | her |
Token ID | 607 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
� | +0.039 |
idents | +0.034 |
sack | +0.032 |
surely | +0.031 |
ory | +0.031 |
Neg logit contributions | |
rum | -0.055 |
Jo | -0.055 |
ud | -0.049 |
Pen | -0.047 |
and | -0.047 |
Token | teacher |
Token ID | 4701 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Jo | +0.045 |
rum | +0.039 |
Ali | +0.039 |
Pen | +0.038 |
Jacob | +0.038 |
Neg logit contributions | |
� | -0.046 |
hotter | -0.042 |
idents | -0.039 |
surely | -0.039 |
ory | -0.038 |
Token | gave |
Token ID | 2921 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
� | +0.104 |
sack | +0.087 |
ory | +0.087 |
idents | +0.080 |
cooler | +0.077 |
Neg logit contributions | |
rum | -0.190 |
Jo | -0.169 |
ud | -0.161 |
and | -0.151 |
Pen | -0.151 |
Token | her |
Token ID | 607 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
� | +0.213 |
idents | +0.184 |
sack | +0.177 |
hotter | +0.175 |
ory | +0.175 |
Neg logit contributions | |
Jo | -0.198 |
rum | -0.192 |
ud | -0.165 |
Pen | -0.164 |
Ali | -0.162 |
Token | a |
Token ID | 257 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Jo | +0.042 |
rum | +0.040 |
Pen | +0.035 |
and | +0.035 |
Ali | +0.035 |
Neg logit contributions | |
� | -0.051 |
idents | -0.043 |
hotter | -0.042 |
surely | -0.041 |
ory | -0.041 |
Token | folder |
Token ID | 9483 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
Jo | +0.012 |
rum | +0.012 |
Pen | +0.011 |
and | +0.010 |
Jacob | +0.010 |
Neg logit contributions | |
� | -0.011 |
idents | -0.009 |
hotter | -0.009 |
surely | -0.008 |
ory | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
� | +0.555 |
idents | +0.478 |
hotter | +0.459 |
sack | +0.454 |
surely | +0.452 |
Neg logit contributions | |
Jo | -0.473 |
rum | -0.455 |
Pen | -0.394 |
ud | -0.392 |
and | -0.391 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Jo | +0.051 |
rum | +0.047 |
Ann | +0.044 |
Pen | +0.044 |
Ali | +0.043 |
Neg logit contributions | |
� | -0.058 |
hotter | -0.052 |
idents | -0.051 |
oming | -0.046 |
ory | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
� | +0.024 |
idents | +0.020 |
hotter | +0.019 |
ory | +0.019 |
surely | +0.019 |
Neg logit contributions | |
Jo | -0.020 |
rum | -0.019 |
Pen | -0.017 |
and | -0.016 |
Ali | -0.016 |
Token | papers |
Token ID | 9473 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Jo | +0.044 |
rum | +0.043 |
and | +0.040 |
Pen | +0.040 |
Ali | +0.038 |
Neg logit contributions | |
� | -0.044 |
hotter | -0.036 |
Dino | -0.035 |
Sorry | -0.035 |
idents | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
� | +0.370 |
idents | +0.323 |
hotter | +0.314 |
Sorry | +0.309 |
Dino | +0.308 |
Neg logit contributions | |
Jo | -0.216 |
rum | -0.213 |
and | -0.203 |
Pen | -0.173 |
jo | -0.169 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Jo | +0.266 |
rum | +0.254 |
Pen | +0.221 |
ud | +0.220 |
and | +0.218 |
Neg logit contributions | |
� | -0.265 |
idents | -0.223 |
sack | -0.216 |
hotter | -0.215 |
ory | -0.214 |
Token | and |
Token ID | 290 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
� | +0.125 |
sack | +0.115 |
idents | +0.114 |
cooler | +0.110 |
ory | +0.106 |
Neg logit contributions | |
Jo | -0.122 |
rum | -0.109 |
ud | -0.099 |
Jamie | -0.098 |
Pen | -0.097 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
� | +0.054 |
idents | +0.047 |
hotter | +0.045 |
surely | +0.045 |
ory | +0.045 |
Neg logit contributions | |
Jo | -0.042 |
rum | -0.040 |
Pen | -0.036 |
Ali | -0.035 |
Jacob | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Jo | +0.132 |
rum | +0.118 |
ud | +0.110 |
Jamie | +0.108 |
jo | +0.108 |
Neg logit contributions | |
� | -0.108 |
sack | -0.096 |
idents | -0.096 |
cooler | -0.094 |
hotter | -0.091 |
Token | w |
Token ID | 266 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
� | +0.052 |
idents | +0.045 |
hotter | +0.043 |
sack | +0.043 |
ory | +0.042 |
Neg logit contributions | |
Jo | -0.046 |
rum | -0.045 |
Pen | -0.039 |
ud | -0.038 |
Ali | -0.038 |
Token | ags |
Token ID | 3775 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
� | +0.091 |
idents | +0.068 |
sack | +0.062 |
ory | +0.061 |
hotter | +0.060 |
Neg logit contributions | |
Jo | -0.213 |
rum | -0.204 |
Pen | -0.189 |
Ali | -0.187 |
ud | -0.185 |
Token | his |
Token ID | 465 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
� | +0.319 |
Dino | +0.274 |
idents | +0.271 |
cooler | +0.263 |
sack | +0.260 |
Neg logit contributions | |
Jo | -0.454 |
rum | -0.423 |
ud | -0.408 |
Pen | -0.391 |
and | -0.386 |
Token | tail |
Token ID | 7894 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Jo | +0.070 |
rum | +0.068 |
Pen | +0.056 |
Ali | +0.054 |
ud | +0.054 |
Neg logit contributions | |
� | -0.135 |
idents | -0.119 |
hotter | -0.115 |
surely | -0.115 |
ory | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Jo | +0.340 |
rum | +0.311 |
Jamie | +0.286 |
Ali | +0.285 |
Jamie | +0.284 |
Neg logit contributions | |
� | -0.215 |
cooler | -0.177 |
sack | -0.174 |
idents | -0.164 |
surely | -0.163 |
Token | He |
Token ID | 679 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
� | +0.023 |
idents | +0.019 |
hotter | +0.018 |
sack | +0.018 |
surely | +0.018 |
Neg logit contributions | |
Jo | -0.030 |
rum | -0.029 |
Pen | -0.026 |
ud | -0.026 |
and | -0.026 |
Token | forg |
Token ID | 5784 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
� | +0.052 |
idents | +0.046 |
sack | +0.044 |
hotter | +0.044 |
ory | +0.043 |
Neg logit contributions | |
Jo | -0.039 |
rum | -0.037 |
ud | -0.032 |
and | -0.032 |
Pen | -0.032 |
Token | help |
Token ID | 1037 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
� | +0.054 |
idents | +0.042 |
sack | +0.042 |
hotter | +0.041 |
surely | +0.041 |
Neg logit contributions | |
Jo | -0.096 |
rum | -0.091 |
ud | -0.085 |
jo | -0.085 |
Pen | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
� | +0.077 |
sack | +0.068 |
Dino | +0.065 |
hotter | +0.064 |
idents | +0.063 |
Neg logit contributions | |
Jo | -0.133 |
rum | -0.123 |
ud | -0.114 |
jo | -0.113 |
Pen | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
� | +0.008 |
idents | +0.006 |
hotter | +0.006 |
sack | +0.006 |
surely | +0.006 |
Neg logit contributions | |
Jo | -0.008 |
rum | -0.007 |
Pen | -0.006 |
and | -0.006 |
Ali | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
� | +0.037 |
idents | +0.030 |
sack | +0.029 |
hotter | +0.029 |
Dino | +0.029 |
Neg logit contributions | |
Jo | -0.043 |
rum | -0.042 |
Pen | -0.037 |
ud | -0.037 |
Ali | -0.036 |
Token | The |
Token ID | 464 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
� | +0.039 |
idents | +0.035 |
ory | +0.033 |
hotter | +0.032 |
sack | +0.032 |
Neg logit contributions | |
Jo | -0.038 |
rum | -0.036 |
and | -0.032 |
ud | -0.031 |
Ali | -0.030 |
Token | moral |
Token ID | 6573 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
� | +0.031 |
idents | +0.028 |
ory | +0.028 |
hotter | +0.026 |
ized | +0.026 |
Neg logit contributions | |
Jo | -0.036 |
rum | -0.034 |
living | -0.033 |
Pen | -0.033 |
Jacob | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
� | +0.537 |
sack | +0.481 |
surely | +0.473 |
cooler | +0.466 |
Dino | +0.464 |
Neg logit contributions | |
Jo | -0.372 |
rum | -0.369 |
Pen | -0.314 |
Jacob | -0.307 |
Ali | -0.303 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Jo | +0.315 |
rum | +0.304 |
ud | +0.275 |
jo | +0.267 |
Pen | +0.267 |
Neg logit contributions | |
� | -0.222 |
idents | -0.179 |
sack | -0.176 |
surely | -0.176 |
Dino | -0.174 |
Token | story |
Token ID | 1621 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
� | +0.057 |
idents | +0.050 |
hotter | +0.049 |
ory | +0.049 |
surely | +0.048 |
Neg logit contributions | |
Jo | -0.033 |
rum | -0.030 |
Pen | -0.026 |
and | -0.025 |
ud | -0.025 |
Token | is |
Token ID | 318 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
� | +0.068 |
idents | +0.062 |
surely | +0.058 |
sack | +0.057 |
hotter | +0.055 |
Neg logit contributions | |
Jo | -0.057 |
rum | -0.051 |
Pen | -0.046 |
Ali | -0.044 |
ud | -0.044 |
Token | always |
Token ID | 1464 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Jo | +0.094 |
rum | +0.092 |
ud | +0.078 |
Pen | +0.078 |
Ali | +0.078 |
Neg logit contributions | |
� | -0.124 |
idents | -0.106 |
hotter | -0.104 |
sack | -0.102 |
ory | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
� | +0.047 |
idents | +0.039 |
sack | +0.038 |
hotter | +0.038 |
cooler | +0.037 |
Neg logit contributions | |
Jo | -0.058 |
rum | -0.056 |
ud | -0.050 |
jo | -0.049 |
Pen | -0.049 |
Token | drink |
Token ID | 4144 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
� | +0.036 |
sack | +0.030 |
idents | +0.029 |
cooler | +0.029 |
surely | +0.028 |
Neg logit contributions | |
Jo | -0.060 |
rum | -0.060 |
ud | -0.057 |
and | -0.053 |
jo | -0.053 |
Token | something |
Token ID | 1223 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
� | +0.135 |
idents | +0.112 |
surely | +0.106 |
ory | +0.104 |
sack | +0.103 |
Neg logit contributions | |
Jo | -0.151 |
rum | -0.147 |
Pen | -0.134 |
and | -0.131 |
Jacob | -0.130 |
Token | good |
Token ID | 922 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
� | +0.139 |
idents | +0.116 |
hotter | +0.111 |
sack | +0.111 |
cooler | +0.109 |
Neg logit contributions | |
Jo | -0.190 |
rum | -0.184 |
ud | -0.165 |
jo | -0.162 |
Ali | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
Jo | +0.055 |
rum | +0.053 |
ud | +0.046 |
Pen | +0.046 |
Ali | +0.045 |
Neg logit contributions | |
� | -0.055 |
idents | -0.047 |
sack | -0.045 |
hotter | -0.045 |
ory | -0.044 |
Token | A |
Token ID | 317 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
� | +0.013 |
idents | +0.009 |
cooler | +0.009 |
ory | +0.008 |
Dino | +0.008 |
Neg logit contributions | |
rum | -0.020 |
Jo | -0.018 |
ud | -0.016 |
jo | -0.016 |
and | -0.016 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
� | +0.353 |
sack | +0.308 |
cooler | +0.298 |
hotter | +0.279 |
ory | +0.278 |
Neg logit contributions | |
rum | -0.505 |
Jo | -0.470 |
ud | -0.426 |
and | -0.416 |
jo | -0.407 |
Token | lady |
Token ID | 10846 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rum | +0.124 |
Jo | +0.117 |
ud | +0.107 |
and | +0.107 |
jo | +0.102 |
Neg logit contributions | |
� | -0.069 |
sack | -0.064 |
cooler | -0.059 |
ory | -0.055 |
idents | -0.053 |
Token | came |
Token ID | 1625 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
� | +0.096 |
sack | +0.080 |
ory | +0.079 |
cooler | +0.077 |
surely | +0.076 |
Neg logit contributions | |
rum | -0.145 |
Jo | -0.136 |
ud | -0.126 |
and | -0.122 |
Jamie | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
� | +0.077 |
hotter | +0.067 |
sack | +0.066 |
ory | +0.066 |
idents | +0.065 |
Neg logit contributions | |
rum | -0.117 |
Jo | -0.115 |
ud | -0.100 |
Jacob | -0.099 |
rd | -0.097 |
Token | gave |
Token ID | 2921 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
� | +0.036 |
idents | +0.029 |
hotter | +0.028 |
sack | +0.028 |
surely | +0.027 |
Neg logit contributions | |
rum | -0.057 |
Jo | -0.056 |
ud | -0.050 |
and | -0.050 |
jo | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
rum | +0.151 |
Jo | +0.148 |
and | +0.135 |
ud | +0.133 |
jo | +0.133 |
Neg logit contributions | |
� | -0.119 |
sack | -0.094 |
Dino | -0.093 |
ory | -0.092 |
cooler | -0.092 |
Token | she |
Token ID | 673 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Jo | +0.022 |
rum | +0.022 |
ud | +0.019 |
and | +0.019 |
jo | +0.018 |
Neg logit contributions | |
� | -0.021 |
idents | -0.018 |
sack | -0.017 |
hotter | -0.017 |
ory | -0.017 |
Token | joined |
Token ID | 5399 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
� | +0.012 |
sack | +0.010 |
ory | +0.010 |
cooler | +0.009 |
idents | +0.009 |
Neg logit contributions | |
rum | -0.020 |
Jo | -0.019 |
and | -0.017 |
Pen | -0.017 |
ud | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
� | +0.039 |
sack | +0.034 |
ory | +0.033 |
cooler | +0.031 |
Dino | +0.031 |
Neg logit contributions | |
Jo | -0.062 |
rum | -0.062 |
jo | -0.054 |
ud | -0.054 |
and | -0.052 |
Token | special |
Token ID | 2041 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
rum | +0.030 |
Jo | +0.030 |
ud | +0.027 |
Pen | +0.026 |
and | +0.025 |
Neg logit contributions | |
� | -0.025 |
idents | -0.021 |
sack | -0.021 |
ory | -0.020 |
surely | -0.020 |
Token | club |
Token ID | 3430 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
� | +0.085 |
sack | +0.074 |
cooler | +0.069 |
idents | +0.067 |
ory | +0.067 |
Neg logit contributions | |
rum | -0.108 |
Jo | -0.104 |
ud | -0.098 |
and | -0.093 |
Jamie | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
� | +0.399 |
sack | +0.350 |
cooler | +0.323 |
surely | +0.311 |
golf | +0.308 |
Neg logit contributions | |
rum | -0.547 |
Jo | -0.537 |
ud | -0.474 |
Pen | -0.463 |
Jamie | -0.461 |
Token | They |
Token ID | 1119 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
rum | +0.018 |
Jo | +0.017 |
ud | +0.015 |
jo | +0.015 |
rd | +0.014 |
Neg logit contributions | |
� | -0.013 |
sack | -0.009 |
idents | -0.009 |
surely | -0.009 |
Dino | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Jo | +0.011 |
rum | +0.011 |
ud | +0.009 |
and | +0.009 |
Pen | +0.009 |
Neg logit contributions | |
� | -0.008 |
idents | -0.007 |
sack | -0.007 |
surely | -0.007 |
ory | -0.007 |
Token | celebrating |
Token ID | 17499 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
rum | +0.034 |
Jo | +0.031 |
ud | +0.029 |
jo | +0.029 |
and | +0.028 |
Neg logit contributions | |
� | -0.019 |
cooler | -0.017 |
surely | -0.017 |
prett | -0.017 |
sack | -0.016 |
Token | by |
Token ID | 416 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rum | +0.125 |
Jo | +0.121 |
ud | +0.113 |
jo | +0.105 |
Pen | +0.103 |
Neg logit contributions | |
� | -0.082 |
idents | -0.073 |
sack | -0.071 |
cooler | -0.068 |
surely | -0.067 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
� | +0.064 |
sack | +0.054 |
idents | +0.053 |
surely | +0.053 |
Dino | +0.053 |
Neg logit contributions | |
rum | -0.082 |
Jo | -0.078 |
ud | -0.072 |
jo | -0.070 |
Pen | -0.069 |
Token | good |
Token ID | 922 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Jo | +0.014 |
rum | +0.013 |
Pen | +0.012 |
Ali | +0.012 |
ud | +0.011 |
Neg logit contributions | |
� | -0.013 |
idents | -0.011 |
hotter | -0.010 |
ory | -0.010 |
surely | -0.010 |
Token | dream |
Token ID | 4320 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
rum | +0.067 |
Jo | +0.065 |
Pen | +0.058 |
Jacob | +0.057 |
Ali | +0.056 |
Neg logit contributions | |
� | -0.035 |
sack | -0.032 |
ory | -0.032 |
cooler | -0.031 |
idents | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
rum | +0.092 |
Jo | +0.092 |
ud | +0.080 |
Pen | +0.080 |
Ali | +0.077 |
Neg logit contributions | |
� | -0.093 |
idents | -0.078 |
surely | -0.078 |
sack | -0.077 |
cooler | -0.074 |
Token | reminded |
Token ID | 14516 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
� | +0.037 |
idents | +0.032 |
sack | +0.031 |
surely | +0.031 |
hotter | +0.030 |
Neg logit contributions | |
rum | -0.044 |
Jo | -0.044 |
ud | -0.040 |
Pen | -0.038 |
and | -0.038 |
Token | her |
Token ID | 607 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
� | +0.137 |
idents | +0.116 |
hotter | +0.113 |
sack | +0.113 |
clips | +0.112 |
Neg logit contributions | |
Jo | -0.061 |
rum | -0.054 |
and | -0.052 |
Pen | -0.048 |
old | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Jo | +0.049 |
rum | +0.048 |
ud | +0.044 |
Pen | +0.041 |
jo | +0.041 |
Neg logit contributions | |
� | -0.041 |
idents | -0.037 |
sack | -0.036 |
surely | -0.036 |
cooler | -0.035 |
Token | always |
Token ID | 1464 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Jo | +0.056 |
rum | +0.055 |
ud | +0.050 |
and | +0.049 |
Pen | +0.048 |
Neg logit contributions | |
� | -0.049 |
surely | -0.042 |
sack | -0.041 |
idents | -0.040 |
cooler | -0.039 |
Token | be |
Token ID | 307 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Jo | +0.325 |
rum | +0.314 |
ud | +0.293 |
and | +0.281 |
Pen | +0.281 |
Neg logit contributions | |
� | -0.244 |
surely | -0.206 |
sack | -0.203 |
idents | -0.201 |
cooler | -0.193 |
Token | careful |
Token ID | 8161 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
Jo | +0.018 |
rum | +0.017 |
ud | +0.015 |
Pen | +0.015 |
Ali | +0.014 |
Neg logit contributions | |
� | -0.020 |
idents | -0.018 |
hotter | -0.017 |
sack | -0.017 |
surely | -0.017 |
Token | about |
Token ID | 546 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
Jo | +0.594 |
rum | +0.560 |
ud | +0.549 |
Pen | +0.535 |
Ali | +0.521 |
Neg logit contributions | |
surely | -0.238 |
� | -0.234 |
still | -0.230 |
idents | -0.225 |
hotter | -0.218 |
Token | thank |
Token ID | 40716 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
Jo | +0.092 |
rum | +0.088 |
Pen | +0.079 |
ud | +0.079 |
and | +0.079 |
Neg logit contributions | |
� | -0.068 |
idents | -0.057 |
sack | -0.054 |
hotter | -0.053 |
ory | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
� | +0.265 |
Dino | +0.202 |
idents | +0.200 |
sack | +0.199 |
surely | +0.198 |
Neg logit contributions | |
rum | -0.439 |
Jo | -0.432 |
ud | -0.410 |
jo | -0.396 |
and | -0.370 |
Token | " |
Token ID | 1 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
� | +0.026 |
sack | +0.022 |
idents | +0.022 |
surely | +0.022 |
ory | +0.021 |
Neg logit contributions | |
Jo | -0.026 |
rum | -0.024 |
ud | -0.022 |
and | -0.021 |
jo | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
� | +0.001 |
idents | +0.001 |
hotter | +0.001 |
sack | +0.001 |
surely | +0.001 |
Neg logit contributions | |
Jo | -0.001 |
rum | -0.001 |
ud | -0.001 |
Pen | -0.001 |
Ali | -0.001 |
Token | smiled |
Token ID | 13541 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
� | +0.017 |
idents | +0.014 |
sack | +0.014 |
surely | +0.013 |
cooler | +0.013 |
Neg logit contributions | |
rum | -0.026 |
Jo | -0.025 |
ud | -0.024 |
and | -0.024 |
jo | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
� | +0.008 |
idents | +0.007 |
sack | +0.007 |
hotter | +0.007 |
surely | +0.007 |
Neg logit contributions | |
Jo | -0.007 |
rum | -0.007 |
Pen | -0.006 |
and | -0.006 |
Ali | -0.006 |
Token | Mama |
Token ID | 40084 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
rum | +0.009 |
Jo | +0.009 |
ud | +0.008 |
jo | +0.008 |
and | +0.008 |
Neg logit contributions | |
� | -0.006 |
idents | -0.004 |
Dino | -0.004 |
surely | -0.004 |
Ros | -0.004 |
Token | p |
Token ID | 279 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
rum | +0.100 |
Jo | +0.097 |
and | +0.090 |
ud | +0.088 |
jo | +0.084 |
Neg logit contributions | |
� | -0.068 |
idents | -0.055 |
ory | -0.054 |
sack | -0.054 |
cooler | -0.053 |
Token | atted |
Token ID | 16898 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Jo | +0.136 |
rum | +0.130 |
ud | +0.116 |
Pen | +0.113 |
Ali | +0.113 |
Neg logit contributions | |
� | -0.135 |
idents | -0.114 |
hotter | -0.113 |
sack | -0.112 |
surely | -0.111 |
Token | her |
Token ID | 607 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
Jo | +0.048 |
rum | +0.047 |
ud | +0.042 |
and | +0.041 |
jo | +0.039 |
Neg logit contributions | |
� | -0.040 |
idents | -0.036 |
hotter | -0.035 |
surely | -0.034 |
sack | -0.034 |
Token | head |
Token ID | 1182 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Jo | +0.072 |
rum | +0.069 |
ud | +0.064 |
and | +0.062 |
jo | +0.061 |
Neg logit contributions | |
� | -0.052 |
sack | -0.043 |
idents | -0.043 |
hotter | -0.042 |
surely | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
� | +0.082 |
idents | +0.076 |
sack | +0.074 |
cooler | +0.071 |
surely | +0.071 |
Neg logit contributions | |
rum | -0.109 |
Jo | -0.107 |
ud | -0.103 |
Pen | -0.093 |
jo | -0.092 |
Token | go |
Token ID | 467 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
rum | +0.096 |
Jo | +0.094 |
ud | +0.090 |
and | +0.089 |
jo | +0.086 |
Neg logit contributions | |
� | -0.049 |
sack | -0.045 |
surely | -0.039 |
cooler | -0.037 |
idents | -0.035 |
Token | for |
Token ID | 329 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
� | +0.078 |
idents | +0.067 |
hotter | +0.063 |
surely | +0.063 |
ory | +0.062 |
Neg logit contributions | |
Jo | -0.075 |
rum | -0.072 |
Pen | -0.063 |
and | -0.063 |
Ali | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
� | +0.061 |
cooler | +0.049 |
Dino | +0.049 |
sack | +0.049 |
idents | +0.047 |
Neg logit contributions | |
rum | -0.077 |
Jo | -0.075 |
ud | -0.069 |
and | -0.067 |
jo | -0.066 |
Token | walk |
Token ID | 2513 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
rum | +0.042 |
Jo | +0.041 |
ud | +0.037 |
Pen | +0.036 |
Ali | +0.036 |
Neg logit contributions | |
� | -0.023 |
idents | -0.018 |
sack | -0.017 |
surely | -0.017 |
ory | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
� | +0.052 |
sack | +0.043 |
cooler | +0.042 |
surely | +0.042 |
ory | +0.041 |
Neg logit contributions | |
rum | -0.076 |
Jo | -0.074 |
ud | -0.067 |
Pen | -0.065 |
Ali | -0.064 |
Token | He |
Token ID | 679 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
rum | +0.028 |
Jo | +0.027 |
ud | +0.025 |
Pen | +0.025 |
rd | +0.023 |
Neg logit contributions | |
� | -0.017 |
idents | -0.014 |
Dino | -0.013 |
sack | -0.013 |
surely | -0.013 |
Token | looked |
Token ID | 3114 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
� | +0.010 |
sack | +0.009 |
cooler | +0.009 |
ory | +0.009 |
surely | +0.009 |
Neg logit contributions | |
rum | -0.020 |
Jo | -0.017 |
and | -0.016 |
ud | -0.016 |
Pen | -0.015 |
Token | around |
Token ID | 1088 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
� | +0.064 |
idents | +0.053 |
hotter | +0.050 |
sack | +0.050 |
surely | +0.049 |
Neg logit contributions | |
Jo | -0.079 |
rum | -0.076 |
Pen | -0.068 |
ud | -0.068 |
and | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
rum | +0.127 |
Jo | +0.125 |
ud | +0.112 |
jo | +0.106 |
and | +0.106 |
Neg logit contributions | |
� | -0.094 |
surely | -0.078 |
idents | -0.077 |
sack | -0.077 |
hotter | -0.076 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
� | +0.006 |
idents | +0.005 |
hotter | +0.005 |
sack | +0.005 |
surely | +0.005 |
Neg logit contributions | |
rum | -0.009 |
Jo | -0.009 |
ud | -0.008 |
Pen | -0.007 |
and | -0.007 |
Token | anytime |
Token ID | 17949 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
� | +0.244 |
idents | +0.205 |
surely | +0.200 |
ory | +0.200 |
sack | +0.199 |
Neg logit contributions | |
Jo | -0.308 |
rum | -0.303 |
ud | -0.267 |
jo | -0.253 |
Pen | -0.252 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
� | +0.137 |
ory | +0.116 |
cooler | +0.114 |
idents | +0.114 |
sack | +0.114 |
Neg logit contributions | |
rum | -0.160 |
Jo | -0.158 |
ud | -0.136 |
jo | -0.130 |
and | -0.129 |
Token | And |
Token ID | 843 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
� | +0.005 |
idents | +0.004 |
Dino | +0.004 |
surely | +0.004 |
sack | +0.004 |
Neg logit contributions | |
Jo | -0.005 |
rum | -0.005 |
ud | -0.005 |
jo | -0.004 |
and | -0.004 |
Token | don |
Token ID | 836 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Jo | +0.098 |
rum | +0.095 |
Pen | +0.084 |
ud | +0.083 |
and | +0.083 |
Neg logit contributions | |
� | -0.089 |
idents | -0.074 |
hotter | -0.071 |
sack | -0.071 |
ory | -0.070 |
Token | 't |
Token ID | 470 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
� | +0.131 |
ory | +0.124 |
idents | +0.117 |
hotter | +0.116 |
sack | +0.112 |
Neg logit contributions | |
Jo | -0.125 |
rum | -0.117 |
Pen | -0.107 |
Jacob | -0.103 |
Ali | -0.103 |
Token | forget |
Token ID | 6044 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
� | +0.155 |
idents | +0.128 |
sack | +0.121 |
hotter | +0.121 |
surely | +0.119 |
Neg logit contributions | |
Jo | -0.197 |
rum | -0.191 |
Pen | -0.169 |
ud | -0.169 |
and | -0.168 |
Token | to |
Token ID | 284 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
idents | +0.189 |
� | +0.183 |
cooler | +0.176 |
sack | +0.174 |
Dino | +0.165 |
Neg logit contributions | |
Jo | -0.329 |
rum | -0.325 |
ud | -0.301 |
and | -0.276 |
jo | -0.275 |
Token | share |
Token ID | 2648 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Jo | +0.067 |
rum | +0.064 |
ud | +0.058 |
Pen | +0.057 |
and | +0.057 |
Neg logit contributions | |
� | -0.048 |
idents | -0.039 |
sack | -0.038 |
hotter | -0.037 |
surely | -0.037 |
Token | your |
Token ID | 534 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
� | +0.260 |
idents | +0.223 |
sack | +0.215 |
hotter | +0.214 |
ory | +0.212 |
Neg logit contributions | |
Jo | -0.252 |
rum | -0.240 |
ud | -0.210 |
Pen | -0.209 |
Ali | -0.208 |
Token | blue |
Token ID | 4171 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
rum | +0.249 |
Jo | +0.244 |
Pen | +0.219 |
and | +0.217 |
rd | +0.210 |
Neg logit contributions | |
� | -0.255 |
idents | -0.222 |
surely | -0.218 |
hotter | -0.216 |
Sorry | -0.206 |
Token | berries |
Token ID | 20853 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
� | +0.002 |
surely | +0.002 |
hotter | +0.002 |
idents | +0.002 |
Sorry | +0.001 |
Neg logit contributions | |
Jo | -0.003 |
rum | -0.003 |
ud | -0.002 |
Pen | -0.002 |
and | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Jo | +0.034 |
rum | +0.032 |
Pen | +0.028 |
ud | +0.028 |
Ali | +0.028 |
Neg logit contributions | |
� | -0.042 |
idents | -0.036 |
hotter | -0.035 |
surely | -0.034 |
sack | -0.034 |
Token | lion |
Token ID | 18744 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
� | +0.029 |
idents | +0.025 |
hotter | +0.024 |
sack | +0.024 |
surely | +0.023 |
Neg logit contributions | |
Jo | -0.030 |
rum | -0.029 |
Pen | -0.026 |
ud | -0.026 |
Ali | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
rum | +0.008 |
Jo | +0.008 |
Jamie | +0.007 |
and | +0.007 |
Jamie | +0.007 |
Neg logit contributions | |
� | -0.004 |
Dino | -0.004 |
sack | -0.003 |
still | -0.003 |
cooler | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
Jo | +0.033 |
rum | +0.032 |
ud | +0.030 |
and | +0.030 |
old | +0.028 |
Neg logit contributions | |
� | -0.018 |
Dino | -0.015 |
idents | -0.014 |
sack | -0.013 |
surely | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
� | +0.021 |
Dino | +0.019 |
sack | +0.018 |
idents | +0.018 |
cooler | +0.018 |
Neg logit contributions | |
rum | -0.020 |
Jo | -0.020 |
and | -0.018 |
ud | -0.017 |
Pen | -0.017 |
Token | huge |
Token ID | 3236 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Jo | +0.083 |
rum | +0.083 |
ud | +0.074 |
and | +0.074 |
jo | +0.070 |
Neg logit contributions | |
� | -0.048 |
Dino | -0.045 |
cooler | -0.042 |
sack | -0.041 |
hotter | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
� | +0.129 |
cooler | +0.119 |
Dino | +0.119 |
sack | +0.118 |
idents | +0.111 |
Neg logit contributions | |
Jo | -0.213 |
rum | -0.205 |
and | -0.184 |
Jamie | -0.181 |
Pen | -0.176 |
Token | very |
Token ID | 845 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
� | +0.013 |
Dino | +0.011 |
sack | +0.010 |
surely | +0.010 |
cooler | +0.010 |
Neg logit contributions | |
Jo | -0.022 |
rum | -0.022 |
ud | -0.021 |
and | -0.020 |
old | -0.019 |
Token | strong |
Token ID | 1913 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
� | +0.055 |
Dino | +0.045 |
ory | +0.045 |
cooler | +0.045 |
sack | +0.044 |
Neg logit contributions | |
Jo | -0.107 |
rum | -0.104 |
ud | -0.095 |
and | -0.095 |
Pen | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
� | +0.106 |
cooler | +0.100 |
Dino | +0.099 |
sack | +0.087 |
still | +0.080 |
Neg logit contributions | |
Jo | -0.310 |
rum | -0.289 |
Jamie | -0.286 |
and | -0.269 |
Mary | -0.268 |
Token | He |
Token ID | 679 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
Jo | +0.033 |
rum | +0.032 |
ud | +0.029 |
a | +0.029 |
and | +0.028 |
Neg logit contributions | |
� | -0.013 |
Dino | -0.010 |
cooler | -0.008 |
Cr | -0.008 |
sack | -0.008 |
Token | started |
Token ID | 2067 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Jo | +0.469 |
rum | +0.447 |
Pen | +0.400 |
ud | +0.396 |
Ali | +0.395 |
Neg logit contributions | |
� | -0.389 |
idents | -0.324 |
hotter | -0.305 |
sack | -0.302 |
ory | -0.301 |
Token | to |
Token ID | 284 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
� | +0.243 |
idents | +0.203 |
surely | +0.203 |
sack | +0.201 |
hotter | +0.200 |
Neg logit contributions | |
Jo | -0.266 |
rum | -0.265 |
ud | -0.238 |
Pen | -0.237 |
and | -0.234 |
Token | float |
Token ID | 12178 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
Jo | +0.092 |
rum | +0.090 |
ud | +0.082 |
and | +0.081 |
Pen | +0.080 |
Neg logit contributions | |
� | -0.057 |
idents | -0.046 |
sack | -0.045 |
surely | -0.044 |
hotter | -0.044 |
Token | away |
Token ID | 1497 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
� | +0.080 |
idents | +0.064 |
hotter | +0.059 |
sack | +0.058 |
surely | +0.058 |
Neg logit contributions | |
Jo | -0.104 |
rum | -0.101 |
Pen | -0.091 |
Ali | -0.090 |
and | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
� | +0.168 |
idents | +0.143 |
hotter | +0.136 |
sack | +0.136 |
surely | +0.135 |
Neg logit contributions | |
Jo | -0.168 |
rum | -0.162 |
Pen | -0.142 |
ud | -0.141 |
and | -0.140 |
Token | taking |
Token ID | 2263 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Jo | +0.006 |
rum | +0.006 |
ud | +0.005 |
and | +0.005 |
Pen | +0.005 |
Neg logit contributions | |
� | -0.005 |
idents | -0.005 |
surely | -0.005 |
hotter | -0.005 |
sack | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
rum | +0.190 |
Jo | +0.189 |
ud | +0.172 |
Pen | +0.167 |
and | +0.164 |
Neg logit contributions | |
� | -0.105 |
sack | -0.090 |
surely | -0.087 |
idents | -0.085 |
hotter | -0.083 |
Token | people |
Token ID | 661 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
� | +0.034 |
sack | +0.029 |
idents | +0.028 |
hotter | +0.028 |
surely | +0.027 |
Neg logit contributions | |
rum | -0.047 |
Jo | -0.047 |
ud | -0.043 |
and | -0.041 |
Pen | -0.040 |
Token | with |
Token ID | 351 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
� | +0.002 |
sack | +0.002 |
surely | +0.002 |
cooler | +0.002 |
hotter | +0.002 |
Neg logit contributions | |
Jo | -0.003 |
rum | -0.003 |
ud | -0.003 |
Pen | -0.002 |
Ali | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
� | +0.008 |
sack | +0.007 |
surely | +0.006 |
cooler | +0.006 |
idents | +0.006 |
Neg logit contributions | |
Jo | -0.013 |
rum | -0.013 |
ud | -0.012 |
and | -0.011 |
jo | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Jo | +0.121 |
rum | +0.116 |
ud | +0.102 |
Pen | +0.101 |
Ali | +0.100 |
Neg logit contributions | |
� | -0.117 |
idents | -0.098 |
sack | -0.097 |
surely | -0.095 |
hotter | -0.094 |
Token | iness |
Token ID | 1272 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Jo | +0.123 |
rum | +0.115 |
Pen | +0.107 |
Ali | +0.105 |
Jacob | +0.104 |
Neg logit contributions | |
� | -0.123 |
idents | -0.105 |
hotter | -0.105 |
surely | -0.104 |
ory | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Jo | +0.130 |
rum | +0.127 |
ud | +0.114 |
Pen | +0.111 |
Jacob | +0.109 |
Neg logit contributions | |
� | -0.110 |
idents | -0.096 |
surely | -0.094 |
sack | -0.093 |
hotter | -0.092 |
Token | the |
Token ID | 262 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
Jo | +0.322 |
rum | +0.312 |
jo | +0.291 |
ud | +0.281 |
and | +0.275 |
Neg logit contributions | |
� | -0.213 |
sack | -0.191 |
cooler | -0.185 |
hotter | -0.179 |
idents | -0.176 |
Token | toilet |
Token ID | 16146 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
� | +0.034 |
idents | +0.028 |
sack | +0.027 |
hotter | +0.027 |
surely | +0.026 |
Neg logit contributions | |
Jo | -0.039 |
rum | -0.038 |
Pen | -0.034 |
ud | -0.034 |
and | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
Jo | +0.164 |
rum | +0.161 |
ud | +0.143 |
Pen | +0.138 |
and | +0.138 |
Neg logit contributions | |
� | -0.146 |
idents | -0.124 |
sack | -0.121 |
cooler | -0.118 |
hotter | -0.117 |
Token | â |
Token ID | 22940 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
rum | +0.035 |
Jo | +0.034 |
ud | +0.030 |
jo | +0.029 |
Pen | +0.029 |
Neg logit contributions | |
� | -0.028 |
Dino | -0.020 |
idents | -0.020 |
ory | -0.020 |
surely | -0.020 |
Token | € |
Token ID | 26391 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Jo | +0.218 |
rum | +0.207 |
Pen | +0.181 |
jo | +0.178 |
ud | +0.178 |
Neg logit contributions | |
� | -0.201 |
idents | -0.170 |
sack | -0.167 |
hotter | -0.163 |
cooler | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
� | +0.144 |
idents | +0.111 |
Dino | +0.095 |
surely | +0.095 |
� | +0.095 |
Neg logit contributions | |
rum | -0.149 |
Jo | -0.138 |
and | -0.127 |
Pen | -0.125 |
ud | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
� | +0.005 |
Dino | +0.003 |
surely | +0.003 |
Sorry | +0.003 |
ory | +0.003 |
Neg logit contributions | |
rum | -0.007 |
Jo | -0.007 |
Pen | -0.006 |
Ali | -0.006 |
Jacob | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
� | +0.002 |
Sorry | +0.002 |
surely | +0.002 |
ory | +0.002 |
Dino | +0.002 |
Neg logit contributions | |
rum | -0.004 |
Jo | -0.003 |
Ali | -0.003 |
Pen | -0.003 |
Jacob | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
� | +0.011 |
idents | +0.009 |
sack | +0.009 |
hotter | +0.009 |
ory | +0.008 |
Neg logit contributions | |
Jo | -0.018 |
rum | -0.017 |
Pen | -0.015 |
ud | -0.015 |
and | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Jo | +0.026 |
rum | +0.024 |
Pen | +0.022 |
Jacob | +0.021 |
Ali | +0.021 |
Neg logit contributions | |
� | -0.023 |
idents | -0.020 |
sack | -0.019 |
hotter | -0.019 |
cooler | -0.018 |
Token | We |
Token ID | 775 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
� | +0.023 |
idents | +0.019 |
ory | +0.019 |
hotter | +0.019 |
sack | +0.019 |
Neg logit contributions | |
Jo | -0.018 |
rum | -0.018 |
Pen | -0.015 |
Ali | -0.015 |
Jacob | -0.015 |
Token | can |
Token ID | 460 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
� | +0.014 |
idents | +0.012 |
sack | +0.012 |
hotter | +0.012 |
surely | +0.011 |
Neg logit contributions | |
Jo | -0.015 |
rum | -0.014 |
Pen | -0.013 |
ud | -0.013 |
and | -0.013 |
Token | help |
Token ID | 1037 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
� | +0.174 |
hotter | +0.158 |
ory | +0.158 |
idents | +0.150 |
Dino | +0.148 |
Neg logit contributions | |
Jo | -0.173 |
rum | -0.164 |
Pen | -0.148 |
Jacob | -0.146 |
Ali | -0.145 |
Token | you |
Token ID | 345 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
� | +0.086 |
idents | +0.076 |
sack | +0.070 |
hotter | +0.069 |
ory | +0.068 |
Neg logit contributions | |
Jo | -0.121 |
rum | -0.118 |
ud | -0.105 |
jo | -0.104 |
Pen | -0.100 |
Token | ." |
Token ID | 526 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
� | +0.027 |
idents | +0.023 |
sack | +0.022 |
hotter | +0.022 |
surely | +0.022 |
Neg logit contributions | |
Jo | -0.030 |
rum | -0.029 |
ud | -0.026 |
Pen | -0.026 |
Ali | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
Jo | +0.152 |
rum | +0.140 |
Pen | +0.132 |
Ali | +0.131 |
and | +0.130 |
Neg logit contributions | |
� | -0.192 |
hotter | -0.168 |
idents | -0.167 |
surely | -0.167 |
sack | -0.167 |
Token |
|
Token ID | 198 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
� | +0.045 |
idents | +0.037 |
sack | +0.035 |
hotter | +0.035 |
Dino | +0.035 |
Neg logit contributions | |
Jo | -0.054 |
rum | -0.052 |
ud | -0.046 |
Pen | -0.046 |
Ali | -0.045 |
Token | L |
Token ID | 43 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
� | +0.042 |
idents | +0.034 |
hotter | +0.033 |
sack | +0.033 |
surely | +0.032 |
Neg logit contributions | |
Jo | -0.055 |
rum | -0.054 |
Pen | -0.048 |
ud | -0.048 |
and | -0.047 |
Token | ily |
Token ID | 813 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
� | +0.127 |
ory | +0.110 |
idents | +0.106 |
cooler | +0.104 |
hotter | +0.104 |
Neg logit contributions | |
Jo | -0.156 |
rum | -0.136 |
jo | -0.128 |
Pen | -0.127 |
Jacob | -0.120 |
Token | stops |
Token ID | 9911 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Jo | +0.082 |
rum | +0.078 |
Pen | +0.069 |
ud | +0.069 |
Ali | +0.068 |
Neg logit contributions | |
� | -0.110 |
idents | -0.094 |
surely | -0.092 |
hotter | -0.091 |
ory | -0.090 |
Token | make |
Token ID | 787 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
rum | +0.084 |
Jo | +0.082 |
ud | +0.080 |
and | +0.075 |
Pen | +0.072 |
Neg logit contributions | |
� | -0.056 |
idents | -0.049 |
surely | -0.046 |
sack | -0.045 |
ory | -0.043 |
Token | history |
Token ID | 2106 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
� | +0.019 |
idents | +0.018 |
sack | +0.017 |
hotter | +0.017 |
cooler | +0.016 |
Neg logit contributions | |
rum | -0.026 |
Jo | -0.025 |
ud | -0.024 |
jo | -0.022 |
Pen | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
� | +0.119 |
idents | +0.101 |
sack | +0.097 |
surely | +0.097 |
cooler | +0.097 |
Neg logit contributions | |
Jo | -0.143 |
rum | -0.142 |
ud | -0.129 |
Pen | -0.123 |
Ali | -0.120 |
Token | They |
Token ID | 1119 |
Feature activation | +9.43e-04 |
Pos logit contributions | |
Jo | +0.018 |
rum | +0.018 |
ud | +0.016 |
Pen | +0.016 |
and | +0.015 |
Neg logit contributions | |
� | -0.016 |
idents | -0.013 |
sack | -0.012 |
surely | -0.012 |
ory | -0.012 |
Token | both |
Token ID | 1111 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
� | +0.000 |
sack | +0.000 |
idents | +0.000 |
surely | +0.000 |
ory | +0.000 |
Neg logit contributions | |
rum | -0.000 |
Jo | -0.000 |
and | -0.000 |
ud | -0.000 |
Pen | -0.000 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
� | +0.051 |
continued | +0.050 |
surely | +0.049 |
ory | +0.047 |
sack | +0.045 |
Neg logit contributions | |
rum | -0.115 |
and | -0.106 |
Jo | -0.104 |
ud | -0.102 |
Pen | -0.095 |
Token | that |
Token ID | 326 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
rum | +0.202 |
Jo | +0.198 |
ud | +0.182 |
jo | +0.175 |
and | +0.174 |
Neg logit contributions | |
� | -0.129 |
surely | -0.109 |
idents | -0.108 |
sack | -0.107 |
Dino | -0.105 |
Token | their |
Token ID | 511 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
rum | +0.090 |
Jo | +0.088 |
ud | +0.083 |
jo | +0.079 |
and | +0.075 |
Neg logit contributions | |
� | -0.051 |
idents | -0.046 |
surely | -0.046 |
sack | -0.046 |
hotter | -0.044 |
Token | kiss |
Token ID | 9245 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
Jo | +0.092 |
rum | +0.090 |
ud | +0.078 |
and | +0.076 |
Pen | +0.076 |
Neg logit contributions | |
� | -0.089 |
idents | -0.078 |
sack | -0.075 |
surely | -0.073 |
ory | -0.071 |
Token | would |
Token ID | 561 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
� | +0.062 |
idents | +0.052 |
hotter | +0.050 |
ory | +0.050 |
sack | +0.050 |
Neg logit contributions | |
Jo | -0.061 |
rum | -0.059 |
Pen | -0.052 |
ud | -0.051 |
Ali | -0.051 |
Token | always |
Token ID | 1464 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
Jo | +0.019 |
rum | +0.018 |
Pen | +0.015 |
Ali | +0.015 |
and | +0.015 |
Neg logit contributions | |
� | -0.020 |
idents | -0.017 |
hotter | -0.017 |
ory | -0.017 |
sack | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Jo | +0.018 |
rum | +0.018 |
ud | +0.015 |
jo | +0.015 |
and | +0.015 |
Neg logit contributions | |
� | -0.015 |
Dino | -0.013 |
hotter | -0.013 |
idents | -0.012 |
sack | -0.012 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Jo | +0.024 |
rum | +0.022 |
Pen | +0.020 |
ud | +0.020 |
Ali | +0.020 |
Neg logit contributions | |
� | -0.023 |
idents | -0.019 |
surely | -0.018 |
ory | -0.018 |
hotter | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
� | +0.180 |
sack | +0.154 |
cooler | +0.147 |
idents | +0.144 |
hotter | +0.141 |
Neg logit contributions | |
Jo | -0.218 |
rum | -0.212 |
Jamie | -0.188 |
Jamie | -0.188 |
Jacob | -0.187 |
Token | chased |
Token ID | 26172 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
� | +0.020 |
sack | +0.018 |
Dino | +0.018 |
idents | +0.018 |
hotter | +0.017 |
Neg logit contributions | |
rum | -0.025 |
Jo | -0.024 |
ud | -0.023 |
and | -0.022 |
jo | -0.021 |
Token | after |
Token ID | 706 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Jo | +0.339 |
rum | +0.330 |
and | +0.301 |
Pen | +0.298 |
ud | +0.289 |
Neg logit contributions | |
� | -0.398 |
idents | -0.323 |
hotter | -0.322 |
surely | -0.315 |
cooler | -0.304 |
Token | it |
Token ID | 340 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
� | +0.199 |
idents | +0.171 |
hotter | +0.164 |
sack | +0.164 |
ory | +0.163 |
Neg logit contributions | |
Jo | -0.167 |
rum | -0.160 |
Pen | -0.138 |
ud | -0.138 |
and | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Jo | +0.139 |
rum | +0.129 |
Jamie | +0.121 |
ud | +0.120 |
jo | +0.119 |
Neg logit contributions | |
� | -0.094 |
sack | -0.078 |
idents | -0.077 |
cooler | -0.076 |
surely | -0.075 |
Token | The |
Token ID | 383 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Jo | +0.015 |
rum | +0.015 |
Pen | +0.014 |
Ali | +0.013 |
Jacob | +0.013 |
Neg logit contributions | |
� | -0.017 |
surely | -0.015 |
hotter | -0.014 |
ory | -0.014 |
idents | -0.014 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
� | +0.097 |
idents | +0.084 |
ory | +0.084 |
hotter | +0.081 |
surely | +0.078 |
Neg logit contributions | |
Jo | -0.096 |
rum | -0.088 |
Pen | -0.084 |
Ali | -0.080 |
ud | -0.080 |
Token | flew |
Token ID | 13112 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
� | +0.166 |
idents | +0.137 |
sack | +0.134 |
surely | +0.130 |
hotter | +0.129 |
Neg logit contributions | |
Jo | -0.224 |
rum | -0.222 |
ud | -0.197 |
and | -0.197 |
Pen | -0.194 |
Token | away |
Token ID | 1497 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
� | +0.003 |
idents | +0.002 |
ory | +0.002 |
hotter | +0.002 |
sack | +0.002 |
Neg logit contributions | |
Jo | -0.004 |
rum | -0.004 |
Pen | -0.003 |
and | -0.003 |
Ali | -0.003 |
Token | completely |
Token ID | 3190 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Jo | +0.073 |
rum | +0.072 |
Pen | +0.064 |
Jacob | +0.063 |
ud | +0.063 |
Neg logit contributions | |
� | -0.072 |
idents | -0.063 |
ory | -0.059 |
Dino | -0.057 |
Sorry | -0.054 |
Token | filled |
Token ID | 5901 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
� | +0.196 |
idents | +0.173 |
Dino | +0.159 |
ory | +0.154 |
trigger | +0.148 |
Neg logit contributions | |
rum | -0.214 |
Jo | -0.213 |
ud | -0.191 |
Pen | -0.183 |
and | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Jo | +0.045 |
rum | +0.044 |
ud | +0.039 |
Pen | +0.038 |
Ali | +0.038 |
Neg logit contributions | |
� | -0.038 |
idents | -0.032 |
surely | -0.031 |
hotter | -0.031 |
sack | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
rum | +0.045 |
Jo | +0.043 |
ud | +0.041 |
and | +0.038 |
clim | +0.038 |
Neg logit contributions | |
� | -0.031 |
idents | -0.024 |
surely | -0.022 |
hotter | -0.020 |
Dino | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
rum | +0.012 |
Jo | +0.011 |
ud | +0.011 |
Pen | +0.010 |
clim | +0.010 |
Neg logit contributions | |
� | -0.008 |
idents | -0.006 |
surely | -0.006 |
sack | -0.006 |
Dino | -0.006 |
Token | Anne |
Token ID | 43227 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
rum | +0.011 |
Jo | +0.010 |
ud | +0.010 |
Pen | +0.009 |
Jacob | +0.009 |
Neg logit contributions | |
� | -0.008 |
Sorry | -0.006 |
surely | -0.006 |
idents | -0.006 |
sack | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
rum | +0.699 |
Jo | +0.652 |
and | +0.627 |
ud | +0.601 |
Pen | +0.588 |
Neg logit contributions | |
� | -0.487 |
surely | -0.398 |
ory | -0.382 |
idents | -0.379 |
sack | -0.375 |
Token | Jack |
Token ID | 3619 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
� | +0.001 |
surely | +0.001 |
sack | +0.001 |
idents | +0.001 |
Ros | +0.001 |
Neg logit contributions | |
rum | -0.001 |
ud | -0.001 |
Jo | -0.001 |
and | -0.000 |
rd | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
� | +0.016 |
surely | +0.013 |
idents | +0.013 |
sack | +0.013 |
ory | +0.013 |
Neg logit contributions | |
rum | -0.022 |
Jo | -0.021 |
and | -0.020 |
Pen | -0.019 |
ud | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
rum | +0.055 |
Jo | +0.053 |
ud | +0.049 |
and | +0.048 |
jo | +0.048 |
Neg logit contributions | |
� | -0.035 |
surely | -0.031 |
cooler | -0.028 |
hotter | -0.028 |
sack | -0.027 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Jo | +0.052 |
rum | +0.050 |
ud | +0.045 |
Pen | +0.045 |
Ali | +0.044 |
Neg logit contributions | |
� | -0.044 |
idents | -0.036 |
hotter | -0.035 |
surely | -0.034 |
sack | -0.034 |
Token | special |
Token ID | 2041 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
� | +0.061 |
sack | +0.054 |
cooler | +0.053 |
idents | +0.049 |
surely | +0.047 |
Neg logit contributions | |
rum | -0.085 |
Jo | -0.084 |
ud | -0.077 |
Pen | -0.074 |
Jacob | -0.073 |
Token | game |
Token ID | 983 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
� | +0.092 |
sack | +0.086 |
cooler | +0.081 |
gem | +0.076 |
idents | +0.072 |
Neg logit contributions | |
rum | -0.129 |
Jo | -0.125 |
ud | -0.120 |
Jamie | -0.112 |
Pen | -0.110 |
Token | of |
Token ID | 286 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Jo | +0.086 |
rum | +0.086 |
ud | +0.078 |
Jamie | +0.076 |
Pen | +0.075 |
Neg logit contributions | |
� | -0.052 |
sack | -0.043 |
cooler | -0.040 |
idents | -0.039 |
Dino | -0.038 |
Token | hide |
Token ID | 7808 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
rum | +0.287 |
Jo | +0.284 |
ud | +0.264 |
jo | +0.261 |
and | +0.239 |
Neg logit contributions | |
� | -0.249 |
sack | -0.224 |
cooler | -0.214 |
golf | -0.212 |
idents | -0.206 |
Token | - |
Token ID | 12 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Jo | +0.368 |
rum | +0.349 |
ud | +0.312 |
Jacob | +0.309 |
jo | +0.308 |
Neg logit contributions | |
� | -0.270 |
sack | -0.244 |
idents | -0.236 |
ory | -0.233 |
cooler | -0.233 |
Token | and |
Token ID | 392 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
� | +0.028 |
ory | +0.027 |
peanuts | +0.027 |
Dino | +0.026 |
Sorry | +0.026 |
Neg logit contributions | |
rum | -0.015 |
Jo | -0.013 |
Pen | -0.012 |
Ali | -0.011 |
Jacob | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
rum | +0.600 |
ud | +0.576 |
Jo | +0.568 |
Pen | +0.531 |
Jacob | +0.521 |
Neg logit contributions | |
� | -0.446 |
idents | -0.417 |
ory | -0.415 |
sack | -0.409 |
Dino | -0.391 |
Token | seek |
Token ID | 36163 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
� | +0.020 |
Sorry | +0.017 |
idents | +0.017 |
Dino | +0.017 |
surely | +0.017 |
Neg logit contributions | |
rum | -0.026 |
Jo | -0.024 |
Pen | -0.023 |
Ali | -0.022 |
ud | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Jo | +0.207 |
rum | +0.202 |
ud | +0.187 |
jo | +0.186 |
Pen | +0.179 |
Neg logit contributions | |
� | -0.083 |
cooler | -0.073 |
sack | -0.067 |
idents | -0.062 |
ized | -0.062 |
Token | so |
Token ID | 523 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
� | +0.011 |
sack | +0.011 |
cooler | +0.011 |
idents | +0.010 |
surely | +0.010 |
Neg logit contributions | |
rum | -0.016 |
Jo | -0.016 |
ud | -0.015 |
jo | -0.014 |
Pen | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
rum | +0.051 |
Jo | +0.051 |
ud | +0.046 |
and | +0.045 |
Pen | +0.044 |
Neg logit contributions | |
� | -0.034 |
idents | -0.028 |
sack | -0.027 |
surely | -0.026 |
hotter | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Jo | +0.154 |
rum | +0.147 |
Pen | +0.131 |
ud | +0.129 |
Ali | +0.127 |
Neg logit contributions | |
� | -0.141 |
idents | -0.120 |
hotter | -0.118 |
sack | -0.115 |
surely | -0.113 |
Token | She |
Token ID | 1375 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
� | +0.026 |
idents | +0.021 |
sack | +0.020 |
hotter | +0.020 |
surely | +0.019 |
Neg logit contributions | |
Jo | -0.030 |
rum | -0.029 |
ud | -0.026 |
and | -0.025 |
jo | -0.025 |
Token | runs |
Token ID | 4539 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
Jo | +0.025 |
rum | +0.025 |
and | +0.022 |
ud | +0.021 |
Pen | +0.021 |
Neg logit contributions | |
� | -0.029 |
idents | -0.026 |
sack | -0.025 |
hotter | -0.025 |
cooler | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Jo | +0.266 |
rum | +0.256 |
and | +0.221 |
Pen | +0.220 |
ud | +0.219 |
Neg logit contributions | |
� | -0.388 |
idents | -0.332 |
hotter | -0.320 |
ory | -0.320 |
sack | -0.318 |
Token | the |
Token ID | 262 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Jo | +0.052 |
rum | +0.050 |
ud | +0.045 |
and | +0.044 |
jo | +0.044 |
Neg logit contributions | |
� | -0.044 |
idents | -0.036 |
sack | -0.035 |
hotter | -0.034 |
surely | -0.034 |
Token | living |
Token ID | 2877 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
� | +0.053 |
idents | +0.045 |
sack | +0.045 |
hotter | +0.043 |
cooler | +0.042 |
Neg logit contributions | |
Jo | -0.058 |
rum | -0.056 |
ud | -0.049 |
and | -0.049 |
Pen | -0.049 |
Token | room |
Token ID | 2119 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Jo | +0.833 |
rum | +0.809 |
jo | +0.724 |
weet | +0.692 |
Pen | +0.691 |
Neg logit contributions | |
� | -0.548 |
sack | -0.532 |
idents | -0.489 |
cooler | -0.486 |
hotter | -0.461 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Jo | +0.202 |
rum | +0.186 |
jo | +0.176 |
Pen | +0.172 |
ud | +0.168 |
Neg logit contributions | |
� | -0.105 |
idents | -0.081 |
sack | -0.079 |
cooler | -0.077 |
surely | -0.071 |
Token | She |
Token ID | 1375 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
� | +0.026 |
idents | +0.021 |
sack | +0.020 |
hotter | +0.020 |
Sorry | +0.019 |
Neg logit contributions | |
Jo | -0.033 |
rum | -0.032 |
ud | -0.028 |
jo | -0.028 |
and | -0.027 |
Token | sees |
Token ID | 7224 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Jo | +0.029 |
rum | +0.029 |
and | +0.026 |
ud | +0.025 |
jo | +0.025 |
Neg logit contributions | |
� | -0.023 |
idents | -0.020 |
sack | -0.020 |
cooler | -0.019 |
hotter | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Jo | +0.040 |
rum | +0.039 |
ud | +0.034 |
Pen | +0.034 |
and | +0.034 |
Neg logit contributions | |
� | -0.037 |
idents | -0.031 |
hotter | -0.030 |
sack | -0.030 |
ory | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
� | +0.037 |
Dino | +0.026 |
surely | +0.025 |
ory | +0.024 |
hotter | +0.021 |
Neg logit contributions | |
rum | -0.075 |
Jo | -0.067 |
rd | -0.062 |
ud | -0.062 |
Jacob | -0.061 |
Token | One |
Token ID | 3198 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
� | +0.041 |
surely | +0.033 |
ory | +0.032 |
Sorry | +0.031 |
Dino | +0.031 |
Neg logit contributions | |
rum | -0.058 |
Jo | -0.054 |
Jacob | -0.049 |
ud | -0.049 |
Pen | -0.048 |
Token | day |
Token ID | 1110 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
rum | +0.029 |
Jo | +0.027 |
ud | +0.024 |
Jacob | +0.024 |
and | +0.024 |
Neg logit contributions | |
� | -0.016 |
ory | -0.014 |
cooler | -0.014 |
surely | -0.014 |
sack | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
rum | +0.121 |
Jo | +0.121 |
and | +0.105 |
jo | +0.104 |
ud | +0.104 |
Neg logit contributions | |
� | -0.114 |
ory | -0.093 |
idents | -0.093 |
sack | -0.090 |
hotter | -0.090 |
Token | Mon |
Token ID | 2892 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
� | +0.005 |
idents | +0.004 |
sack | +0.004 |
hotter | +0.004 |
surely | +0.004 |
Neg logit contributions | |
Jo | -0.003 |
rum | -0.003 |
Pen | -0.003 |
Ali | -0.003 |
Jacob | -0.003 |
Token | a |
Token ID | 64 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
Jo | +0.045 |
rum | +0.042 |
Pen | +0.029 |
ud | +0.028 |
and | +0.027 |
Neg logit contributions | |
� | -0.166 |
idents | -0.150 |
ory | -0.148 |
sack | -0.146 |
hotter | -0.146 |
Token | was |
Token ID | 373 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
rum | +0.722 |
Jo | +0.694 |
and | +0.608 |
Pen | +0.605 |
ud | +0.597 |
Neg logit contributions | |
� | -0.539 |
sack | -0.468 |
ory | -0.460 |
idents | -0.449 |
cooler | -0.428 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
rum | +0.046 |
Jo | +0.045 |
jo | +0.040 |
ud | +0.037 |
and | +0.036 |
Neg logit contributions | |
� | -0.042 |
hotter | -0.037 |
cooler | -0.037 |
surely | -0.037 |
sack | -0.036 |
Token | dolls |
Token ID | 36062 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Jo | +0.243 |
rum | +0.237 |
ud | +0.210 |
jo | +0.209 |
Pen | +0.204 |
Neg logit contributions | |
� | -0.203 |
sack | -0.166 |
idents | -0.165 |
hotter | -0.159 |
surely | -0.159 |
Token | with |
Token ID | 351 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
rum | +0.157 |
Jo | +0.156 |
Pen | +0.134 |
jo | +0.132 |
Ali | +0.131 |
Neg logit contributions | |
� | -0.115 |
sack | -0.092 |
surely | -0.089 |
idents | -0.087 |
cooler | -0.085 |
Token | T |
Token ID | 309 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
� | +0.022 |
sack | +0.018 |
Dino | +0.018 |
cooler | +0.018 |
hotter | +0.017 |
Neg logit contributions | |
rum | -0.027 |
Jo | -0.026 |
jo | -0.023 |
ud | -0.022 |
and | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | +2.73e-03 |
Pos logit contributions | |
� | +0.006 |
idents | +0.005 |
sack | +0.005 |
Dino | +0.005 |
hotter | +0.004 |
Neg logit contributions | |
Jo | -0.004 |
rum | -0.003 |
Pen | -0.003 |
and | -0.003 |
Ali | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
surely | +0.000 |
still | +0.000 |
� | +0.000 |
idents | +0.000 |
finally | +0.000 |
Neg logit contributions | |
rum | -0.000 |
ud | -0.000 |
and | -0.000 |
rd | -0.000 |
Jo | -0.000 |
Token | special |
Token ID | 2041 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
� | +0.043 |
idents | +0.036 |
sack | +0.034 |
hotter | +0.034 |
surely | +0.034 |
Neg logit contributions | |
Jo | -0.050 |
rum | -0.048 |
ud | -0.042 |
Pen | -0.042 |
and | -0.042 |
Token | find |
Token ID | 1064 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
� | +0.087 |
idents | +0.071 |
sack | +0.071 |
ory | +0.067 |
hotter | +0.067 |
Neg logit contributions | |
Jo | -0.128 |
rum | -0.126 |
and | -0.113 |
ud | -0.113 |
Jacob | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e-02 |
Pos logit contributions | |
� | +0.058 |
sack | +0.051 |
cooler | +0.048 |
ory | +0.047 |
idents | +0.047 |
Neg logit contributions | |
rum | -0.089 |
Jo | -0.089 |
ud | -0.081 |
jo | -0.078 |
and | -0.077 |
Token | Ann |
Token ID | 5506 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
rum | +0.007 |
ud | +0.006 |
weet | +0.006 |
Jo | +0.006 |
and | +0.006 |
Neg logit contributions | |
� | -0.006 |
idents | -0.004 |
surely | -0.004 |
Finally | -0.004 |
Later | -0.004 |
Token | abel |
Token ID | 9608 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
rum | +0.506 |
and | +0.429 |
Jo | +0.379 |
uzzle | +0.360 |
outage | +0.355 |
Neg logit contributions | |
� | -0.619 |
ory | -0.619 |
still | -0.583 |
surely | -0.582 |
continued | -0.582 |
Token | le |
Token ID | 293 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
rum | +0.874 |
Jo | +0.803 |
and | +0.758 |
ud | +0.743 |
Ali | +0.740 |
Neg logit contributions | |
� | -0.586 |
ory | -0.513 |
ized | -0.505 |
surely | -0.497 |
sack | -0.463 |
Token | taught |
Token ID | 7817 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
rum | +0.131 |
Jo | +0.123 |
and | +0.117 |
ud | +0.114 |
Pen | +0.112 |
Neg logit contributions | |
� | -0.089 |
ory | -0.073 |
sack | -0.072 |
surely | -0.070 |
idents | -0.069 |
Token | them |
Token ID | 606 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
� | +0.090 |
idents | +0.082 |
Ros | +0.080 |
Dino | +0.075 |
sack | +0.074 |
Neg logit contributions | |
rum | -0.185 |
ud | -0.166 |
Jo | -0.164 |
and | -0.156 |
rd | -0.155 |
Token | the |
Token ID | 262 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
� | +0.047 |
idents | +0.044 |
sack | +0.044 |
cooler | +0.043 |
prett | +0.040 |
Neg logit contributions | |
Jo | -0.071 |
rum | -0.070 |
ud | -0.066 |
jo | -0.063 |
Pen | -0.059 |