Token | Some |
Token ID | 2773 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
orse | +0.049 |
oc | +0.037 |
weapon | +0.036 |
bone | +0.035 |
Carl | +0.034 |
Neg logit contributions | |
groom | -0.056 |
register | -0.052 |
roses | -0.051 |
decides | -0.049 |
ponies | -0.049 |
Token | people |
Token ID | 661 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
groom | +0.270 |
roses | +0.251 |
decides | +0.237 |
register | +0.232 |
ponies | +0.229 |
Neg logit contributions | |
orse | -0.422 |
oc | -0.348 |
weapon | -0.346 |
uddy | -0.343 |
Carl | -0.336 |
Token | live |
Token ID | 2107 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
groom | +0.148 |
roses | +0.135 |
register | +0.130 |
decides | +0.129 |
ponies | +0.123 |
Neg logit contributions | |
orse | -0.202 |
weapon | -0.164 |
oc | -0.163 |
bone | -0.156 |
uddy | -0.156 |
Token | on |
Token ID | 319 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
orse | +0.252 |
weapon | +0.200 |
oc | +0.197 |
bone | +0.189 |
oy | +0.188 |
Neg logit contributions | |
groom | -0.226 |
register | -0.205 |
roses | -0.205 |
decides | -0.197 |
ponies | -0.193 |
Token | y |
Token ID | 331 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
groom | +0.122 |
register | +0.113 |
roses | +0.110 |
decides | +0.109 |
ponies | +0.102 |
Neg logit contributions | |
orse | -0.144 |
weapon | -0.115 |
oc | -0.114 |
bone | -0.111 |
hockey | -0.110 |
Token | ach |
Token ID | 620 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
orse | +0.285 |
weapon | +0.227 |
oc | +0.226 |
uddy | +0.216 |
ggy | +0.216 |
Neg logit contributions | |
groom | -0.235 |
roses | -0.224 |
register | -0.214 |
decides | -0.212 |
ponies | -0.204 |
Token | ts |
Token ID | 912 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
orse | +0.853 |
weapon | +0.667 |
oc | +0.665 |
bone | +0.629 |
oy | +0.628 |
Neg logit contributions | |
groom | -0.755 |
roses | -0.696 |
register | -0.684 |
decides | -0.669 |
ponies | -0.648 |
Token | and |
Token ID | 290 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
orse | +0.286 |
weapon | +0.228 |
oc | +0.226 |
bone | +0.215 |
uddy | +0.215 |
Neg logit contributions | |
groom | -0.241 |
roses | -0.223 |
register | -0.215 |
decides | -0.213 |
ponies | -0.206 |
Token | travel |
Token ID | 3067 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
orse | +0.034 |
weapon | +0.027 |
oc | +0.027 |
bone | +0.025 |
Carl | +0.025 |
Neg logit contributions | |
groom | -0.030 |
roses | -0.028 |
register | -0.027 |
decides | -0.027 |
ponies | -0.026 |
Token | around |
Token ID | 1088 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
orse | +0.155 |
weapon | +0.124 |
oc | +0.123 |
bone | +0.118 |
oy | +0.116 |
Neg logit contributions | |
groom | -0.150 |
roses | -0.137 |
register | -0.136 |
decides | -0.131 |
ponies | -0.127 |
Token | the |
Token ID | 262 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
groom | +0.113 |
roses | +0.103 |
register | +0.102 |
decides | +0.099 |
ponies | +0.095 |
Neg logit contributions | |
orse | -0.140 |
weapon | -0.111 |
oc | -0.111 |
bone | -0.105 |
Carl | -0.104 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
groom | +0.078 |
roses | +0.070 |
register | +0.069 |
decides | +0.068 |
ponies | +0.065 |
Neg logit contributions | |
orse | -0.087 |
weapon | -0.070 |
oc | -0.067 |
uddy | -0.066 |
Carl | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
orse | +0.107 |
oc | +0.086 |
bone | +0.084 |
weapon | +0.084 |
Carl | +0.083 |
Neg logit contributions | |
groom | -0.099 |
register | -0.091 |
roses | -0.091 |
decides | -0.090 |
ponies | -0.085 |
Token | handful |
Token ID | 10089 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
orse | +0.029 |
weapon | +0.023 |
Carl | +0.023 |
Andy | +0.023 |
uddy | +0.022 |
Neg logit contributions | |
groom | -0.026 |
roses | -0.023 |
register | -0.022 |
decides | -0.021 |
ponies | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
orse | +0.135 |
weapon | +0.100 |
oc | +0.099 |
ggy | +0.092 |
bone | +0.092 |
Neg logit contributions | |
groom | -0.175 |
roses | -0.165 |
register | -0.162 |
decides | -0.159 |
ponies | -0.154 |
Token | happily |
Token ID | 18177 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
orse | +0.024 |
weapon | +0.020 |
oc | +0.019 |
uddy | +0.019 |
unch | +0.019 |
Neg logit contributions | |
groom | -0.020 |
roses | -0.019 |
decides | -0.018 |
register | -0.018 |
ponies | -0.017 |
Token | mun |
Token ID | 29856 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
groom | +0.087 |
roses | +0.079 |
register | +0.077 |
decides | +0.076 |
ponies | +0.072 |
Neg logit contributions | |
orse | -0.095 |
weapon | -0.077 |
oc | -0.075 |
bone | -0.072 |
uddy | -0.072 |
Token | ched |
Token ID | 1740 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
orse | +0.691 |
oc | +0.503 |
weapon | +0.488 |
hockey | +0.472 |
puck | +0.466 |
Neg logit contributions | |
groom | -0.887 |
roses | -0.830 |
ponies | -0.806 |
decides | -0.802 |
register | -0.799 |
Token | away |
Token ID | 1497 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
orse | +0.000 |
weapon | +0.000 |
oc | +0.000 |
bone | +0.000 |
uddy | +0.000 |
Neg logit contributions | |
groom | -0.000 |
roses | -0.000 |
register | -0.000 |
decides | -0.000 |
ponies | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
groom | +0.150 |
roses | +0.139 |
register | +0.133 |
decides | +0.128 |
ponies | +0.127 |
Neg logit contributions | |
orse | -0.196 |
weapon | -0.157 |
oc | -0.155 |
uddy | -0.151 |
bone | -0.148 |
Token | The |
Token ID | 383 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
orse | +0.045 |
weapon | +0.033 |
oc | +0.033 |
bone | +0.031 |
uddy | +0.031 |
Neg logit contributions | |
groom | -0.056 |
roses | -0.053 |
register | -0.052 |
decides | -0.051 |
ponies | -0.050 |
Token | popcorn |
Token ID | 38914 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
orse | +0.220 |
weapon | +0.179 |
oc | +0.174 |
bone | +0.174 |
hockey | +0.171 |
Neg logit contributions | |
groom | -0.175 |
roses | -0.162 |
decides | -0.158 |
register | -0.153 |
ponies | -0.148 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
orse | +0.258 |
oc | +0.220 |
inations | +0.209 |
weapon | +0.202 |
unch | +0.200 |
Neg logit contributions | |
groom | -0.187 |
roses | -0.181 |
her | -0.166 |
decides | -0.166 |
register | -0.162 |
Token | Sam |
Token ID | 3409 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
groom | +0.007 |
roses | +0.007 |
her | +0.006 |
Angel | +0.006 |
herself | +0.006 |
Neg logit contributions | |
oc | -0.012 |
orse | -0.011 |
inations | -0.010 |
oy | -0.010 |
rd | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
orse | +0.458 |
oc | +0.373 |
weapon | +0.368 |
unch | +0.352 |
puck | +0.351 |
Neg logit contributions | |
groom | -0.392 |
roses | -0.367 |
decides | -0.348 |
register | -0.347 |
ponies | -0.334 |
Token | se |
Token ID | 384 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
orse | +0.037 |
oc | +0.033 |
uddy | +0.030 |
anas | +0.029 |
oy | +0.029 |
Neg logit contributions | |
groom | -0.028 |
roses | -0.026 |
decides | -0.025 |
mirror | -0.024 |
register | -0.022 |
Token | ah |
Token ID | 993 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
orse | +0.084 |
Andy | +0.067 |
Carl | +0.067 |
burying | +0.065 |
puck | +0.065 |
Neg logit contributions | |
groom | -0.089 |
decides | -0.084 |
register | -0.080 |
roses | -0.078 |
ponies | -0.075 |
Token | orse |
Token ID | 7615 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
igsaw | +0.314 |
uddy | +0.288 |
Timothy | +0.278 |
Johnny | +0.272 |
Jerry | +0.270 |
Neg logit contributions | |
roses | -0.342 |
groom | -0.331 |
decides | -0.316 |
rose | -0.300 |
back | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
orse | +0.869 |
oc | +0.747 |
puck | +0.715 |
unch | +0.705 |
weapon | +0.702 |
Neg logit contributions | |
groom | -0.641 |
roses | -0.600 |
decides | -0.585 |
register | -0.552 |
ponies | -0.522 |
Token |
|
Token ID | 198 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
orse | +0.062 |
inations | +0.053 |
oc | +0.051 |
weapon | +0.051 |
ggy | +0.050 |
Neg logit contributions | |
decides | -0.042 |
groom | -0.039 |
roses | -0.038 |
als | -0.036 |
She | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
orse | +0.046 |
weapon | +0.042 |
puck | +0.039 |
bullets | +0.039 |
oc | +0.038 |
Neg logit contributions | |
groom | -0.028 |
roses | -0.028 |
She | -0.027 |
decides | -0.027 |
Angel | -0.026 |
Token | Fin |
Token ID | 18467 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
orse | +0.043 |
inations | +0.033 |
burying | +0.033 |
weapon | +0.032 |
unch | +0.031 |
Neg logit contributions | |
She | -0.037 |
decides | -0.037 |
groom | -0.037 |
roses | -0.034 |
als | -0.033 |
Token | said |
Token ID | 531 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
orse | +0.557 |
unch | +0.489 |
weapon | +0.465 |
importantly | +0.452 |
oc | +0.447 |
Neg logit contributions | |
groom | -0.447 |
decides | -0.425 |
roses | -0.401 |
ponies | -0.350 |
Angel | -0.349 |
Token |
|
Token ID | 198 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
orse | +0.037 |
weapon | +0.030 |
oc | +0.028 |
bone | +0.027 |
puck | +0.027 |
Neg logit contributions | |
groom | -0.040 |
roses | -0.038 |
decides | -0.037 |
register | -0.036 |
ponies | -0.035 |
Token | They |
Token ID | 2990 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
orse | +0.040 |
oc | +0.032 |
weapon | +0.031 |
ggy | +0.030 |
uddy | +0.030 |
Neg logit contributions | |
groom | -0.039 |
roses | -0.036 |
register | -0.036 |
decides | -0.035 |
ponies | -0.034 |
Token | both |
Token ID | 1111 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
groom | +0.045 |
roses | +0.042 |
register | +0.041 |
decides | +0.040 |
ponies | +0.040 |
Neg logit contributions | |
orse | -0.048 |
oc | -0.038 |
weapon | -0.038 |
bone | -0.036 |
oy | -0.036 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
orse | +0.010 |
weapon | +0.008 |
oc | +0.008 |
bone | +0.008 |
uddy | +0.007 |
Neg logit contributions | |
groom | -0.010 |
roses | -0.009 |
decides | -0.009 |
register | -0.009 |
ponies | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
orse | +0.122 |
weapon | +0.099 |
Carl | +0.098 |
oc | +0.097 |
bone | +0.097 |
Neg logit contributions | |
groom | -0.107 |
register | -0.097 |
decides | -0.096 |
roses | -0.095 |
ponies | -0.090 |
Token | lun |
Token ID | 14678 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
orse | +0.056 |
oc | +0.047 |
unch | +0.045 |
uddy | +0.044 |
weapon | +0.043 |
Neg logit contributions | |
roses | -0.034 |
groom | -0.033 |
decides | -0.032 |
ponies | -0.030 |
back | -0.029 |
Token | ches |
Token ID | 2052 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
orse | +0.871 |
weapon | +0.698 |
oc | +0.689 |
bone | +0.660 |
uddy | +0.651 |
Neg logit contributions | |
groom | -0.707 |
roses | -0.652 |
register | -0.627 |
decides | -0.623 |
ponies | -0.602 |
Token | . |
Token ID | 13 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
groom | +0.025 |
register | +0.024 |
roses | +0.024 |
ponies | +0.022 |
decides | +0.021 |
Neg logit contributions | |
orse | -0.042 |
oc | -0.034 |
unch | -0.032 |
weapon | -0.032 |
inations | -0.032 |
Token | Ell |
Token ID | 7122 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
orse | +0.051 |
oc | +0.040 |
Carl | +0.038 |
weapon | +0.038 |
Andy | +0.038 |
Neg logit contributions | |
groom | -0.065 |
roses | -0.060 |
register | -0.060 |
decides | -0.058 |
ponies | -0.057 |
Token | a |
Token ID | 64 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
orse | +0.010 |
oc | +0.008 |
ggy | +0.008 |
weapon | +0.007 |
uddy | +0.007 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.007 |
register | -0.007 |
decides | -0.006 |
ponies | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
orse | +0.131 |
weapon | +0.102 |
oc | +0.100 |
bone | +0.095 |
uddy | +0.094 |
Neg logit contributions | |
groom | -0.130 |
roses | -0.121 |
register | -0.117 |
decides | -0.116 |
ponies | -0.112 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
groom | +0.015 |
roses | +0.015 |
register | +0.014 |
ponies | +0.014 |
decides | +0.014 |
Neg logit contributions | |
orse | -0.022 |
oc | -0.018 |
unch | -0.017 |
weapon | -0.017 |
uddy | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
orse | +0.261 |
oc | +0.215 |
weapon | +0.210 |
uddy | +0.204 |
unch | +0.200 |
Neg logit contributions | |
groom | -0.218 |
roses | -0.203 |
decides | -0.190 |
ponies | -0.187 |
register | -0.185 |
Token | proud |
Token ID | 6613 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
orse | +0.146 |
oc | +0.115 |
weapon | +0.115 |
uddy | +0.108 |
bone | +0.108 |
Neg logit contributions | |
groom | -0.139 |
roses | -0.128 |
decides | -0.124 |
register | -0.124 |
ponies | -0.119 |
Token | of |
Token ID | 286 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
orse | +0.094 |
oc | +0.077 |
weapon | +0.075 |
uddy | +0.073 |
puck | +0.073 |
Neg logit contributions | |
groom | -0.079 |
roses | -0.076 |
ponies | -0.070 |
decides | -0.069 |
register | -0.069 |
Token | his |
Token ID | 465 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
orse | +0.244 |
weapon | +0.202 |
oc | +0.200 |
bone | +0.194 |
Carl | +0.193 |
Neg logit contributions | |
groom | -0.131 |
roses | -0.117 |
register | -0.114 |
decides | -0.111 |
ponies | -0.105 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
orse | +0.371 |
oc | +0.292 |
unch | +0.286 |
uddy | +0.282 |
Carl | +0.274 |
Neg logit contributions | |
groom | -0.338 |
roses | -0.319 |
ponies | -0.301 |
decides | -0.300 |
register | -0.299 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
orse | +0.908 |
oc | +0.696 |
unch | +0.691 |
weapon | +0.688 |
uddy | +0.672 |
Neg logit contributions | |
groom | -0.638 |
register | -0.626 |
roses | -0.615 |
ponies | -0.585 |
decides | -0.579 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
orse | +0.060 |
weapon | +0.049 |
ggy | +0.045 |
oy | +0.045 |
inations | +0.045 |
Neg logit contributions | |
groom | -0.062 |
decides | -0.059 |
roses | -0.058 |
register | -0.057 |
Angel | -0.057 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
orse | +0.383 |
weapon | +0.307 |
oc | +0.295 |
oy | +0.287 |
puck | +0.285 |
Neg logit contributions | |
groom | -0.294 |
roses | -0.282 |
decides | -0.272 |
register | -0.272 |
ponies | -0.262 |
Token | upon |
Token ID | 2402 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
orse | +0.235 |
oc | +0.199 |
weapon | +0.188 |
anas | +0.185 |
puck | +0.184 |
Neg logit contributions | |
groom | -0.208 |
roses | -0.201 |
register | -0.197 |
decides | -0.195 |
ponies | -0.188 |
Token | a |
Token ID | 257 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
orse | +0.667 |
oc | +0.591 |
uddy | +0.583 |
weapon | +0.561 |
oy | +0.546 |
Neg logit contributions | |
groom | -0.293 |
roses | -0.261 |
herself | -0.248 |
her | -0.245 |
ponies | -0.242 |
Token | to |
Token ID | 284 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
groom | +0.224 |
roses | +0.211 |
decides | +0.188 |
ponies | +0.185 |
register | +0.180 |
Neg logit contributions | |
orse | -0.313 |
oc | -0.255 |
weapon | -0.255 |
uddy | -0.245 |
bone | -0.241 |
Token | eat |
Token ID | 4483 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
orse | +0.055 |
weapon | +0.043 |
oc | +0.043 |
bone | +0.041 |
uddy | +0.040 |
Neg logit contributions | |
groom | -0.053 |
roses | -0.050 |
register | -0.048 |
decides | -0.048 |
ponies | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
orse | +0.129 |
oc | +0.103 |
weapon | +0.103 |
bone | +0.099 |
Carl | +0.097 |
Neg logit contributions | |
groom | -0.120 |
roses | -0.109 |
register | -0.109 |
decides | -0.107 |
ponies | -0.103 |
Token | The |
Token ID | 383 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
orse | +0.037 |
weapon | +0.029 |
oc | +0.028 |
bone | +0.027 |
uddy | +0.026 |
Neg logit contributions | |
groom | -0.041 |
roses | -0.039 |
register | -0.038 |
decides | -0.037 |
ponies | -0.036 |
Token | bear |
Token ID | 6842 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
orse | +0.224 |
weapon | +0.181 |
oc | +0.179 |
bone | +0.171 |
uddy | +0.171 |
Neg logit contributions | |
groom | -0.158 |
roses | -0.145 |
register | -0.139 |
decides | -0.137 |
ponies | -0.133 |
Token | mun |
Token ID | 29856 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
orse | +0.034 |
weapon | +0.028 |
unch | +0.027 |
uddy | +0.026 |
puck | +0.026 |
Neg logit contributions | |
groom | -0.034 |
roses | -0.031 |
decides | -0.031 |
register | -0.028 |
ponies | -0.028 |
Token | ched |
Token ID | 1740 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
orse | +0.654 |
oc | +0.485 |
weapon | +0.464 |
bone | +0.440 |
unch | +0.440 |
Neg logit contributions | |
groom | -0.918 |
roses | -0.852 |
register | -0.834 |
ponies | -0.831 |
decides | -0.822 |
Token | the |
Token ID | 262 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
groom | +0.005 |
roses | +0.005 |
register | +0.005 |
decides | +0.005 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.009 |
weapon | -0.007 |
oc | -0.007 |
bone | -0.007 |
uddy | -0.007 |
Token | juicy |
Token ID | 35075 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
orse | +0.025 |
weapon | +0.019 |
oc | +0.019 |
bone | +0.018 |
uddy | +0.018 |
Neg logit contributions | |
groom | -0.021 |
roses | -0.019 |
register | -0.018 |
decides | -0.018 |
ponies | -0.018 |
Token | green |
Token ID | 4077 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
orse | +0.104 |
oc | +0.085 |
weapon | +0.083 |
bone | +0.081 |
hockey | +0.078 |
Neg logit contributions | |
groom | -0.097 |
register | -0.088 |
decides | -0.087 |
roses | -0.086 |
ponies | -0.083 |
Token | sa |
Token ID | 473 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
groom | +0.042 |
roses | +0.038 |
register | +0.038 |
decides | +0.038 |
ponies | +0.036 |
Neg logit contributions | |
orse | -0.049 |
oc | -0.039 |
weapon | -0.039 |
bone | -0.037 |
oy | -0.036 |
Token | on |
Token ID | 319 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
orse | +0.435 |
oc | +0.346 |
weapon | +0.339 |
uddy | +0.335 |
unch | +0.331 |
Neg logit contributions | |
groom | -0.338 |
roses | -0.312 |
register | -0.295 |
decides | -0.293 |
ponies | -0.287 |
Token | one |
Token ID | 530 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
groom | +0.119 |
roses | +0.114 |
ponies | +0.103 |
decides | +0.100 |
register | +0.098 |
Neg logit contributions | |
orse | -0.206 |
uddy | -0.171 |
oc | -0.171 |
weapon | -0.164 |
unch | -0.164 |
Token | of |
Token ID | 286 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
groom | +0.229 |
roses | +0.212 |
register | +0.203 |
decides | +0.194 |
ponies | +0.191 |
Neg logit contributions | |
orse | -0.287 |
oc | -0.233 |
weapon | -0.227 |
uddy | -0.227 |
unch | -0.223 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
orse | +0.125 |
weapon | +0.100 |
oc | +0.100 |
bone | +0.095 |
uddy | +0.094 |
Neg logit contributions | |
groom | -0.098 |
roses | -0.090 |
register | -0.087 |
decides | -0.086 |
ponies | -0.083 |
Token | y |
Token ID | 331 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
orse | +0.010 |
oc | +0.008 |
uddy | +0.008 |
weapon | +0.008 |
unch | +0.008 |
Neg logit contributions | |
groom | -0.008 |
roses | -0.008 |
register | -0.007 |
decides | -0.007 |
ponies | -0.007 |
Token | ach |
Token ID | 620 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
orse | +0.226 |
weapon | +0.172 |
oc | +0.171 |
uddy | +0.166 |
ggy | +0.165 |
Neg logit contributions | |
groom | -0.238 |
roses | -0.234 |
register | -0.220 |
decides | -0.217 |
ponies | -0.213 |
Token | ts |
Token ID | 912 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
orse | +0.697 |
oc | +0.585 |
uddy | +0.582 |
weapon | +0.571 |
unch | +0.554 |
Neg logit contributions | |
groom | -0.841 |
roses | -0.784 |
decides | -0.732 |
register | -0.725 |
ponies | -0.718 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
orse | +0.264 |
oc | +0.220 |
weapon | +0.217 |
uddy | +0.211 |
Carl | +0.209 |
Neg logit contributions | |
groom | -0.207 |
roses | -0.188 |
register | -0.184 |
ponies | -0.177 |
decides | -0.174 |
Token | He |
Token ID | 679 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
orse | +0.036 |
inations | +0.030 |
weapon | +0.028 |
unch | +0.028 |
beard | +0.028 |
Neg logit contributions | |
decides | -0.024 |
Angel | -0.023 |
groom | -0.023 |
She | -0.022 |
her | -0.022 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
orse | +0.341 |
unch | +0.294 |
weapon | +0.284 |
uddy | +0.279 |
oc | +0.279 |
Neg logit contributions | |
groom | -0.267 |
decides | -0.240 |
roses | -0.227 |
register | -0.208 |
nurses | -0.206 |
Token | he |
Token ID | 339 |
Feature activation | +6.20e+00 |
Pos logit contributions | |
groom | +0.159 |
roses | +0.155 |
ponies | +0.147 |
register | +0.147 |
nurses | +0.142 |
Neg logit contributions | |
orse | -0.124 |
oc | -0.107 |
unch | -0.092 |
uddy | -0.092 |
weapon | -0.089 |
Token | feeling |
Token ID | 4203 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
orse | +0.121 |
oc | +0.095 |
weapon | +0.095 |
uddy | +0.089 |
bone | +0.089 |
Neg logit contributions | |
groom | -0.118 |
roses | -0.110 |
register | -0.105 |
decides | -0.104 |
ponies | -0.102 |
Token | very |
Token ID | 845 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
orse | +0.382 |
weapon | +0.289 |
hockey | +0.280 |
Benny | +0.277 |
oc | +0.277 |
Neg logit contributions | |
groom | -0.390 |
register | -0.364 |
roses | -0.355 |
decides | -0.346 |
ponies | -0.340 |
Token | pleased |
Token ID | 10607 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
groom | +0.046 |
roses | +0.043 |
register | +0.042 |
decides | +0.041 |
ponies | +0.040 |
Neg logit contributions | |
orse | -0.044 |
weapon | -0.034 |
oc | -0.033 |
bone | -0.032 |
ggy | -0.032 |
Token | by |
Token ID | 416 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
orse | +0.293 |
weapon | +0.242 |
oc | +0.242 |
uddy | +0.239 |
puck | +0.235 |
Neg logit contributions | |
groom | -0.212 |
roses | -0.206 |
ponies | -0.181 |
register | -0.181 |
decides | -0.176 |
Token | his |
Token ID | 465 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
orse | +0.667 |
oc | +0.558 |
weapon | +0.553 |
uddy | +0.534 |
bone | +0.526 |
Neg logit contributions | |
groom | -0.424 |
roses | -0.394 |
register | -0.360 |
decides | -0.354 |
ponies | -0.349 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
orse | +0.360 |
oc | +0.282 |
weapon | +0.274 |
unch | +0.271 |
uddy | +0.270 |
Neg logit contributions | |
groom | -0.327 |
roses | -0.307 |
register | -0.289 |
decides | -0.288 |
ponies | -0.285 |
Token | . |
Token ID | 13 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
orse | +0.893 |
oc | +0.723 |
uddy | +0.703 |
unch | +0.699 |
weapon | +0.691 |
Neg logit contributions | |
groom | -0.616 |
roses | -0.597 |
register | -0.591 |
ponies | -0.548 |
decides | -0.540 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
orse | +0.053 |
weapon | +0.044 |
ggy | +0.040 |
oy | +0.040 |
inations | +0.040 |
Neg logit contributions | |
groom | -0.053 |
roses | -0.050 |
decides | -0.049 |
register | -0.049 |
Angel | -0.049 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
orse | +0.414 |
weapon | +0.338 |
oc | +0.326 |
oy | +0.319 |
puck | +0.317 |
Neg logit contributions | |
groom | -0.250 |
roses | -0.240 |
decides | -0.231 |
register | -0.229 |
ponies | -0.217 |
Token | there |
Token ID | 612 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
orse | +0.232 |
oc | +0.195 |
weapon | +0.186 |
puck | +0.182 |
anas | +0.181 |
Neg logit contributions | |
groom | -0.202 |
roses | -0.197 |
register | -0.192 |
decides | -0.191 |
ponies | -0.182 |
Token | was |
Token ID | 373 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
orse | +0.095 |
weapon | +0.078 |
inations | +0.076 |
bullets | +0.075 |
oc | +0.074 |
Neg logit contributions | |
groom | -0.076 |
roses | -0.074 |
decides | -0.072 |
register | -0.071 |
her | -0.070 |
Token | started |
Token ID | 2067 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
groom | +0.026 |
roses | +0.024 |
register | +0.023 |
decides | +0.023 |
ponies | +0.022 |
Neg logit contributions | |
orse | -0.029 |
weapon | -0.023 |
oc | -0.023 |
bone | -0.022 |
uddy | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
groom | +0.282 |
roses | +0.263 |
register | +0.251 |
decides | +0.249 |
ponies | +0.243 |
Neg logit contributions | |
orse | -0.287 |
oc | -0.225 |
weapon | -0.225 |
bone | -0.210 |
uddy | -0.210 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
orse | +0.048 |
weapon | +0.038 |
oc | +0.037 |
bone | +0.035 |
uddy | +0.035 |
Neg logit contributions | |
groom | -0.045 |
roses | -0.042 |
register | -0.041 |
decides | -0.040 |
ponies | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
orse | +0.127 |
weapon | +0.101 |
oc | +0.101 |
bone | +0.097 |
Carl | +0.095 |
Neg logit contributions | |
groom | -0.108 |
roses | -0.098 |
register | -0.097 |
decides | -0.095 |
ponies | -0.092 |
Token | They |
Token ID | 1119 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
orse | +0.027 |
Andy | +0.021 |
Carl | +0.021 |
Benny | +0.021 |
Joe | +0.020 |
Neg logit contributions | |
groom | -0.036 |
register | -0.034 |
decides | -0.032 |
ponies | -0.032 |
roses | -0.031 |
Token | mun |
Token ID | 29856 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
orse | +0.068 |
oc | +0.049 |
weapon | +0.049 |
bone | +0.047 |
Carl | +0.047 |
Neg logit contributions | |
groom | -0.083 |
roses | -0.079 |
register | -0.079 |
decides | -0.076 |
ponies | -0.075 |
Token | ched |
Token ID | 1740 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
orse | +0.687 |
oc | +0.508 |
weapon | +0.485 |
unch | +0.470 |
bone | +0.470 |
Neg logit contributions | |
groom | -0.867 |
roses | -0.801 |
register | -0.792 |
decides | -0.784 |
ponies | -0.775 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
groom | +0.012 |
roses | +0.011 |
register | +0.011 |
decides | +0.011 |
ponies | +0.010 |
Neg logit contributions | |
orse | -0.018 |
weapon | -0.015 |
oc | -0.014 |
unch | -0.014 |
uddy | -0.014 |
Token | cr |
Token ID | 1067 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.008 |
oc | +0.008 |
uddy | +0.007 |
unch | +0.007 |
Neg logit contributions | |
groom | -0.009 |
roses | -0.009 |
decides | -0.008 |
register | -0.008 |
ponies | -0.008 |
Token | un |
Token ID | 403 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
orse | +0.315 |
weapon | +0.252 |
oc | +0.248 |
bone | +0.230 |
hockey | +0.228 |
Neg logit contributions | |
groom | -0.292 |
roses | -0.277 |
register | -0.269 |
ponies | -0.254 |
als | -0.253 |
Token | ched |
Token ID | 1740 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
orse | +0.263 |
weapon | +0.236 |
puck | +0.208 |
bone | +0.205 |
oc | +0.204 |
Neg logit contributions | |
groom | -0.207 |
roses | -0.194 |
als | -0.186 |
register | -0.178 |
ponies | -0.173 |
Token | was |
Token ID | 373 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
orse | +0.417 |
weapon | +0.335 |
unch | +0.316 |
uddy | +0.316 |
oc | +0.312 |
Neg logit contributions | |
groom | -0.419 |
decides | -0.385 |
roses | -0.384 |
register | -0.369 |
ponies | -0.353 |
Token | so |
Token ID | 523 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
orse | +0.151 |
oc | +0.122 |
weapon | +0.122 |
uddy | +0.116 |
bone | +0.113 |
Neg logit contributions | |
groom | -0.133 |
roses | -0.121 |
register | -0.118 |
decides | -0.116 |
ponies | -0.112 |
Token | proud |
Token ID | 6613 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
orse | +0.070 |
weapon | +0.060 |
uddy | +0.059 |
oc | +0.057 |
bullets | +0.056 |
Neg logit contributions | |
groom | -0.058 |
decides | -0.051 |
roses | -0.051 |
register | -0.049 |
bride | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
orse | +0.016 |
gh | +0.014 |
uddy | +0.014 |
oc | +0.014 |
ggies | +0.014 |
Neg logit contributions | |
roses | -0.008 |
her | -0.007 |
ponies | -0.007 |
groom | -0.007 |
flowers | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
orse | +0.126 |
uddy | +0.106 |
oc | +0.101 |
unch | +0.097 |
weapon | +0.092 |
Neg logit contributions | |
herself | -0.140 |
roses | -0.138 |
groom | -0.137 |
her | -0.134 |
decides | -0.131 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
orse | +0.357 |
oc | +0.299 |
Andy | +0.295 |
uddy | +0.293 |
Joe | +0.286 |
Neg logit contributions | |
groom | -0.264 |
back | -0.257 |
roses | -0.243 |
register | -0.242 |
mirror | -0.236 |
Token | and |
Token ID | 290 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
orse | +1.042 |
emy | +0.852 |
unch | +0.844 |
inations | +0.840 |
orses | +0.838 |
Neg logit contributions | |
register | -0.457 |
back | -0.434 |
groom | -0.404 |
roses | -0.395 |
her | -0.392 |
Token | hurried |
Token ID | 31662 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
orse | +0.033 |
uddy | +0.029 |
oc | +0.027 |
unch | +0.027 |
weapon | +0.026 |
Neg logit contributions | |
groom | -0.034 |
decides | -0.031 |
roses | -0.030 |
register | -0.028 |
ponies | -0.027 |
Token | back |
Token ID | 736 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
groom | +0.039 |
roses | +0.034 |
register | +0.032 |
decides | +0.031 |
ponies | +0.029 |
Neg logit contributions | |
orse | -0.100 |
weapon | -0.085 |
oc | -0.084 |
bone | -0.082 |
uddy | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
groom | +0.370 |
roses | +0.335 |
register | +0.324 |
decides | +0.318 |
ponies | +0.305 |
Neg logit contributions | |
orse | -0.594 |
weapon | -0.488 |
oc | -0.485 |
bone | -0.465 |
uddy | -0.460 |
Token | his |
Token ID | 465 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
orse | +0.067 |
oc | +0.052 |
uddy | +0.051 |
weapon | +0.050 |
unch | +0.047 |
Neg logit contributions | |
groom | -0.088 |
roses | -0.080 |
decides | -0.079 |
register | -0.078 |
ponies | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
orse | +0.139 |
oc | +0.113 |
weapon | +0.111 |
puck | +0.107 |
bone | +0.105 |
Neg logit contributions | |
groom | -0.105 |
roses | -0.102 |
register | -0.095 |
decides | -0.093 |
ponies | -0.092 |
Token | have |
Token ID | 423 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
orse | +0.074 |
weapon | +0.052 |
Carl | +0.052 |
oc | +0.051 |
Andy | +0.051 |
Neg logit contributions | |
groom | -0.071 |
register | -0.069 |
roses | -0.067 |
ponies | -0.065 |
nurses | -0.064 |
Token | made |
Token ID | 925 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
orse | +0.158 |
weapon | +0.126 |
oc | +0.126 |
bone | +0.120 |
uddy | +0.119 |
Neg logit contributions | |
groom | -0.128 |
roses | -0.117 |
register | -0.114 |
decides | -0.112 |
ponies | -0.108 |
Token | this |
Token ID | 428 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
orse | +0.099 |
weapon | +0.082 |
oc | +0.081 |
bone | +0.078 |
uddy | +0.078 |
Neg logit contributions | |
groom | -0.056 |
roses | -0.051 |
register | -0.049 |
decides | -0.047 |
ponies | -0.046 |
Token | intelligent |
Token ID | 12661 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
orse | +0.160 |
weapon | +0.123 |
oc | +0.122 |
bone | +0.115 |
uddy | +0.114 |
Neg logit contributions | |
groom | -0.165 |
roses | -0.154 |
register | -0.149 |
decides | -0.147 |
ponies | -0.143 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
orse | +0.162 |
weapon | +0.130 |
oc | +0.129 |
bone | +0.123 |
uddy | +0.123 |
Neg logit contributions | |
groom | -0.121 |
roses | -0.111 |
register | -0.107 |
decides | -0.106 |
ponies | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
orse | +0.758 |
oc | +0.581 |
weapon | +0.578 |
bone | +0.541 |
uddy | +0.540 |
Neg logit contributions | |
groom | -0.783 |
roses | -0.737 |
register | -0.715 |
decides | -0.699 |
ponies | -0.685 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
orse | +0.044 |
oc | +0.032 |
Andy | +0.031 |
His | +0.030 |
uddy | +0.030 |
Neg logit contributions | |
groom | -0.077 |
roses | -0.072 |
register | -0.069 |
decides | -0.068 |
ponies | -0.067 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
orse | +0.451 |
weapon | +0.370 |
oc | +0.363 |
oy | +0.351 |
ggy | +0.350 |
Neg logit contributions | |
groom | -0.243 |
roses | -0.229 |
register | -0.221 |
decides | -0.217 |
ponies | -0.207 |
Token | there |
Token ID | 612 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
orse | +0.240 |
oc | +0.196 |
weapon | +0.191 |
puck | +0.186 |
bone | +0.181 |
Neg logit contributions | |
groom | -0.233 |
roses | -0.227 |
register | -0.220 |
decides | -0.216 |
ponies | -0.211 |
Token | was |
Token ID | 373 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
orse | +0.129 |
weapon | +0.109 |
inations | +0.106 |
bullets | +0.104 |
puck | +0.104 |
Neg logit contributions | |
her | -0.086 |
groom | -0.086 |
roses | -0.085 |
decides | -0.085 |
mirror | -0.078 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
orse | +0.136 |
oc | +0.118 |
uddy | +0.112 |
weapon | +0.110 |
puck | +0.109 |
Neg logit contributions | |
groom | -0.091 |
roses | -0.089 |
decides | -0.079 |
her | -0.078 |
ponies | -0.078 |
Token | have |
Token ID | 423 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
orse | +0.080 |
weapon | +0.062 |
oc | +0.060 |
Carl | +0.058 |
ggy | +0.058 |
Neg logit contributions | |
groom | -0.065 |
roses | -0.061 |
register | -0.061 |
ponies | -0.058 |
decides | -0.056 |
Token | made |
Token ID | 925 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
orse | +0.165 |
oc | +0.134 |
weapon | +0.133 |
uddy | +0.127 |
bone | +0.127 |
Neg logit contributions | |
groom | -0.122 |
roses | -0.112 |
register | -0.107 |
decides | -0.106 |
ponies | -0.102 |
Token | this |
Token ID | 428 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
orse | +0.095 |
oc | +0.079 |
uddy | +0.077 |
weapon | +0.076 |
oy | +0.074 |
Neg logit contributions | |
groom | -0.060 |
roses | -0.057 |
register | -0.053 |
decides | -0.050 |
ponies | -0.050 |
Token | exciting |
Token ID | 7895 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
orse | +0.189 |
uddy | +0.161 |
unch | +0.153 |
oc | +0.151 |
ggies | +0.151 |
Neg logit contributions | |
groom | -0.129 |
roses | -0.127 |
decides | -0.119 |
mirror | -0.118 |
register | -0.112 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
orse | +0.487 |
uddy | +0.414 |
unch | +0.388 |
oc | +0.366 |
emy | +0.358 |
Neg logit contributions | |
roses | -0.362 |
groom | -0.350 |
mirror | -0.339 |
decides | -0.319 |
ponies | -0.306 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
orse | +0.835 |
oc | +0.656 |
weapon | +0.637 |
uddy | +0.615 |
unch | +0.609 |
Neg logit contributions | |
groom | -0.708 |
roses | -0.674 |
register | -0.652 |
decides | -0.627 |
ponies | -0.622 |
Token | She |
Token ID | 1375 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
orse | +0.075 |
His | +0.066 |
weapon | +0.066 |
oc | +0.065 |
Andy | +0.065 |
Neg logit contributions | |
groom | -0.044 |
roses | -0.037 |
register | -0.036 |
bride | -0.032 |
ponies | -0.031 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
groom | +0.270 |
roses | +0.247 |
decides | +0.239 |
register | +0.238 |
ponies | +0.227 |
Neg logit contributions | |
orse | -0.318 |
weapon | -0.254 |
oc | -0.252 |
bone | -0.240 |
uddy | -0.239 |
Token | back |
Token ID | 736 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
groom | +0.049 |
roses | +0.044 |
register | +0.043 |
decides | +0.042 |
ponies | +0.040 |
Neg logit contributions | |
orse | -0.080 |
weapon | -0.067 |
oc | -0.065 |
bone | -0.064 |
Carl | -0.064 |
Token | home |
Token ID | 1363 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
groom | +0.493 |
register | +0.449 |
roses | +0.433 |
decides | +0.431 |
ponies | +0.404 |
Neg logit contributions | |
orse | -0.459 |
weapon | -0.382 |
Carl | -0.367 |
bone | -0.360 |
Andy | -0.360 |
Token | was |
Token ID | 373 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
groom | +0.173 |
decides | +0.161 |
roses | +0.159 |
register | +0.146 |
als | +0.141 |
Neg logit contributions | |
orse | -0.178 |
weapon | -0.151 |
uddy | -0.149 |
unch | -0.148 |
bone | -0.143 |
Token | so |
Token ID | 523 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
orse | +0.144 |
weapon | +0.113 |
oc | +0.113 |
bone | +0.107 |
uddy | +0.106 |
Neg logit contributions | |
groom | -0.136 |
roses | -0.126 |
register | -0.123 |
decides | -0.121 |
ponies | -0.117 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
orse | +0.063 |
weapon | +0.050 |
oc | +0.049 |
bone | +0.047 |
uddy | +0.047 |
Neg logit contributions | |
groom | -0.065 |
roses | -0.061 |
decides | -0.059 |
register | -0.058 |
ponies | -0.055 |
Token | with |
Token ID | 351 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
orse | +0.141 |
oc | +0.120 |
weapon | +0.116 |
puck | +0.115 |
uddy | +0.114 |
Neg logit contributions | |
roses | -0.087 |
groom | -0.085 |
ponies | -0.077 |
decides | -0.076 |
her | -0.076 |
Token | her |
Token ID | 607 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
orse | +0.445 |
weapon | +0.381 |
Carl | +0.372 |
oc | +0.369 |
bone | +0.369 |
Neg logit contributions | |
groom | -0.175 |
register | -0.146 |
roses | -0.143 |
decides | -0.139 |
ponies | -0.125 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
roses | +0.288 |
back | +0.278 |
groom | +0.275 |
wardrobe | +0.261 |
mirror | +0.256 |
Neg logit contributions | |
orse | -0.339 |
unch | -0.315 |
uddy | -0.313 |
Andy | -0.301 |
Jerry | -0.298 |
Token | and |
Token ID | 290 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
orse | +0.902 |
oc | +0.719 |
puck | +0.693 |
weapon | +0.690 |
unch | +0.681 |
Neg logit contributions | |
groom | -0.617 |
roses | -0.604 |
register | -0.593 |
ponies | -0.556 |
decides | -0.536 |
Token | for |
Token ID | 329 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
orse | +0.036 |
weapon | +0.029 |
oc | +0.028 |
Carl | +0.027 |
bone | +0.027 |
Neg logit contributions | |
groom | -0.031 |
roses | -0.028 |
register | -0.028 |
decides | -0.027 |
ponies | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
orse | +0.251 |
oc | +0.203 |
uddy | +0.196 |
weapon | +0.196 |
unch | +0.190 |
Neg logit contributions | |
groom | -0.229 |
roses | -0.213 |
register | -0.202 |
decides | -0.199 |
ponies | -0.194 |
Token | rest |
Token ID | 1334 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
orse | +0.042 |
unch | +0.036 |
run | +0.036 |
uddy | +0.036 |
oc | +0.036 |
Neg logit contributions | |
groom | -0.037 |
roses | -0.037 |
register | -0.033 |
bride | -0.032 |
mirror | -0.032 |
Token | of |
Token ID | 286 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
orse | +0.242 |
oc | +0.197 |
weapon | +0.188 |
puck | +0.183 |
bone | +0.178 |
Neg logit contributions | |
groom | -0.251 |
roses | -0.248 |
register | -0.243 |
ponies | -0.226 |
decides | -0.221 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
groom | +0.012 |
roses | +0.011 |
decides | +0.011 |
register | +0.011 |
ponies | +0.011 |
Neg logit contributions | |
orse | -0.010 |
oc | -0.008 |
weapon | -0.007 |
uddy | -0.007 |
unch | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
groom | +0.073 |
roses | +0.070 |
ponies | +0.064 |
decides | +0.059 |
nurses | +0.054 |
Neg logit contributions | |
orse | -0.116 |
oc | -0.102 |
uddy | -0.096 |
weapon | -0.094 |
ggy | -0.093 |
Token | watch |
Token ID | 2342 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
orse | +0.031 |
oc | +0.025 |
weapon | +0.024 |
uddy | +0.024 |
unch | +0.023 |
Neg logit contributions | |
groom | -0.033 |
roses | -0.030 |
decides | -0.029 |
register | -0.027 |
ponies | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
groom | +0.064 |
roses | +0.061 |
ponies | +0.056 |
decides | +0.054 |
register | +0.052 |
Neg logit contributions | |
orse | -0.100 |
uddy | -0.084 |
oc | -0.083 |
weapon | -0.081 |
unch | -0.080 |
Token | y |
Token ID | 331 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
groom | +0.002 |
roses | +0.002 |
decides | +0.002 |
ponies | +0.002 |
register | +0.002 |
Neg logit contributions | |
orse | -0.004 |
oc | -0.003 |
uddy | -0.003 |
weapon | -0.003 |
ggy | -0.003 |
Token | ach |
Token ID | 620 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
orse | +0.209 |
weapon | +0.162 |
oc | +0.154 |
uddy | +0.151 |
ggy | +0.150 |
Neg logit contributions | |
groom | -0.233 |
roses | -0.229 |
register | -0.215 |
decides | -0.212 |
ponies | -0.209 |
Token | ts |
Token ID | 912 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
orse | +0.805 |
uddy | +0.692 |
weapon | +0.691 |
oc | +0.674 |
bone | +0.663 |
Neg logit contributions | |
groom | -0.718 |
roses | -0.672 |
decides | -0.618 |
register | -0.607 |
ponies | -0.603 |
Token | on |
Token ID | 319 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
orse | +0.242 |
weapon | +0.196 |
oc | +0.195 |
uddy | +0.190 |
bone | +0.188 |
Neg logit contributions | |
groom | -0.209 |
roses | -0.194 |
register | -0.184 |
decides | -0.183 |
ponies | -0.179 |
Token | the |
Token ID | 262 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
groom | +0.139 |
roses | +0.129 |
decides | +0.119 |
register | +0.118 |
ponies | +0.117 |
Neg logit contributions | |
orse | -0.203 |
weapon | -0.165 |
oc | -0.164 |
uddy | -0.160 |
unch | -0.156 |
Token | water |
Token ID | 1660 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
groom | +0.001 |
roses | +0.000 |
register | +0.000 |
decides | +0.000 |
ponies | +0.000 |
Neg logit contributions | |
orse | -0.001 |
oc | -0.000 |
weapon | -0.000 |
uddy | -0.000 |
unch | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
groom | +0.176 |
roses | +0.164 |
register | +0.158 |
decides | +0.156 |
ponies | +0.151 |
Neg logit contributions | |
orse | -0.185 |
oc | -0.145 |
weapon | -0.145 |
uddy | -0.138 |
bone | -0.138 |
Token | so |
Token ID | 523 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
orse | +0.125 |
ggy | +0.089 |
weapon | +0.087 |
Carl | +0.084 |
unch | +0.083 |
Neg logit contributions | |
groom | -0.149 |
roses | -0.144 |
register | -0.141 |
decides | -0.140 |
ponies | -0.136 |
Token | proud |
Token ID | 6613 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
orse | +0.055 |
oc | +0.040 |
weapon | +0.040 |
ggy | +0.038 |
unch | +0.037 |
Neg logit contributions | |
groom | -0.069 |
roses | -0.066 |
register | -0.065 |
decides | -0.063 |
ponies | -0.062 |
Token | of |
Token ID | 286 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
orse | +0.011 |
oc | +0.009 |
weapon | +0.009 |
puck | +0.009 |
uddy | +0.009 |
Neg logit contributions | |
roses | -0.010 |
groom | -0.009 |
ponies | -0.009 |
register | -0.008 |
decides | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
orse | +0.214 |
Carl | +0.186 |
weapon | +0.183 |
Andy | +0.183 |
ggy | +0.180 |
Neg logit contributions | |
groom | -0.062 |
register | -0.046 |
decides | -0.045 |
roses | -0.044 |
ponies | -0.036 |
Token | new |
Token ID | 649 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
groom | +0.321 |
roses | +0.300 |
decides | +0.273 |
bride | +0.273 |
ponies | +0.272 |
Neg logit contributions | |
orse | -0.352 |
uddy | -0.309 |
oc | -0.304 |
Andy | -0.299 |
Joe | -0.291 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
orse | +0.091 |
uddy | +0.074 |
oc | +0.070 |
inations | +0.069 |
unch | +0.068 |
Neg logit contributions | |
groom | -0.092 |
roses | -0.085 |
ponies | -0.079 |
decides | -0.079 |
bride | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
orse | +0.870 |
oc | +0.677 |
weapon | +0.673 |
puck | +0.657 |
unch | +0.651 |
Neg logit contributions | |
groom | -0.655 |
roses | -0.622 |
register | -0.618 |
ponies | -0.587 |
decides | -0.573 |
Token | she |
Token ID | 673 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
orse | +0.039 |
weapon | +0.032 |
oc | +0.032 |
bone | +0.030 |
uddy | +0.030 |
Neg logit contributions | |
groom | -0.026 |
roses | -0.023 |
register | -0.022 |
decides | -0.022 |
ponies | -0.021 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
groom | +0.243 |
roses | +0.221 |
decides | +0.215 |
register | +0.214 |
ponies | +0.204 |
Neg logit contributions | |
orse | -0.273 |
weapon | -0.219 |
oc | -0.217 |
uddy | -0.207 |
bone | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
orse | +0.020 |
weapon | +0.016 |
oc | +0.015 |
bone | +0.015 |
Carl | +0.015 |
Neg logit contributions | |
groom | -0.020 |
roses | -0.019 |
register | -0.018 |
decides | -0.018 |
ponies | -0.017 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
orse | +0.086 |
weapon | +0.069 |
oc | +0.069 |
bone | +0.065 |
uddy | +0.065 |
Neg logit contributions | |
groom | -0.067 |
roses | -0.062 |
register | -0.060 |
decides | -0.059 |
ponies | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
orse | +0.067 |
weapon | +0.055 |
oc | +0.055 |
bone | +0.053 |
uddy | +0.052 |
Neg logit contributions | |
groom | -0.040 |
roses | -0.036 |
register | -0.035 |
decides | -0.034 |
ponies | -0.033 |
Token | thankful |
Token ID | 25535 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
groom | +0.007 |
roses | +0.007 |
register | +0.006 |
decides | +0.006 |
ponies | +0.006 |
Neg logit contributions | |
orse | -0.007 |
weapon | -0.006 |
oc | -0.006 |
uddy | -0.006 |
bone | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
orse | +0.075 |
oc | +0.058 |
weapon | +0.058 |
bone | +0.055 |
uddy | +0.054 |
Neg logit contributions | |
groom | -0.070 |
roses | -0.065 |
register | -0.063 |
decides | -0.062 |
ponies | -0.060 |
Token | her |
Token ID | 607 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
orse | +0.288 |
weapon | +0.236 |
Carl | +0.231 |
Andy | +0.230 |
oc | +0.230 |
Neg logit contributions | |
groom | -0.173 |
decides | -0.159 |
roses | -0.153 |
register | -0.148 |
ponies | -0.140 |
Token | incredible |
Token ID | 8082 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
groom | +0.349 |
roses | +0.340 |
register | +0.312 |
ponies | +0.311 |
decides | +0.309 |
Neg logit contributions | |
orse | -0.333 |
oc | -0.266 |
puck | -0.246 |
weapon | -0.244 |
uddy | -0.243 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
orse | +0.209 |
oc | +0.153 |
weapon | +0.142 |
uddy | +0.136 |
unch | +0.134 |
Neg logit contributions | |
groom | -0.329 |
roses | -0.316 |
decides | -0.298 |
ponies | -0.296 |
register | -0.291 |
Token | . |
Token ID | 13 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
orse | +0.791 |
weapon | +0.613 |
oc | +0.613 |
puck | +0.579 |
unch | +0.572 |
Neg logit contributions | |
groom | -0.742 |
roses | -0.698 |
register | -0.681 |
decides | -0.657 |
ponies | -0.649 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
orse | +0.052 |
weapon | +0.040 |
oc | +0.039 |
bone | +0.037 |
puck | +0.036 |
Neg logit contributions | |
groom | -0.063 |
roses | -0.059 |
register | -0.058 |
decides | -0.057 |
ponies | -0.056 |
Token | M |
Token ID | 44 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
orse | +0.429 |
weapon | +0.350 |
oc | +0.343 |
oy | +0.329 |
ggy | +0.328 |
Neg logit contributions | |
groom | -0.262 |
roses | -0.246 |
register | -0.239 |
decides | -0.234 |
ponies | -0.225 |
Token | ummy |
Token ID | 13513 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
groom | +0.134 |
roses | +0.127 |
register | +0.125 |
decides | +0.120 |
ponies | +0.119 |
Neg logit contributions | |
orse | -0.138 |
weapon | -0.115 |
oc | -0.112 |
puck | -0.108 |
bone | -0.104 |
Token | was |
Token ID | 373 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
orse | +0.278 |
weapon | +0.216 |
oc | +0.216 |
bone | +0.205 |
Carl | +0.203 |
Neg logit contributions | |
groom | -0.267 |
roses | -0.248 |
register | -0.245 |
decides | -0.237 |
ponies | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
orse | +0.056 |
puck | +0.046 |
weapon | +0.045 |
unch | +0.045 |
uddy | +0.045 |
Neg logit contributions | |
groom | -0.040 |
roses | -0.038 |
register | -0.036 |
decides | -0.035 |
ponies | -0.033 |
Token | The |
Token ID | 383 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
orse | +0.023 |
weapon | +0.018 |
ggy | +0.017 |
oc | +0.017 |
inations | +0.017 |
Neg logit contributions | |
groom | -0.023 |
roses | -0.022 |
decides | -0.022 |
register | -0.021 |
ponies | -0.021 |
Token | cater |
Token ID | 20825 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
orse | +0.170 |
weapon | +0.132 |
oc | +0.130 |
bone | +0.124 |
Carl | +0.122 |
Neg logit contributions | |
groom | -0.179 |
roses | -0.166 |
register | -0.163 |
decides | -0.160 |
ponies | -0.156 |
Token | pillar |
Token ID | 41643 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
orse | +0.204 |
weapon | +0.160 |
oc | +0.154 |
bone | +0.151 |
puck | +0.150 |
Neg logit contributions | |
groom | -0.191 |
roses | -0.180 |
register | -0.174 |
decides | -0.172 |
ponies | -0.167 |
Token | happily |
Token ID | 18177 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
orse | +0.053 |
weapon | +0.044 |
uddy | +0.042 |
unch | +0.042 |
oc | +0.041 |
Neg logit contributions | |
groom | -0.050 |
roses | -0.046 |
decides | -0.045 |
register | -0.043 |
Angel | -0.041 |
Token | mun |
Token ID | 29856 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
groom | +0.116 |
roses | +0.107 |
decides | +0.104 |
register | +0.102 |
ponies | +0.097 |
Neg logit contributions | |
orse | -0.110 |
weapon | -0.088 |
oc | -0.085 |
uddy | -0.082 |
bone | -0.081 |
Token | ched |
Token ID | 1740 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
orse | +0.646 |
oc | +0.477 |
weapon | +0.467 |
bone | +0.439 |
Benny | +0.436 |
Neg logit contributions | |
groom | -0.896 |
roses | -0.833 |
ponies | -0.809 |
register | -0.804 |
decides | -0.798 |
Token | on |
Token ID | 319 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
groom | +0.015 |
roses | +0.014 |
decides | +0.013 |
register | +0.013 |
ponies | +0.012 |
Neg logit contributions | |
orse | -0.030 |
weapon | -0.024 |
oc | -0.024 |
unch | -0.023 |
uddy | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
groom | +0.131 |
roses | +0.123 |
decides | +0.115 |
register | +0.109 |
her | +0.108 |
Neg logit contributions | |
orse | -0.187 |
uddy | -0.152 |
weapon | -0.151 |
oc | -0.150 |
unch | -0.148 |
Token | mushroom |
Token ID | 28520 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
orse | +0.009 |
oc | +0.007 |
weapon | +0.007 |
uddy | +0.006 |
unch | +0.006 |
Neg logit contributions | |
groom | -0.009 |
roses | -0.008 |
register | -0.008 |
decides | -0.008 |
ponies | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
orse | +0.019 |
ggy | +0.015 |
weapon | +0.015 |
oc | +0.015 |
uddy | +0.015 |
Neg logit contributions | |
groom | -0.013 |
roses | -0.013 |
register | -0.012 |
decides | -0.011 |
als | -0.011 |
Token | played |
Token ID | 2826 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
groom | +0.025 |
roses | +0.023 |
decides | +0.022 |
ponies | +0.022 |
register | +0.021 |
Neg logit contributions | |
orse | -0.025 |
weapon | -0.021 |
oc | -0.021 |
uddy | -0.019 |
ggy | -0.019 |
Token | tag |
Token ID | 7621 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
orse | +0.195 |
oc | +0.151 |
weapon | +0.151 |
uddy | +0.148 |
unch | +0.145 |
Neg logit contributions | |
groom | -0.169 |
roses | -0.159 |
ponies | -0.149 |
register | -0.147 |
decides | -0.146 |
Token | and |
Token ID | 290 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
orse | +0.118 |
weapon | +0.093 |
oc | +0.091 |
unch | +0.090 |
uddy | +0.087 |
Neg logit contributions | |
groom | -0.087 |
roses | -0.082 |
ponies | -0.077 |
register | -0.077 |
decides | -0.075 |
Token | shared |
Token ID | 4888 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
orse | +0.011 |
oc | +0.009 |
weapon | +0.009 |
unch | +0.009 |
uddy | +0.008 |
Neg logit contributions | |
groom | -0.012 |
roses | -0.011 |
decides | -0.011 |
ponies | -0.011 |
register | -0.010 |
Token | their |
Token ID | 511 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
groom | +0.061 |
roses | +0.057 |
ponies | +0.053 |
decides | +0.052 |
register | +0.051 |
Neg logit contributions | |
orse | -0.075 |
weapon | -0.060 |
oc | -0.057 |
uddy | -0.057 |
unch | -0.057 |
Token | lun |
Token ID | 14678 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
orse | +0.030 |
unch | +0.023 |
weapon | +0.023 |
oc | +0.023 |
uddy | +0.022 |
Neg logit contributions | |
roses | -0.027 |
groom | -0.026 |
ponies | -0.025 |
decides | -0.024 |
register | -0.022 |
Token | ches |
Token ID | 2052 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
orse | +0.844 |
weapon | +0.673 |
oc | +0.669 |
bone | +0.637 |
uddy | +0.629 |
Neg logit contributions | |
groom | -0.694 |
roses | -0.639 |
register | -0.621 |
decides | -0.611 |
ponies | -0.591 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
groom | +0.048 |
roses | +0.044 |
register | +0.043 |
ponies | +0.042 |
decides | +0.041 |
Neg logit contributions | |
orse | -0.060 |
weapon | -0.047 |
oc | -0.047 |
unch | -0.045 |
uddy | -0.044 |
Token | Molly |
Token ID | 30236 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
orse | +0.040 |
weapon | +0.032 |
oc | +0.030 |
bone | +0.029 |
puck | +0.029 |
Neg logit contributions | |
groom | -0.041 |
roses | -0.038 |
decides | -0.038 |
register | -0.037 |
ponies | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
orse | +0.038 |
weapon | +0.031 |
oc | +0.030 |
bone | +0.028 |
unch | +0.028 |
Neg logit contributions | |
groom | -0.038 |
roses | -0.035 |
decides | -0.035 |
register | -0.034 |
ponies | -0.033 |
Token | fair |
Token ID | 3148 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
orse | +0.286 |
oc | +0.240 |
weapon | +0.230 |
uddy | +0.223 |
unch | +0.222 |
Neg logit contributions | |
groom | -0.217 |
roses | -0.194 |
decides | -0.188 |
register | -0.182 |
ponies | -0.180 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
register | +0.041 |
groom | +0.038 |
pan | +0.038 |
Elsa | +0.035 |
Elsa | +0.035 |
Neg logit contributions | |
orse | -0.043 |
crocod | -0.040 |
discovery | -0.039 |
oc | -0.039 |
weapon | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
groom | +0.189 |
roses | +0.176 |
decides | +0.173 |
register | +0.168 |
ponies | +0.163 |
Neg logit contributions | |
orse | -0.178 |
weapon | -0.141 |
oc | -0.135 |
bone | -0.133 |
uddy | -0.132 |
Token | overwhelmed |
Token ID | 20974 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
orse | +0.134 |
weapon | +0.101 |
oc | +0.100 |
ggy | +0.096 |
Carl | +0.095 |
Neg logit contributions | |
groom | -0.142 |
roses | -0.133 |
register | -0.131 |
decides | -0.128 |
ponies | -0.125 |
Token | with |
Token ID | 351 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
groom | +0.023 |
roses | +0.022 |
register | +0.020 |
ponies | +0.020 |
decides | +0.020 |
Neg logit contributions | |
orse | -0.028 |
weapon | -0.021 |
puck | -0.021 |
oc | -0.021 |
uddy | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
orse | +0.330 |
weapon | +0.261 |
oc | +0.259 |
bone | +0.246 |
uddy | +0.244 |
Neg logit contributions | |
groom | -0.287 |
roses | -0.265 |
register | -0.257 |
decides | -0.254 |
ponies | -0.246 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
orse | +0.030 |
weapon | +0.024 |
crocod | +0.022 |
oc | +0.022 |
bone | +0.022 |
Neg logit contributions | |
groom | -0.033 |
register | -0.032 |
decides | -0.030 |
roses | -0.030 |
nurses | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
orse | +0.829 |
oc | +0.650 |
weapon | +0.642 |
puck | +0.615 |
unch | +0.614 |
Neg logit contributions | |
groom | -0.697 |
roses | -0.662 |
register | -0.643 |
decides | -0.616 |
ponies | -0.610 |
Token | She |
Token ID | 1375 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
orse | +0.066 |
His | +0.058 |
Andy | +0.058 |
Carl | +0.058 |
Benny | +0.057 |
Neg logit contributions | |
groom | -0.043 |
roses | -0.036 |
register | -0.035 |
bride | -0.033 |
ponies | -0.031 |
Token | protected |
Token ID | 6861 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
groom | +0.297 |
roses | +0.275 |
register | +0.268 |
decides | +0.265 |
ponies | +0.256 |
Neg logit contributions | |
orse | -0.302 |
weapon | -0.236 |
oc | -0.234 |
bone | -0.222 |
uddy | -0.219 |
Token | the |
Token ID | 262 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
orse | +0.255 |
Carl | +0.218 |
weapon | +0.218 |
Andy | +0.216 |
Benny | +0.211 |
Neg logit contributions | |
groom | -0.152 |
register | -0.137 |
decides | -0.134 |
roses | -0.129 |
ponies | -0.121 |
Token | nest |
Token ID | 16343 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
orse | +0.034 |
weapon | +0.026 |
crocod | +0.026 |
oc | +0.025 |
bone | +0.025 |
Neg logit contributions | |
register | -0.037 |
groom | -0.037 |
decides | -0.034 |
nurses | -0.033 |
Elsa | -0.033 |
Token | little |
Token ID | 1310 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
orse | +0.182 |
weapon | +0.150 |
oc | +0.147 |
bone | +0.145 |
ggy | +0.140 |
Neg logit contributions | |
groom | -0.149 |
roses | -0.139 |
decides | -0.137 |
register | -0.131 |
ponies | -0.130 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
orse | +0.119 |
weapon | +0.107 |
bone | +0.106 |
oc | +0.105 |
crocod | +0.102 |
Neg logit contributions | |
groom | -0.071 |
decides | -0.066 |
register | -0.064 |
roses | -0.063 |
ponies | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
groom | +0.214 |
roses | +0.194 |
decides | +0.193 |
register | +0.183 |
ponies | +0.175 |
Neg logit contributions | |
orse | -0.206 |
weapon | -0.173 |
unch | -0.160 |
uddy | -0.160 |
bone | -0.156 |
Token | thrilled |
Token ID | 20536 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
orse | +0.108 |
weapon | +0.082 |
oc | +0.082 |
bone | +0.078 |
ggy | +0.078 |
Neg logit contributions | |
groom | -0.109 |
roses | -0.102 |
register | -0.100 |
decides | -0.099 |
ponies | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
orse | +0.108 |
oc | +0.089 |
weapon | +0.086 |
puck | +0.084 |
uddy | +0.082 |
Neg logit contributions | |
groom | -0.074 |
roses | -0.070 |
register | -0.067 |
decides | -0.064 |
ponies | -0.064 |
Token | mun |
Token ID | 29856 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
groom | +0.001 |
roses | +0.001 |
register | +0.001 |
decides | +0.001 |
ponies | +0.001 |
Neg logit contributions | |
orse | -0.001 |
weapon | -0.001 |
oc | -0.001 |
bone | -0.001 |
uddy | -0.001 |
Token | ched |
Token ID | 1740 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
orse | +0.623 |
oc | +0.455 |
weapon | +0.428 |
hockey | +0.416 |
ggy | +0.415 |
Neg logit contributions | |
groom | -0.903 |
roses | -0.853 |
decides | -0.827 |
ponies | -0.826 |
register | -0.817 |
Token | away |
Token ID | 1497 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
groom | +0.018 |
register | +0.015 |
roses | +0.015 |
decides | +0.015 |
ponies | +0.014 |
Neg logit contributions | |
orse | -0.030 |
oc | -0.026 |
weapon | -0.026 |
bone | -0.025 |
Carl | -0.025 |
Token | happily |
Token ID | 18177 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
groom | +0.179 |
roses | +0.164 |
register | +0.161 |
decides | +0.160 |
ponies | +0.152 |
Neg logit contributions | |
orse | -0.213 |
weapon | -0.170 |
oc | -0.169 |
bone | -0.162 |
Carl | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
groom | +0.096 |
register | +0.088 |
roses | +0.087 |
ponies | +0.082 |
decides | +0.079 |
Neg logit contributions | |
orse | -0.126 |
weapon | -0.105 |
oc | -0.101 |
puck | -0.099 |
uddy | -0.098 |
Token | |
Token ID | 220 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
orse | +0.027 |
His | +0.024 |
Benny | +0.023 |
Andy | +0.022 |
oc | +0.022 |
Neg logit contributions | |
groom | -0.026 |
register | -0.023 |
roses | -0.023 |
pan | -0.022 |
nurses | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
groom | +0.217 |
decides | +0.193 |
register | +0.193 |
roses | +0.193 |
ponies | +0.183 |
Neg logit contributions | |
orse | -0.304 |
hockey | -0.257 |
weapon | -0.253 |
fishing | -0.253 |
Benny | -0.249 |
Token | broom |
Token ID | 47085 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
groom | +0.022 |
roses | +0.020 |
register | +0.019 |
decides | +0.019 |
ponies | +0.018 |
Neg logit contributions | |
orse | -0.027 |
oc | -0.021 |
weapon | -0.021 |
oy | -0.020 |
uddy | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
groom | +0.244 |
roses | +0.225 |
decides | +0.223 |
register | +0.223 |
ponies | +0.212 |
Neg logit contributions | |
orse | -0.227 |
weapon | -0.182 |
oc | -0.179 |
bone | -0.171 |
uddy | -0.166 |
Token | a |
Token ID | 257 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
groom | +0.031 |
register | +0.031 |
roses | +0.028 |
ponies | +0.027 |
decides | +0.027 |
Neg logit contributions | |
orse | -0.031 |
weapon | -0.025 |
bone | -0.024 |
Andy | -0.023 |
puck | -0.023 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.019 |
decides | +0.019 |
register | +0.019 |
ponies | +0.018 |
Neg logit contributions | |
orse | -0.028 |
weapon | -0.023 |
oc | -0.022 |
bone | -0.022 |
hockey | -0.021 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
groom | +0.028 |
decides | +0.024 |
register | +0.023 |
roses | +0.022 |
ponies | +0.021 |
Neg logit contributions | |
orse | -0.116 |
weapon | -0.102 |
oc | -0.099 |
bone | -0.098 |
ggy | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
groom | +0.875 |
roses | +0.812 |
register | +0.785 |
decides | +0.777 |
ponies | +0.747 |
Neg logit contributions | |
orse | -0.958 |
weapon | -0.755 |
oc | -0.752 |
bone | -0.709 |
Carl | -0.704 |
Token | start |
Token ID | 923 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
groom | +0.033 |
register | +0.032 |
roses | +0.029 |
ponies | +0.029 |
decides | +0.028 |
Neg logit contributions | |
orse | -0.031 |
weapon | -0.025 |
bone | -0.024 |
Andy | -0.023 |
hockey | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
groom | +0.224 |
roses | +0.211 |
register | +0.198 |
decides | +0.196 |
ponies | +0.192 |
Neg logit contributions | |
orse | -0.277 |
oc | -0.222 |
weapon | -0.220 |
uddy | -0.208 |
unch | -0.207 |
Token | clean |
Token ID | 3424 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.007 |
oc | +0.007 |
bone | +0.007 |
ggy | +0.007 |
Neg logit contributions | |
groom | -0.007 |
register | -0.007 |
roses | -0.007 |
decides | -0.006 |
ponies | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
orse | +0.026 |
oc | +0.022 |
weapon | +0.022 |
hockey | +0.021 |
Carl | +0.021 |
Neg logit contributions | |
groom | -0.017 |
register | -0.015 |
decides | -0.015 |
roses | -0.015 |
ponies | -0.014 |
Token | m |
Token ID | 285 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.019 |
register | +0.019 |
decides | +0.018 |
ponies | +0.017 |
Neg logit contributions | |
orse | -0.029 |
oc | -0.023 |
weapon | -0.023 |
oy | -0.022 |
Carl | -0.022 |
Token | op |
Token ID | 404 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
groom | +0.385 |
register | +0.380 |
roses | +0.362 |
salon | +0.335 |
nurses | +0.331 |
Neg logit contributions | |
orse | -0.356 |
weapon | -0.310 |
Benny | -0.301 |
Carl | -0.298 |
Freddy | -0.293 |
Token | and |
Token ID | 290 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
orse | +0.210 |
weapon | +0.167 |
oc | +0.165 |
bone | +0.158 |
Carl | +0.154 |
Neg logit contributions | |
groom | -0.213 |
roses | -0.194 |
decides | -0.190 |
register | -0.189 |
ponies | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
groom | +0.030 |
roses | +0.027 |
register | +0.027 |
decides | +0.026 |
ponies | +0.026 |
Neg logit contributions | |
orse | -0.035 |
weapon | -0.028 |
oc | -0.027 |
bone | -0.027 |
puck | -0.026 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.019 |
register | +0.019 |
decides | +0.018 |
ponies | +0.017 |
Neg logit contributions | |
orse | -0.029 |
oc | -0.023 |
weapon | -0.023 |
oy | -0.022 |
Carl | -0.022 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
groom | +0.027 |
roses | +0.022 |
decides | +0.021 |
register | +0.021 |
ponies | +0.018 |
Neg logit contributions | |
orse | -0.117 |
weapon | -0.102 |
oc | -0.101 |
bone | -0.099 |
ggy | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
groom | +0.746 |
roses | +0.694 |
register | +0.667 |
decides | +0.656 |
ponies | +0.619 |
Neg logit contributions | |
orse | -1.066 |
weapon | -0.862 |
oc | -0.858 |
Carl | -0.822 |
puck | -0.816 |
Token | cleaned |
Token ID | 20750 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
groom | +0.029 |
register | +0.027 |
roses | +0.027 |
decides | +0.026 |
ponies | +0.026 |
Neg logit contributions | |
orse | -0.033 |
weapon | -0.026 |
oc | -0.025 |
bone | -0.025 |
puck | -0.024 |
Token | up |
Token ID | 510 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
groom | +0.077 |
roses | +0.068 |
register | +0.067 |
decides | +0.065 |
ponies | +0.063 |
Neg logit contributions | |
orse | -0.118 |
oc | -0.098 |
weapon | -0.097 |
bone | -0.094 |
Carl | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
groom | +0.248 |
roses | +0.234 |
register | +0.222 |
decides | +0.214 |
ponies | +0.210 |
Neg logit contributions | |
orse | -0.386 |
weapon | -0.313 |
oc | -0.308 |
unch | -0.300 |
uddy | -0.298 |
Token | dough |
Token ID | 15756 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
groom | +0.025 |
roses | +0.023 |
register | +0.023 |
decides | +0.022 |
ponies | +0.022 |
Neg logit contributions | |
orse | -0.025 |
weapon | -0.020 |
oc | -0.020 |
bone | -0.019 |
hockey | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
groom | +0.268 |
register | +0.240 |
roses | +0.239 |
decides | +0.232 |
ponies | +0.232 |
Neg logit contributions | |
orse | -0.284 |
weapon | -0.225 |
Benny | -0.223 |
hockey | -0.220 |
oy | -0.215 |
Token | broom |
Token ID | 47085 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
groom | +0.025 |
roses | +0.023 |
register | +0.022 |
decides | +0.022 |
ponies | +0.021 |
Neg logit contributions | |
orse | -0.026 |
oc | -0.020 |
weapon | -0.020 |
uddy | -0.019 |
Carl | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
groom | +0.250 |
roses | +0.233 |
decides | +0.228 |
register | +0.227 |
ponies | +0.215 |
Neg logit contributions | |
orse | -0.221 |
weapon | -0.181 |
oc | -0.174 |
bone | -0.169 |
hockey | -0.162 |
Token | a |
Token ID | 257 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
groom | +0.033 |
register | +0.032 |
roses | +0.029 |
decides | +0.029 |
la | +0.029 |
Neg logit contributions | |
orse | -0.029 |
weapon | -0.024 |
bone | -0.023 |
Andy | -0.022 |
hockey | -0.022 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
groom | +0.021 |
decides | +0.020 |
register | +0.020 |
roses | +0.020 |
ponies | +0.019 |
Neg logit contributions | |
orse | -0.027 |
weapon | -0.023 |
bone | -0.022 |
oc | -0.021 |
hockey | -0.021 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
groom | +0.049 |
decides | +0.044 |
roses | +0.043 |
register | +0.043 |
ponies | +0.041 |
Neg logit contributions | |
orse | -0.091 |
weapon | -0.081 |
bone | -0.077 |
oc | -0.077 |
hockey | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
groom | +0.894 |
roses | +0.828 |
register | +0.808 |
decides | +0.794 |
ponies | +0.771 |
Neg logit contributions | |
orse | -0.938 |
weapon | -0.735 |
oc | -0.730 |
bone | -0.693 |
uddy | -0.683 |
Token | You |
Token ID | 921 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
groom | +0.007 |
register | +0.006 |
roses | +0.006 |
ponies | +0.006 |
decides | +0.006 |
Neg logit contributions | |
orse | -0.005 |
oc | -0.004 |
weapon | -0.004 |
bone | -0.003 |
Andy | -0.003 |
Token | have |
Token ID | 423 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
orse | +0.280 |
weapon | +0.232 |
oc | +0.227 |
bone | +0.222 |
uddy | +0.212 |
Neg logit contributions | |
groom | -0.213 |
roses | -0.196 |
register | -0.192 |
ponies | -0.183 |
decides | -0.177 |
Token | to |
Token ID | 284 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
orse | +0.075 |
weapon | +0.058 |
bone | +0.056 |
hockey | +0.055 |
ggy | +0.054 |
Neg logit contributions | |
groom | -0.087 |
register | -0.083 |
roses | -0.080 |
decides | -0.077 |
ponies | -0.076 |
Token | clean |
Token ID | 3424 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
orse | +0.012 |
weapon | +0.010 |
oc | +0.009 |
ggy | +0.009 |
bone | +0.009 |
Neg logit contributions | |
groom | -0.010 |
register | -0.009 |
roses | -0.009 |
decides | -0.009 |
ponies | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
orse | +0.131 |
oc | +0.106 |
weapon | +0.101 |
bone | +0.096 |
ggy | +0.096 |
Neg logit contributions | |
groom | -0.127 |
roses | -0.122 |
register | -0.118 |
decides | -0.113 |
ponies | -0.111 |
Token | paper |
Token ID | 3348 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
orse | +0.091 |
oc | +0.073 |
weapon | +0.073 |
uddy | +0.070 |
unch | +0.069 |
Neg logit contributions | |
groom | -0.064 |
roses | -0.059 |
register | -0.056 |
decides | -0.055 |
ponies | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
groom | +0.000 |
roses | +0.000 |
register | +0.000 |
decides | +0.000 |
ponies | +0.000 |
Neg logit contributions | |
orse | -0.000 |
weapon | -0.000 |
oc | -0.000 |
bone | -0.000 |
uddy | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
groom | +0.028 |
register | +0.026 |
roses | +0.026 |
decides | +0.025 |
ponies | +0.024 |
Neg logit contributions | |
orse | -0.033 |
weapon | -0.027 |
oc | -0.025 |
bone | -0.025 |
Carl | -0.024 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.019 |
register | +0.019 |
decides | +0.018 |
ponies | +0.018 |
Neg logit contributions | |
orse | -0.026 |
weapon | -0.021 |
oc | -0.020 |
bone | -0.020 |
uddy | -0.019 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
groom | +0.029 |
roses | +0.023 |
decides | +0.022 |
register | +0.022 |
ponies | +0.020 |
Neg logit contributions | |
orse | -0.112 |
weapon | -0.097 |
oc | -0.096 |
bone | -0.094 |
ggy | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
groom | +0.839 |
roses | +0.787 |
register | +0.760 |
decides | +0.742 |
ponies | +0.716 |
Neg logit contributions | |
orse | -0.987 |
oc | -0.784 |
weapon | -0.775 |
puck | -0.732 |
bone | -0.730 |
Token | they |
Token ID | 484 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
groom | +0.028 |
register | +0.025 |
roses | +0.025 |
decides | +0.024 |
ponies | +0.024 |
Neg logit contributions | |
orse | -0.031 |
weapon | -0.025 |
oc | -0.024 |
bone | -0.024 |
hockey | -0.023 |
Token | cleaned |
Token ID | 20750 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
groom | +0.029 |
roses | +0.027 |
register | +0.027 |
decides | +0.026 |
ponies | +0.026 |
Neg logit contributions | |
orse | -0.026 |
weapon | -0.020 |
oc | -0.020 |
bone | -0.019 |
Carl | -0.018 |
Token | up |
Token ID | 510 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
groom | +0.083 |
register | +0.072 |
decides | +0.072 |
roses | +0.072 |
ponies | +0.069 |
Neg logit contributions | |
orse | -0.101 |
oc | -0.086 |
Carl | -0.085 |
Andy | -0.085 |
weapon | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
groom | +0.290 |
roses | +0.265 |
register | +0.259 |
decides | +0.256 |
ponies | +0.247 |
Neg logit contributions | |
orse | -0.339 |
weapon | -0.270 |
oc | -0.269 |
bone | -0.256 |
Carl | -0.254 |
Token | her |
Token ID | 607 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
orse | +0.306 |
Benny | +0.280 |
Andy | +0.277 |
Tim | +0.275 |
weapon | +0.275 |
Neg logit contributions | |
groom | -0.165 |
decides | -0.151 |
register | -0.149 |
roses | -0.136 |
ponies | -0.129 |
Token | little |
Token ID | 1310 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
groom | +0.269 |
roses | +0.250 |
register | +0.225 |
ponies | +0.220 |
decides | +0.208 |
Neg logit contributions | |
orse | -0.550 |
oc | -0.466 |
weapon | -0.438 |
unch | -0.435 |
oy | -0.432 |
Token | broom |
Token ID | 47085 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
orse | +0.081 |
weapon | +0.067 |
oc | +0.064 |
bone | +0.064 |
hockey | +0.062 |
Neg logit contributions | |
groom | -0.070 |
register | -0.063 |
roses | -0.063 |
decides | -0.062 |
ponies | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
groom | +0.236 |
roses | +0.217 |
register | +0.213 |
decides | +0.212 |
ponies | +0.203 |
Neg logit contributions | |
orse | -0.235 |
weapon | -0.186 |
oc | -0.181 |
bone | -0.174 |
uddy | -0.172 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
groom | +0.028 |
register | +0.026 |
decides | +0.026 |
roses | +0.026 |
ponies | +0.025 |
Neg logit contributions | |
orse | -0.030 |
weapon | -0.024 |
Carl | -0.023 |
Andy | -0.022 |
Benny | -0.022 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
groom | +0.064 |
decides | +0.060 |
register | +0.057 |
roses | +0.057 |
ponies | +0.055 |
Neg logit contributions | |
orse | -0.074 |
weapon | -0.061 |
ggy | -0.058 |
bone | -0.057 |
oc | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
groom | +0.828 |
roses | +0.773 |
register | +0.746 |
decides | +0.725 |
ponies | +0.709 |
Neg logit contributions | |
orse | -1.003 |
oc | -0.799 |
weapon | -0.790 |
bone | -0.746 |
puck | -0.741 |
Token | trying |
Token ID | 2111 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
groom | +0.071 |
register | +0.066 |
roses | +0.066 |
decides | +0.065 |
ponies | +0.063 |
Neg logit contributions | |
orse | -0.055 |
weapon | -0.041 |
oc | -0.040 |
bone | -0.039 |
hockey | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
orse | +0.191 |
weapon | +0.155 |
bone | +0.144 |
hockey | +0.142 |
Carl | +0.141 |
Neg logit contributions | |
groom | -0.231 |
register | -0.212 |
decides | -0.206 |
roses | -0.206 |
ponies | -0.197 |
Token | get |
Token ID | 651 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
orse | +0.013 |
weapon | +0.010 |
ggy | +0.010 |
Carl | +0.009 |
bone | +0.009 |
Neg logit contributions | |
groom | -0.013 |
register | -0.012 |
decides | -0.012 |
ponies | -0.012 |
roses | -0.012 |
Token | all |
Token ID | 477 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
groom | +0.259 |
register | +0.234 |
decides | +0.231 |
roses | +0.227 |
ponies | +0.225 |
Neg logit contributions | |
orse | -0.270 |
weapon | -0.230 |
Benny | -0.220 |
hockey | -0.220 |
bone | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
groom | +0.102 |
register | +0.091 |
decides | +0.090 |
roses | +0.089 |
ponies | +0.085 |
Neg logit contributions | |
orse | -0.111 |
weapon | -0.091 |
bone | -0.088 |
Carl | -0.086 |
hockey | -0.086 |
Token | broom |
Token ID | 47085 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
groom | +0.022 |
roses | +0.020 |
register | +0.020 |
decides | +0.019 |
ponies | +0.019 |
Neg logit contributions | |
orse | -0.025 |
weapon | -0.020 |
oc | -0.020 |
bone | -0.019 |
puck | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
groom | +0.239 |
roses | +0.219 |
decides | +0.217 |
register | +0.213 |
ponies | +0.205 |
Neg logit contributions | |
orse | -0.229 |
weapon | -0.187 |
oc | -0.180 |
bone | -0.175 |
ggy | -0.170 |
Token | a |
Token ID | 257 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
groom | +0.029 |
register | +0.028 |
decides | +0.026 |
roses | +0.026 |
ponies | +0.025 |
Neg logit contributions | |
orse | -0.030 |
weapon | -0.024 |
bone | -0.023 |
Andy | -0.022 |
puck | -0.022 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
groom | +0.019 |
decides | +0.018 |
register | +0.018 |
roses | +0.018 |
ponies | +0.017 |
Neg logit contributions | |
orse | -0.025 |
weapon | -0.021 |
bone | -0.020 |
oc | -0.020 |
puck | -0.019 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
groom | +0.039 |
decides | +0.034 |
roses | +0.033 |
register | +0.032 |
ponies | +0.030 |
Neg logit contributions | |
orse | -0.100 |
weapon | -0.087 |
oc | -0.085 |
bone | -0.084 |
ggy | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
groom | +0.806 |
roses | +0.749 |
register | +0.733 |
decides | +0.709 |
ponies | +0.684 |
Neg logit contributions | |
orse | -1.024 |
oc | -0.814 |
weapon | -0.806 |
Carl | -0.770 |
uddy | -0.762 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
groom | +0.003 |
roses | +0.003 |
decides | +0.003 |
register | +0.003 |
ponies | +0.003 |
Neg logit contributions | |
orse | -0.004 |
weapon | -0.003 |
oc | -0.003 |
oy | -0.003 |
ggy | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
groom | +0.014 |
roses | +0.014 |
decides | +0.013 |
register | +0.013 |
She | +0.013 |
Neg logit contributions | |
orse | -0.017 |
weapon | -0.014 |
oy | -0.013 |
oc | -0.013 |
puck | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
groom | +0.012 |
roses | +0.011 |
register | +0.010 |
decides | +0.010 |
ponies | +0.010 |
Neg logit contributions | |
orse | -0.021 |
weapon | -0.018 |
oc | -0.018 |
bone | -0.017 |
uddy | -0.017 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
groom | +0.225 |
register | +0.216 |
roses | +0.206 |
ponies | +0.204 |
decides | +0.196 |
Neg logit contributions | |
orse | -0.363 |
oc | -0.297 |
puck | -0.294 |
bone | -0.292 |
ggy | -0.292 |
Token | a |
Token ID | 257 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
groom | +0.417 |
roses | +0.374 |
register | +0.369 |
decides | +0.366 |
ponies | +0.347 |
Neg logit contributions | |
orse | -0.520 |
weapon | -0.430 |
bone | -0.417 |
oc | -0.414 |
Carl | -0.411 |
Token | broom |
Token ID | 47085 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
groom | +0.017 |
roses | +0.016 |
register | +0.015 |
decides | +0.015 |
ponies | +0.015 |
Neg logit contributions | |
orse | -0.021 |
weapon | -0.017 |
oc | -0.017 |
bone | -0.016 |
uddy | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
groom | +0.214 |
roses | +0.199 |
register | +0.194 |
decides | +0.188 |
ponies | +0.184 |
Neg logit contributions | |
orse | -0.249 |
weapon | -0.193 |
oc | -0.193 |
Carl | -0.184 |
unch | -0.184 |
Token | a |
Token ID | 257 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
groom | +0.025 |
register | +0.023 |
roses | +0.023 |
decides | +0.022 |
ponies | +0.021 |
Neg logit contributions | |
orse | -0.025 |
weapon | -0.020 |
bone | -0.020 |
hockey | -0.019 |
puck | -0.019 |
Token | dust |
Token ID | 8977 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
groom | +0.016 |
register | +0.015 |
decides | +0.015 |
roses | +0.015 |
ponies | +0.014 |
Neg logit contributions | |
orse | -0.019 |
weapon | -0.016 |
bone | -0.015 |
oc | -0.015 |
hockey | -0.015 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
groom | +0.030 |
roses | +0.026 |
decides | +0.025 |
register | +0.025 |
ponies | +0.022 |
Neg logit contributions | |
orse | -0.099 |
weapon | -0.086 |
oc | -0.084 |
bone | -0.083 |
puck | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
groom | +0.813 |
roses | +0.757 |
register | +0.732 |
decides | +0.721 |
ponies | +0.688 |
Neg logit contributions | |
orse | -0.994 |
oc | -0.791 |
weapon | -0.789 |
Carl | -0.753 |
uddy | -0.743 |
Token | They |
Token ID | 1119 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
orse | +0.001 |
weapon | +0.001 |
oc | +0.001 |
bone | +0.001 |
uddy | +0.000 |
Neg logit contributions | |
groom | -0.002 |
roses | -0.002 |
register | -0.002 |
decides | -0.002 |
ponies | -0.002 |
Token | help |
Token ID | 1037 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
orse | +0.041 |
weapon | +0.034 |
oc | +0.033 |
bone | +0.033 |
Carl | +0.031 |
Neg logit contributions | |
groom | -0.045 |
register | -0.042 |
roses | -0.041 |
ponies | -0.040 |
decides | -0.039 |
Token | him |
Token ID | 683 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
groom | +0.157 |
roses | +0.141 |
decides | +0.141 |
register | +0.140 |
ponies | +0.132 |
Neg logit contributions | |
orse | -0.215 |
Carl | -0.180 |
ggy | -0.177 |
hockey | -0.176 |
bone | -0.175 |
Token | sweep |
Token ID | 16085 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
orse | +0.202 |
weapon | +0.162 |
oc | +0.157 |
bone | +0.154 |
ggy | +0.154 |
Neg logit contributions | |
groom | -0.198 |
register | -0.180 |
roses | -0.178 |
ponies | -0.174 |
decides | -0.173 |
Token | a |
Token ID | 257 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
groom | +0.252 |
roses | +0.224 |
decides | +0.223 |
ponies | +0.217 |
register | +0.214 |
Neg logit contributions | |
orse | -0.249 |
Tim | -0.224 |
Benny | -0.221 |
weapon | -0.215 |
Andy | -0.215 |
Token | broom |
Token ID | 47085 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
groom | +0.010 |
roses | +0.009 |
register | +0.009 |
decides | +0.008 |
ponies | +0.008 |
Neg logit contributions | |
orse | -0.012 |
oc | -0.010 |
weapon | -0.009 |
oy | -0.009 |
Carl | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
groom | +0.237 |
roses | +0.221 |
decides | +0.218 |
register | +0.213 |
ponies | +0.204 |
Neg logit contributions | |
orse | -0.205 |
weapon | -0.168 |
oc | -0.164 |
bone | -0.159 |
hockey | -0.149 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
groom | +0.018 |
register | +0.017 |
roses | +0.016 |
decides | +0.016 |
ponies | +0.016 |
Neg logit contributions | |
orse | -0.015 |
weapon | -0.013 |
bone | -0.012 |
Andy | -0.012 |
hockey | -0.012 |
Token | dust |
Token ID | 8977 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.008 |
register | +0.008 |
decides | +0.008 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.011 |
weapon | -0.009 |
oc | -0.009 |
bone | -0.009 |
uddy | -0.009 |
Token | pan |
Token ID | 6839 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.023 |
decides | +0.022 |
roses | +0.019 |
register | +0.018 |
ponies | +0.017 |
Neg logit contributions | |
orse | -0.087 |
weapon | -0.079 |
bone | -0.076 |
oc | -0.076 |
hockey | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
groom | +0.953 |
roses | +0.883 |
register | +0.863 |
decides | +0.852 |
ponies | +0.830 |
Neg logit contributions | |
orse | -0.849 |
weapon | -0.654 |
oc | -0.648 |
bone | -0.620 |
ggy | -0.606 |
Token | clean |
Token ID | 3424 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
orse | +0.028 |
weapon | +0.023 |
oc | +0.022 |
bone | +0.022 |
ggy | +0.022 |
Neg logit contributions | |
groom | -0.024 |
register | -0.022 |
decides | -0.022 |
roses | -0.022 |
ponies | -0.021 |
Token | up |
Token ID | 510 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
orse | +0.036 |
oc | +0.030 |
weapon | +0.030 |
bone | +0.029 |
hockey | +0.029 |
Neg logit contributions | |
groom | -0.042 |
decides | -0.037 |
register | -0.037 |
roses | -0.036 |
ponies | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
groom | +0.306 |
roses | +0.280 |
register | +0.275 |
decides | +0.274 |
ponies | +0.262 |
Neg logit contributions | |
orse | -0.296 |
weapon | -0.232 |
oc | -0.231 |
bone | -0.220 |
Carl | -0.216 |
Token | mess |
Token ID | 2085 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.007 |
register | +0.007 |
decides | +0.007 |
ponies | +0.006 |
Neg logit contributions | |
orse | -0.009 |
weapon | -0.007 |
oc | -0.007 |
bone | -0.007 |
hockey | -0.006 |
Token | word |
Token ID | 1573 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
orse | +0.030 |
unch | +0.023 |
orses | +0.023 |
oy | +0.022 |
inations | +0.022 |
Neg logit contributions | |
groom | -0.023 |
roses | -0.021 |
mirror | -0.020 |
decides | -0.020 |
ponies | -0.019 |
Token | : |
Token ID | 25 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
orse | +0.042 |
weapon | +0.033 |
oc | +0.032 |
bone | +0.031 |
ggy | +0.030 |
Neg logit contributions | |
groom | -0.048 |
roses | -0.044 |
register | -0.043 |
decides | -0.043 |
ponies | -0.041 |
Token | pin |
Token ID | 6757 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
groom | +0.210 |
roses | +0.194 |
register | +0.190 |
decides | +0.186 |
ponies | +0.180 |
Neg logit contributions | |
orse | -0.220 |
weapon | -0.172 |
oc | -0.171 |
bone | -0.162 |
Carl | -0.160 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
orse | +0.244 |
weapon | +0.191 |
oc | +0.189 |
bone | +0.178 |
ggy | +0.176 |
Neg logit contributions | |
groom | -0.268 |
roses | -0.248 |
register | -0.243 |
decides | -0.237 |
ponies | -0.232 |
Token | He |
Token ID | 679 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
groom | +0.009 |
roses | +0.008 |
decides | +0.008 |
register | +0.008 |
Angel | +0.008 |
Neg logit contributions | |
orse | -0.006 |
weapon | -0.005 |
oc | -0.005 |
oy | -0.004 |
ggy | -0.004 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
orse | +0.305 |
oc | +0.252 |
weapon | +0.252 |
bone | +0.241 |
puck | +0.239 |
Neg logit contributions | |
groom | -0.222 |
register | -0.206 |
roses | -0.204 |
ponies | -0.188 |
nurses | -0.181 |
Token | not |
Token ID | 407 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
groom | +0.804 |
roses | +0.748 |
decides | +0.710 |
register | +0.705 |
ponies | +0.690 |
Neg logit contributions | |
orse | -1.004 |
oc | -0.813 |
weapon | -0.793 |
uddy | -0.769 |
unch | -0.762 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
orse | +0.157 |
oc | +0.135 |
uddy | +0.125 |
oy | +0.124 |
ggy | +0.124 |
Neg logit contributions | |
groom | -0.102 |
decides | -0.094 |
roses | -0.092 |
ponies | -0.085 |
register | -0.080 |
Token | play |
Token ID | 711 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.007 |
oc | +0.007 |
bone | +0.007 |
uddy | +0.007 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.007 |
register | -0.007 |
decides | -0.006 |
ponies | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
orse | +0.123 |
weapon | +0.091 |
oc | +0.091 |
uddy | +0.086 |
bone | +0.085 |
Neg logit contributions | |
groom | -0.151 |
roses | -0.141 |
register | -0.138 |
decides | -0.136 |
ponies | -0.132 |
Token | pins |
Token ID | 20567 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
orse | +0.262 |
oc | +0.205 |
weapon | +0.203 |
unch | +0.195 |
uddy | +0.195 |
Neg logit contributions | |
groom | -0.232 |
roses | -0.218 |
register | -0.208 |
decides | -0.205 |
ponies | -0.200 |
Token | for |
Token ID | 329 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
groom | +0.257 |
roses | +0.241 |
register | +0.234 |
decides | +0.231 |
ponies | +0.224 |
Neg logit contributions | |
orse | -0.277 |
weapon | -0.215 |
oc | -0.215 |
bone | -0.203 |
ggy | -0.201 |
Token | the |
Token ID | 262 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
orse | +0.193 |
weapon | +0.155 |
oc | +0.153 |
bone | +0.147 |
Carl | +0.146 |
Neg logit contributions | |
groom | -0.151 |
roses | -0.138 |
register | -0.135 |
decides | -0.133 |
ponies | -0.128 |
Token | elephant |
Token ID | 20950 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
groom | +0.024 |
roses | +0.022 |
register | +0.021 |
decides | +0.021 |
ponies | +0.021 |
Neg logit contributions | |
orse | -0.034 |
unch | -0.026 |
oc | -0.026 |
weapon | -0.025 |
puck | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
groom | +0.031 |
register | +0.029 |
roses | +0.029 |
ponies | +0.028 |
decides | +0.027 |
Neg logit contributions | |
orse | -0.045 |
unch | -0.035 |
weapon | -0.035 |
puck | -0.035 |
oy | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.008 |
register | +0.008 |
decides | +0.007 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.007 |
oc | -0.005 |
weapon | -0.005 |
bone | -0.005 |
Carl | -0.005 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.310 |
register | +0.288 |
roses | +0.282 |
pan | +0.259 |
ponies | +0.257 |
Neg logit contributions | |
orse | -0.404 |
weapon | -0.344 |
oc | -0.335 |
bone | -0.332 |
puck | -0.316 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
groom | +0.854 |
roses | +0.792 |
register | +0.765 |
decides | +0.757 |
ponies | +0.734 |
Neg logit contributions | |
orse | -0.956 |
weapon | -0.754 |
oc | -0.753 |
bone | -0.711 |
uddy | -0.705 |
Token | teach |
Token ID | 4545 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
orse | +0.011 |
weapon | +0.009 |
oc | +0.008 |
bone | +0.008 |
uddy | +0.008 |
Neg logit contributions | |
groom | -0.008 |
roses | -0.007 |
register | -0.007 |
decides | -0.007 |
ponies | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
groom | +0.172 |
roses | +0.158 |
register | +0.157 |
decides | +0.154 |
ponies | +0.147 |
Neg logit contributions | |
orse | -0.154 |
weapon | -0.118 |
oc | -0.116 |
bone | -0.114 |
Carl | -0.113 |
Token | some |
Token ID | 617 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
orse | +0.208 |
weapon | +0.167 |
oc | +0.165 |
bone | +0.159 |
ggy | +0.157 |
Neg logit contributions | |
groom | -0.172 |
roses | -0.156 |
register | -0.154 |
decides | -0.150 |
ponies | -0.144 |
Token | things |
Token ID | 1243 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
groom | +0.216 |
roses | +0.208 |
ponies | +0.194 |
register | +0.192 |
decides | +0.192 |
Neg logit contributions | |
orse | -0.270 |
oc | -0.209 |
weapon | -0.202 |
uddy | -0.200 |
unch | -0.197 |
Token | judge |
Token ID | 5052 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
groom | +0.005 |
roses | +0.004 |
register | +0.004 |
decides | +0.004 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.006 |
oc | -0.005 |
weapon | -0.005 |
unch | -0.005 |
uddy | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
groom | +0.093 |
roses | +0.087 |
register | +0.085 |
decides | +0.084 |
ponies | +0.082 |
Neg logit contributions | |
orse | -0.081 |
weapon | -0.061 |
oc | -0.061 |
bone | -0.057 |
uddy | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
groom | +0.144 |
roses | +0.135 |
register | +0.131 |
decides | +0.131 |
ponies | +0.124 |
Neg logit contributions | |
orse | -0.155 |
weapon | -0.123 |
oc | -0.119 |
bone | -0.117 |
ggy | -0.115 |
Token | person |
Token ID | 1048 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
groom | +0.024 |
roses | +0.022 |
register | +0.021 |
decides | +0.021 |
ponies | +0.020 |
Neg logit contributions | |
orse | -0.027 |
oc | -0.021 |
weapon | -0.021 |
unch | -0.020 |
uddy | -0.020 |
Token | who |
Token ID | 508 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
groom | +0.091 |
roses | +0.084 |
register | +0.082 |
ponies | +0.079 |
decides | +0.078 |
Neg logit contributions | |
orse | -0.113 |
weapon | -0.090 |
oc | -0.089 |
unch | -0.086 |
uddy | -0.086 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.020 |
roses | +0.019 |
decides | +0.018 |
register | +0.018 |
ponies | +0.017 |
Neg logit contributions | |
orse | -0.021 |
weapon | -0.016 |
oc | -0.016 |
unch | -0.015 |
uddy | -0.015 |
Token | who |
Token ID | 508 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
groom | +0.872 |
roses | +0.806 |
register | +0.789 |
decides | +0.774 |
ponies | +0.749 |
Neg logit contributions | |
orse | -0.927 |
weapon | -0.729 |
oc | -0.720 |
bone | -0.688 |
ggy | -0.676 |
Token | is |
Token ID | 318 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
groom | +0.020 |
roses | +0.019 |
register | +0.019 |
decides | +0.018 |
ponies | +0.018 |
Neg logit contributions | |
orse | -0.022 |
weapon | -0.017 |
oc | -0.017 |
bone | -0.016 |
uddy | -0.016 |
Token | right |
Token ID | 826 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
groom | +0.148 |
roses | +0.140 |
register | +0.136 |
decides | +0.134 |
ponies | +0.128 |
Neg logit contributions | |
orse | -0.150 |
weapon | -0.118 |
oc | -0.114 |
bone | -0.112 |
ggy | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
orse | +0.014 |
weapon | +0.012 |
oc | +0.011 |
bone | +0.011 |
hockey | +0.011 |
Neg logit contributions | |
groom | -0.023 |
roses | -0.021 |
decides | -0.020 |
register | -0.020 |
ponies | -0.020 |
Token | who |
Token ID | 508 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
groom | +0.031 |
roses | +0.029 |
register | +0.028 |
decides | +0.026 |
ponies | +0.026 |
Neg logit contributions | |
orse | -0.034 |
weapon | -0.028 |
oc | -0.027 |
bone | -0.026 |
hockey | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
groom | +0.031 |
roses | +0.029 |
register | +0.029 |
decides | +0.028 |
ponies | +0.027 |
Neg logit contributions | |
orse | -0.034 |
weapon | -0.027 |
oc | -0.026 |
bone | -0.025 |
Carl | -0.025 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
groom | +0.025 |
roses | +0.023 |
register | +0.023 |
decides | +0.022 |
ponies | +0.022 |
Neg logit contributions | |
orse | -0.027 |
weapon | -0.022 |
oc | -0.021 |
bone | -0.020 |
puck | -0.020 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
groom | +0.058 |
roses | +0.053 |
register | +0.052 |
decides | +0.051 |
ponies | +0.049 |
Neg logit contributions | |
orse | -0.073 |
oc | -0.058 |
weapon | -0.058 |
bone | -0.055 |
unch | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
orse | +0.162 |
weapon | +0.126 |
oc | +0.125 |
bone | +0.118 |
ggy | +0.116 |
Neg logit contributions | |
groom | -0.182 |
roses | -0.169 |
register | -0.164 |
decides | -0.161 |
ponies | -0.156 |
Token | She |
Token ID | 1375 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
groom | +0.005 |
register | +0.005 |
roses | +0.005 |
decides | +0.004 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.011 |
oc | -0.009 |
weapon | -0.009 |
Carl | -0.009 |
uddy | -0.009 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.324 |
roses | +0.295 |
register | +0.294 |
ponies | +0.269 |
pan | +0.269 |
Neg logit contributions | |
orse | -0.381 |
weapon | -0.323 |
oc | -0.319 |
bone | -0.310 |
puck | -0.305 |
Token | to |
Token ID | 284 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
groom | +0.892 |
roses | +0.823 |
register | +0.811 |
decides | +0.792 |
ponies | +0.766 |
Neg logit contributions | |
orse | -0.916 |
weapon | -0.717 |
oc | -0.703 |
bone | -0.676 |
ggy | -0.666 |
Token | teach |
Token ID | 4545 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
orse | +0.010 |
oc | +0.008 |
weapon | +0.008 |
unch | +0.008 |
uddy | +0.008 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.007 |
decides | -0.006 |
register | -0.006 |
ponies | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
groom | +0.159 |
roses | +0.149 |
register | +0.143 |
decides | +0.142 |
ponies | +0.138 |
Neg logit contributions | |
orse | -0.172 |
oc | -0.135 |
weapon | -0.134 |
bone | -0.126 |
unch | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
orse | +0.225 |
oc | +0.181 |
weapon | +0.180 |
uddy | +0.172 |
unch | +0.172 |
Neg logit contributions | |
groom | -0.156 |
roses | -0.144 |
register | -0.139 |
decides | -0.138 |
ponies | -0.133 |
Token | lesson |
Token ID | 11483 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
groom | +0.027 |
roses | +0.025 |
decides | +0.024 |
ponies | +0.023 |
register | +0.023 |
Neg logit contributions | |
orse | -0.025 |
oc | -0.019 |
oy | -0.018 |
unch | -0.018 |
burying | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
groom | +0.359 |
register | +0.350 |
roses | +0.317 |
pan | +0.305 |
ponies | +0.298 |
Neg logit contributions | |
orse | -0.372 |
weapon | -0.289 |
oc | -0.281 |
Carl | -0.274 |
bone | -0.272 |
Token | uncomfortable |
Token ID | 12916 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
groom | +0.166 |
register | +0.160 |
decides | +0.156 |
roses | +0.155 |
als | +0.147 |
Neg logit contributions | |
orse | -0.129 |
weapon | -0.095 |
burying | -0.094 |
ggy | -0.092 |
Andy | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
orse | +0.197 |
oc | +0.152 |
weapon | +0.150 |
puck | +0.141 |
bone | +0.140 |
Neg logit contributions | |
groom | -0.185 |
roses | -0.177 |
register | -0.170 |
decides | -0.166 |
ponies | -0.165 |
Token | so |
Token ID | 523 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
groom | +0.076 |
roses | +0.072 |
decides | +0.068 |
register | +0.068 |
ponies | +0.067 |
Neg logit contributions | |
orse | -0.060 |
oc | -0.045 |
weapon | -0.044 |
uddy | -0.042 |
oy | -0.041 |
Token | she |
Token ID | 673 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
orse | +0.002 |
Andy | +0.002 |
he | +0.002 |
ggy | +0.002 |
weapon | +0.002 |
Neg logit contributions | |
groom | -0.001 |
register | -0.001 |
decides | -0.001 |
roses | -0.001 |
pan | -0.001 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.315 |
register | +0.309 |
roses | +0.289 |
ponies | +0.272 |
pan | +0.268 |
Neg logit contributions | |
orse | -0.322 |
weapon | -0.257 |
bone | -0.238 |
puck | -0.235 |
ggy | -0.235 |
Token | to |
Token ID | 284 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
groom | +1.003 |
register | +0.965 |
decides | +0.910 |
roses | +0.904 |
ponies | +0.864 |
Neg logit contributions | |
orse | -0.780 |
weapon | -0.584 |
bone | -0.546 |
ggy | -0.543 |
oc | -0.524 |
Token | stay |
Token ID | 2652 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.007 |
oc | +0.007 |
bone | +0.007 |
ggy | +0.007 |
Neg logit contributions | |
groom | -0.007 |
register | -0.006 |
roses | -0.006 |
decides | -0.006 |
ponies | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
orse | +0.003 |
weapon | +0.003 |
oc | +0.003 |
hockey | +0.003 |
bone | +0.003 |
Neg logit contributions | |
groom | -0.003 |
register | -0.003 |
roses | -0.003 |
decides | -0.003 |
ponies | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
orse | +0.063 |
weapon | +0.051 |
oc | +0.050 |
bone | +0.049 |
hockey | +0.048 |
Neg logit contributions | |
groom | -0.049 |
register | -0.045 |
roses | -0.044 |
decides | -0.044 |
ponies | -0.041 |
Token | bed |
Token ID | 3996 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
groom | +0.403 |
register | +0.369 |
roses | +0.361 |
decides | +0.359 |
ponies | +0.337 |
Neg logit contributions | |
orse | -0.407 |
weapon | -0.332 |
oc | -0.320 |
bone | -0.318 |
ggy | -0.305 |
Token | red |
Token ID | 2266 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
groom | +0.351 |
register | +0.324 |
roses | +0.312 |
decides | +0.312 |
ponies | +0.285 |
Neg logit contributions | |
orse | -0.452 |
weapon | -0.380 |
bone | -0.365 |
ggy | -0.354 |
hockey | -0.353 |
Token | dress |
Token ID | 6576 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
groom | +0.104 |
register | +0.097 |
decides | +0.093 |
roses | +0.091 |
nurses | +0.085 |
Neg logit contributions | |
orse | -0.095 |
weapon | -0.087 |
bone | -0.086 |
hockey | -0.082 |
oc | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
groom | +0.171 |
roses | +0.159 |
decides | +0.155 |
register | +0.155 |
ponies | +0.148 |
Neg logit contributions | |
orse | -0.151 |
weapon | -0.121 |
oc | -0.117 |
bone | -0.115 |
ggy | -0.112 |
Token | but |
Token ID | 475 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
groom | +0.073 |
roses | +0.070 |
decides | +0.065 |
ponies | +0.065 |
register | +0.062 |
Neg logit contributions | |
orse | -0.061 |
oc | -0.048 |
weapon | -0.046 |
oy | -0.045 |
uddy | -0.044 |
Token | she |
Token ID | 673 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
orse | +0.316 |
weapon | +0.260 |
bone | +0.253 |
Carl | +0.252 |
hockey | +0.248 |
Neg logit contributions | |
groom | -0.185 |
register | -0.168 |
roses | -0.163 |
decides | -0.157 |
ponies | -0.150 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.274 |
roses | +0.249 |
register | +0.246 |
ponies | +0.228 |
decides | +0.226 |
Neg logit contributions | |
orse | -0.372 |
weapon | -0.303 |
oc | -0.302 |
bone | -0.293 |
Carl | -0.286 |
Token | to |
Token ID | 284 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
groom | +1.006 |
register | +0.986 |
roses | +0.914 |
decides | +0.910 |
nurses | +0.879 |
Neg logit contributions | |
orse | -0.761 |
weapon | -0.555 |
ggy | -0.534 |
bone | -0.531 |
hockey | -0.530 |
Token | t |
Token ID | 256 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
orse | +0.011 |
weapon | +0.008 |
oc | +0.008 |
bone | +0.008 |
uddy | +0.008 |
Neg logit contributions | |
groom | -0.008 |
roses | -0.008 |
register | -0.007 |
decides | -0.007 |
ponies | -0.007 |
Token | uck |
Token ID | 1347 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
groom | +0.249 |
roses | +0.229 |
decides | +0.218 |
register | +0.216 |
ponies | +0.205 |
Neg logit contributions | |
orse | -0.399 |
oc | -0.325 |
weapon | -0.323 |
unch | -0.316 |
ggy | -0.314 |
Token | the |
Token ID | 262 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
groom | +0.062 |
register | +0.058 |
decides | +0.056 |
ponies | +0.053 |
heavens | +0.050 |
Neg logit contributions | |
he | -0.070 |
orse | -0.069 |
Benny | -0.069 |
Tim | -0.069 |
Carl | -0.068 |
Token | cord |
Token ID | 15050 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
groom | +0.026 |
register | +0.024 |
decides | +0.024 |
roses | +0.023 |
ponies | +0.022 |
Neg logit contributions | |
orse | -0.026 |
weapon | -0.023 |
bone | -0.023 |
puck | -0.021 |
hockey | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
groom | +0.277 |
roses | +0.256 |
register | +0.249 |
decides | +0.245 |
ponies | +0.238 |
Neg logit contributions | |
orse | -0.304 |
weapon | -0.240 |
oc | -0.237 |
bone | -0.226 |
Carl | -0.223 |
Token | little |
Token ID | 1310 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
groom | +0.024 |
roses | +0.022 |
decides | +0.021 |
register | +0.021 |
ponies | +0.020 |
Neg logit contributions | |
orse | -0.026 |
weapon | -0.020 |
oc | -0.020 |
oy | -0.019 |
uddy | -0.019 |
Token | better |
Token ID | 1365 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
orse | +0.086 |
oc | +0.068 |
weapon | +0.067 |
uddy | +0.066 |
oy | +0.066 |
Neg logit contributions | |
groom | -0.065 |
roses | -0.059 |
decides | -0.058 |
register | -0.057 |
ponies | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
groom | +0.359 |
roses | +0.311 |
register | +0.304 |
decides | +0.302 |
bride | +0.279 |
Neg logit contributions | |
orse | -0.478 |
Andy | -0.395 |
uddy | -0.393 |
Carl | -0.390 |
unch | -0.387 |
Token | He |
Token ID | 679 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
groom | +0.009 |
roses | +0.009 |
decides | +0.009 |
register | +0.008 |
ponies | +0.008 |
Neg logit contributions | |
orse | -0.006 |
inations | -0.004 |
weapon | -0.004 |
oy | -0.004 |
oc | -0.004 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
orse | +0.321 |
weapon | +0.269 |
oc | +0.264 |
bone | +0.258 |
puck | +0.255 |
Neg logit contributions | |
groom | -0.211 |
register | -0.190 |
roses | -0.188 |
ponies | -0.172 |
nurses | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
groom | +0.752 |
roses | +0.713 |
decides | +0.669 |
register | +0.657 |
ponies | +0.650 |
Neg logit contributions | |
orse | -1.032 |
oc | -0.858 |
weapon | -0.819 |
unch | -0.810 |
uddy | -0.795 |
Token | try |
Token ID | 1949 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
orse | +0.010 |
oc | +0.008 |
weapon | +0.008 |
unch | +0.008 |
uddy | +0.008 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.006 |
decides | -0.006 |
register | -0.006 |
ponies | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
groom | +0.088 |
roses | +0.080 |
register | +0.080 |
decides | +0.078 |
ponies | +0.075 |
Neg logit contributions | |
orse | -0.095 |
weapon | -0.076 |
oc | -0.073 |
bone | -0.072 |
hockey | -0.071 |
Token | He |
Token ID | 679 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
groom | +0.009 |
roses | +0.009 |
decides | +0.009 |
register | +0.008 |
Angel | +0.008 |
Neg logit contributions | |
orse | -0.005 |
weapon | -0.004 |
inations | -0.004 |
oc | -0.003 |
oy | -0.003 |
Token | pushes |
Token ID | 20070 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
orse | +0.302 |
puck | +0.258 |
weapon | +0.255 |
oc | +0.253 |
bone | +0.250 |
Neg logit contributions | |
groom | -0.215 |
register | -0.203 |
roses | -0.191 |
ponies | -0.176 |
nurses | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.021 |
decides | +0.020 |
register | +0.020 |
ponies | +0.019 |
Neg logit contributions | |
orse | -0.019 |
weapon | -0.015 |
oc | -0.015 |
puck | -0.014 |
bone | -0.014 |
Token | One |
Token ID | 3198 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
groom | +0.018 |
roses | +0.016 |
register | +0.016 |
decides | +0.015 |
ponies | +0.015 |
Neg logit contributions | |
orse | -0.024 |
oc | -0.019 |
weapon | -0.019 |
ggy | -0.019 |
uddy | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
groom | +0.244 |
roses | +0.241 |
decides | +0.221 |
nurses | +0.221 |
register | +0.216 |
Neg logit contributions | |
orse | -0.251 |
unch | -0.197 |
bullets | -0.196 |
puck | -0.194 |
weapon | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
orse | +0.129 |
weapon | +0.095 |
Carl | +0.092 |
oy | +0.091 |
ggy | +0.090 |
Neg logit contributions | |
groom | -0.189 |
register | -0.172 |
decides | -0.172 |
roses | -0.172 |
ponies | -0.166 |
Token | Sara |
Token ID | 24799 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
groom | +0.055 |
register | +0.050 |
decides | +0.050 |
roses | +0.050 |
ponies | +0.046 |
Neg logit contributions | |
orse | -0.078 |
weapon | -0.064 |
Carl | -0.063 |
bone | -0.062 |
oc | -0.062 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.220 |
roses | +0.200 |
register | +0.193 |
ponies | +0.185 |
Angel | +0.179 |
Neg logit contributions | |
orse | -0.288 |
weapon | -0.238 |
oc | -0.236 |
bone | -0.222 |
puck | -0.216 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
groom | +0.926 |
register | +0.857 |
roses | +0.842 |
decides | +0.828 |
ponies | +0.791 |
Neg logit contributions | |
orse | -0.875 |
weapon | -0.686 |
oc | -0.651 |
bone | -0.646 |
ggy | -0.638 |
Token | make |
Token ID | 787 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.007 |
oc | +0.007 |
bone | +0.007 |
uddy | +0.007 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.007 |
register | -0.007 |
decides | -0.006 |
ponies | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
groom | +0.055 |
roses | +0.050 |
register | +0.049 |
decides | +0.049 |
ponies | +0.047 |
Neg logit contributions | |
orse | -0.064 |
weapon | -0.051 |
oc | -0.050 |
bone | -0.049 |
ggy | -0.048 |
Token | box |
Token ID | 3091 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
groom | +0.023 |
roses | +0.021 |
decides | +0.021 |
register | +0.021 |
ponies | +0.020 |
Neg logit contributions | |
orse | -0.032 |
weapon | -0.027 |
oc | -0.026 |
bone | -0.026 |
puck | -0.025 |
Token | into |
Token ID | 656 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
orse | +0.019 |
weapon | +0.015 |
oc | +0.015 |
bone | +0.014 |
ggy | +0.014 |
Neg logit contributions | |
groom | -0.021 |
roses | -0.020 |
decides | -0.019 |
register | -0.019 |
ponies | -0.019 |
Token | back |
Token ID | 736 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
groom | +0.040 |
register | +0.035 |
roses | +0.034 |
ponies | +0.030 |
decides | +0.030 |
Neg logit contributions | |
orse | -0.089 |
weapon | -0.078 |
oc | -0.076 |
bone | -0.075 |
oy | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
groom | +0.602 |
roses | +0.555 |
register | +0.547 |
decides | +0.524 |
ponies | +0.516 |
Neg logit contributions | |
orse | -0.505 |
weapon | -0.395 |
oc | -0.394 |
bone | -0.372 |
oy | -0.359 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
groom | +0.007 |
decides | +0.007 |
roses | +0.007 |
register | +0.006 |
Angel | +0.006 |
Neg logit contributions | |
orse | -0.007 |
weapon | -0.005 |
inations | -0.005 |
oc | -0.005 |
oy | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
decides | +0.015 |
roses | +0.015 |
She | +0.015 |
groom | +0.015 |
Angel | +0.014 |
Neg logit contributions | |
orse | -0.021 |
weapon | -0.018 |
oy | -0.017 |
puck | -0.017 |
oc | -0.017 |
Token | He |
Token ID | 1544 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
groom | +0.018 |
decides | +0.017 |
She | +0.017 |
register | +0.017 |
roses | +0.017 |
Neg logit contributions | |
orse | -0.021 |
weapon | -0.017 |
Carl | -0.017 |
unch | -0.016 |
bone | -0.016 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
orse | +0.135 |
weapon | +0.119 |
puck | +0.119 |
che | +0.116 |
oc | +0.115 |
Neg logit contributions | |
groom | -0.102 |
register | -0.095 |
roses | -0.087 |
ponies | -0.084 |
pan | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
groom | +0.736 |
roses | +0.692 |
decides | +0.656 |
register | +0.629 |
ponies | +0.624 |
Neg logit contributions | |
orse | -1.047 |
oc | -0.880 |
weapon | -0.840 |
unch | -0.832 |
uddy | -0.824 |
Token | look |
Token ID | 804 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
orse | +0.011 |
weapon | +0.009 |
oc | +0.009 |
bone | +0.008 |
Carl | +0.008 |
Neg logit contributions | |
groom | -0.009 |
roses | -0.008 |
register | -0.008 |
decides | -0.007 |
ponies | -0.007 |
Token | for |
Token ID | 329 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
orse | +0.042 |
weapon | +0.034 |
oc | +0.033 |
bone | +0.032 |
hockey | +0.031 |
Neg logit contributions | |
groom | -0.061 |
roses | -0.055 |
register | -0.054 |
ponies | -0.051 |
salon | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
orse | +0.203 |
oc | +0.166 |
weapon | +0.164 |
uddy | +0.158 |
unch | +0.157 |
Neg logit contributions | |
groom | -0.144 |
roses | -0.133 |
register | -0.127 |
decides | -0.125 |
ponies | -0.120 |
Token | real |
Token ID | 1103 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
groom | +0.024 |
roses | +0.022 |
decides | +0.021 |
register | +0.021 |
ponies | +0.020 |
Neg logit contributions | |
orse | -0.025 |
oc | -0.019 |
unch | -0.018 |
weapon | -0.018 |
oy | -0.018 |
Token | best |
Token ID | 1266 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
groom | +0.023 |
roses | +0.022 |
register | +0.021 |
decides | +0.021 |
ponies | +0.020 |
Neg logit contributions | |
orse | -0.031 |
weapon | -0.026 |
oc | -0.025 |
bone | -0.024 |
puck | -0.023 |
Token | book |
Token ID | 1492 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
groom | +0.157 |
roses | +0.146 |
ponies | +0.140 |
register | +0.137 |
decides | +0.134 |
Neg logit contributions | |
orse | -0.189 |
unch | -0.146 |
oc | -0.143 |
uddy | -0.140 |
Carl | -0.139 |
Token | ever |
Token ID | 1683 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
orse | +0.034 |
weapon | +0.025 |
oc | +0.025 |
bone | +0.023 |
uddy | +0.023 |
Neg logit contributions | |
groom | -0.043 |
roses | -0.041 |
register | -0.040 |
decides | -0.039 |
ponies | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
orse | +0.142 |
weapon | +0.112 |
oc | +0.109 |
unch | +0.107 |
puck | +0.107 |
Neg logit contributions | |
groom | -0.126 |
roses | -0.118 |
decides | -0.115 |
register | -0.114 |
ponies | -0.110 |
Token | She |
Token ID | 1375 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
groom | +0.006 |
register | +0.005 |
roses | +0.005 |
decides | +0.005 |
pan | +0.005 |
Neg logit contributions | |
orse | -0.008 |
His | -0.007 |
Carl | -0.007 |
Benny | -0.007 |
Andy | -0.007 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.303 |
register | +0.299 |
roses | +0.283 |
pan | +0.269 |
nurses | +0.263 |
Neg logit contributions | |
orse | -0.393 |
weapon | -0.330 |
oc | -0.326 |
bone | -0.320 |
puck | -0.316 |
Token | to |
Token ID | 284 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
groom | +1.018 |
register | +0.994 |
decides | +0.927 |
roses | +0.927 |
pan | +0.892 |
Neg logit contributions | |
orse | -0.746 |
weapon | -0.550 |
ggy | -0.524 |
bone | -0.523 |
hockey | -0.516 |
Token | read |
Token ID | 1100 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
orse | +0.010 |
weapon | +0.008 |
oc | +0.008 |
bone | +0.008 |
ggy | +0.008 |
Neg logit contributions | |
groom | -0.009 |
roses | -0.008 |
register | -0.008 |
decides | -0.008 |
ponies | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
groom | +0.185 |
register | +0.172 |
decides | +0.166 |
roses | +0.163 |
nurses | +0.156 |
Neg logit contributions | |
orse | -0.149 |
bone | -0.123 |
weapon | -0.120 |
hockey | -0.119 |
oc | -0.115 |
Token | again |
Token ID | 757 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
orse | +0.013 |
weapon | +0.011 |
oc | +0.010 |
bone | +0.010 |
ggy | +0.010 |
Neg logit contributions | |
groom | -0.015 |
roses | -0.013 |
register | -0.013 |
decides | -0.013 |
ponies | -0.012 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
groom | +0.290 |
roses | +0.271 |
register | +0.269 |
decides | +0.261 |
ponies | +0.253 |
Neg logit contributions | |
orse | -0.264 |
oc | -0.205 |
weapon | -0.201 |
bone | -0.190 |
ggy | -0.186 |
Token | under |
Token ID | 739 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
orse | +0.242 |
oc | +0.196 |
weapon | +0.187 |
oy | +0.185 |
unch | +0.184 |
Neg logit contributions | |
groom | -0.185 |
roses | -0.172 |
register | -0.167 |
decides | -0.163 |
ponies | -0.158 |
Token | the |
Token ID | 262 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
groom | +0.022 |
roses | +0.020 |
register | +0.019 |
decides | +0.019 |
ponies | +0.019 |
Neg logit contributions | |
orse | -0.030 |
weapon | -0.024 |
oc | -0.024 |
bone | -0.023 |
uddy | -0.023 |
Token | couch |
Token ID | 18507 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
groom | +0.025 |
decides | +0.023 |
register | +0.022 |
roses | +0.022 |
ponies | +0.021 |
Neg logit contributions | |
orse | -0.026 |
weapon | -0.023 |
bone | -0.022 |
oc | -0.021 |
puck | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
groom | +0.337 |
roses | +0.314 |
register | +0.306 |
decides | +0.301 |
ponies | +0.292 |
Neg logit contributions | |
orse | -0.350 |
weapon | -0.273 |
oc | -0.270 |
bone | -0.256 |
uddy | -0.254 |
Token | She |
Token ID | 1375 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
groom | +0.004 |
roses | +0.004 |
register | +0.004 |
decides | +0.004 |
ponies | +0.003 |
Neg logit contributions | |
orse | -0.008 |
weapon | -0.007 |
oc | -0.007 |
bone | -0.007 |
oy | -0.007 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.341 |
register | +0.318 |
roses | +0.283 |
pan | +0.282 |
bride | +0.272 |
Neg logit contributions | |
orse | -0.374 |
weapon | -0.312 |
oc | -0.307 |
bone | -0.304 |
Carl | -0.303 |
Token | to |
Token ID | 284 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
groom | +0.941 |
register | +0.880 |
roses | +0.862 |
decides | +0.845 |
ponies | +0.814 |
Neg logit contributions | |
orse | -0.866 |
weapon | -0.663 |
oc | -0.630 |
bone | -0.629 |
ggy | -0.622 |
Token | be |
Token ID | 307 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
orse | +0.011 |
oc | +0.009 |
weapon | +0.009 |
uddy | +0.009 |
unch | +0.009 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.007 |
decides | -0.006 |
register | -0.006 |
ponies | -0.006 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
orse | +0.229 |
ggy | +0.208 |
hockey | +0.191 |
weapon | +0.187 |
Tim | +0.179 |
Neg logit contributions | |
register | -0.275 |
groom | -0.274 |
als | -0.272 |
roses | -0.265 |
decides | -0.257 |
Token | and |
Token ID | 290 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
groom | +0.088 |
roses | +0.081 |
register | +0.079 |
decides | +0.077 |
ponies | +0.075 |
Neg logit contributions | |
orse | -0.076 |
weapon | -0.060 |
oc | -0.058 |
bone | -0.057 |
hockey | -0.055 |
Token | help |
Token ID | 1037 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
groom | +0.032 |
roses | +0.030 |
register | +0.030 |
decides | +0.029 |
ponies | +0.028 |
Neg logit contributions | |
orse | -0.034 |
weapon | -0.027 |
oc | -0.027 |
bone | -0.026 |
Carl | -0.025 |
Token | ." |
Token ID | 526 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
orse | +0.013 |
weapon | +0.010 |
oc | +0.010 |
bone | +0.010 |
ggy | +0.010 |
Neg logit contributions | |
groom | -0.013 |
roses | -0.012 |
register | -0.012 |
decides | -0.011 |
ponies | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
groom | +0.451 |
roses | +0.438 |
decides | +0.425 |
register | +0.412 |
ponies | +0.399 |
Neg logit contributions | |
orse | -0.482 |
weapon | -0.383 |
oc | -0.381 |
oy | -0.362 |
inations | -0.360 |
Token |
|
Token ID | 198 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
groom | +0.019 |
roses | +0.018 |
decides | +0.018 |
register | +0.017 |
She | +0.017 |
Neg logit contributions | |
orse | -0.021 |
weapon | -0.017 |
oc | -0.016 |
oy | -0.016 |
puck | -0.016 |
Token | L |
Token ID | 43 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
groom | +0.018 |
roses | +0.017 |
register | +0.016 |
decides | +0.016 |
ponies | +0.015 |
Neg logit contributions | |
orse | -0.023 |
weapon | -0.019 |
oc | -0.018 |
bone | -0.018 |
Carl | -0.018 |
Token | ily |
Token ID | 813 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
orse | +0.173 |
weapon | +0.143 |
ggy | +0.138 |
unch | +0.136 |
oc | +0.136 |
Neg logit contributions | |
groom | -0.120 |
roses | -0.104 |
ponies | -0.099 |
register | -0.096 |
decides | -0.094 |
Token | decides |
Token ID | 13267 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
groom | +0.252 |
register | +0.225 |
roses | +0.219 |
bride | +0.204 |
nurses | +0.204 |
Neg logit contributions | |
orse | -0.257 |
puck | -0.220 |
weapon | -0.217 |
bone | -0.217 |
hockey | -0.213 |
Token | to |
Token ID | 284 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
groom | +0.936 |
roses | +0.854 |
register | +0.854 |
decides | +0.825 |
ponies | +0.800 |
Neg logit contributions | |
orse | -0.878 |
weapon | -0.681 |
oc | -0.655 |
bone | -0.646 |
ggy | -0.643 |
Token | show |
Token ID | 905 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
orse | +0.011 |
oc | +0.009 |
weapon | +0.009 |
unch | +0.009 |
uddy | +0.009 |
Neg logit contributions | |
groom | -0.007 |
roses | -0.006 |
decides | -0.006 |
register | -0.006 |
ponies | -0.005 |
Token | Ben |
Token ID | 3932 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
groom | +0.061 |
roses | +0.056 |
decides | +0.055 |
register | +0.055 |
ponies | +0.052 |
Neg logit contributions | |
orse | -0.056 |
Carl | -0.046 |
weapon | -0.045 |
Benny | -0.044 |
hockey | -0.043 |
Token | how |
Token ID | 703 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
orse | +0.050 |
weapon | +0.041 |
oc | +0.041 |
bone | +0.039 |
uddy | +0.039 |
Neg logit contributions | |
groom | -0.034 |
roses | -0.031 |
register | -0.030 |
decides | -0.029 |
ponies | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
groom | +0.221 |
roses | +0.207 |
decides | +0.199 |
ponies | +0.189 |
register | +0.183 |
Neg logit contributions | |
orse | -0.319 |
oc | -0.274 |
weapon | -0.256 |
unch | -0.248 |
oy | -0.247 |
Token | |
Token ID | 220 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
orse | +0.015 |
weapon | +0.012 |
oc | +0.012 |
ggy | +0.011 |
oy | +0.011 |
Neg logit contributions | |
groom | -0.014 |
roses | -0.013 |
decides | -0.013 |
register | -0.013 |
ponies | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
groom | +0.037 |
roses | +0.035 |
register | +0.035 |
decides | +0.034 |
ponies | +0.033 |
Neg logit contributions | |
orse | -0.038 |
weapon | -0.031 |
oc | -0.030 |
oy | -0.028 |
puck | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
orse | +0.002 |
weapon | +0.001 |
oc | +0.001 |
puck | +0.001 |
bullets | +0.001 |
Neg logit contributions | |
groom | -0.001 |
roses | -0.001 |
decides | -0.001 |
register | -0.001 |
She | -0.001 |
Token | After |
Token ID | 3260 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
orse | +0.003 |
weapon | +0.002 |
oc | +0.002 |
bone | +0.002 |
oy | +0.002 |
Neg logit contributions | |
groom | -0.002 |
roses | -0.002 |
decides | -0.002 |
She | -0.002 |
register | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
orse | +0.218 |
oc | +0.196 |
uddy | +0.189 |
weapon | +0.187 |
rig | +0.182 |
Neg logit contributions | |
groom | -0.152 |
roses | -0.150 |
her | -0.138 |
register | -0.136 |
Angel | -0.135 |
Token | nap |
Token ID | 25422 |
Feature activation | +8.35e+00 |
Pos logit contributions | |
groom | +0.003 |
roses | +0.002 |
register | +0.002 |
decides | +0.002 |
ponies | +0.002 |
Neg logit contributions | |
orse | -0.003 |
weapon | -0.003 |
oc | -0.002 |
bone | -0.002 |
hockey | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
orse | +0.498 |
weapon | +0.388 |
oc | +0.381 |
bone | +0.362 |
uddy | +0.361 |
Neg logit contributions | |
groom | -0.487 |
roses | -0.460 |
register | -0.448 |
decides | -0.433 |
ponies | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
groom | +0.036 |
roses | +0.033 |
register | +0.032 |
decides | +0.031 |
ponies | +0.030 |
Neg logit contributions | |
orse | -0.049 |
weapon | -0.040 |
oc | -0.040 |
bone | -0.038 |
uddy | -0.038 |
Token | baby |
Token ID | 5156 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
groom | +0.001 |
roses | +0.001 |
decides | +0.001 |
register | +0.001 |
als | +0.001 |
Neg logit contributions | |
orse | -0.001 |
bone | -0.001 |
weapon | -0.001 |
oc | -0.001 |
hockey | -0.001 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
groom | +0.326 |
roses | +0.309 |
register | +0.303 |
decides | +0.295 |
ponies | +0.284 |
Neg logit contributions | |
orse | -0.306 |
oc | -0.238 |
weapon | -0.231 |
bone | -0.226 |
ggy | -0.219 |
Token | much |
Token ID | 881 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
groom | +0.026 |
roses | +0.024 |
register | +0.023 |
decides | +0.023 |
ponies | +0.022 |
Neg logit contributions | |
orse | -0.028 |
weapon | -0.022 |
oc | -0.022 |
bone | -0.021 |
Carl | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
groom | +0.055 |
roses | +0.049 |
register | +0.048 |
decides | +0.046 |
ponies | +0.044 |
Neg logit contributions | |
orse | -0.074 |
weapon | -0.061 |
oc | -0.060 |
Andy | -0.059 |
Carl | -0.059 |
Token | play |
Token ID | 711 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
orse | +0.190 |
weapon | +0.157 |
oc | +0.157 |
bone | +0.151 |
Carl | +0.149 |
Neg logit contributions | |
groom | -0.101 |
roses | -0.091 |
register | -0.088 |
decides | -0.085 |
ponies | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
orse | +0.259 |
weapon | +0.199 |
oc | +0.197 |
uddy | +0.191 |
unch | +0.190 |
Neg logit contributions | |
groom | -0.236 |
roses | -0.221 |
register | -0.214 |
decides | -0.208 |
ponies | -0.205 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
orse | +0.101 |
weapon | +0.084 |
oc | +0.082 |
ggy | +0.079 |
oy | +0.078 |
Neg logit contributions | |
groom | -0.069 |
roses | -0.064 |
decides | -0.062 |
register | -0.060 |
ponies | -0.059 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
orse | +0.394 |
weapon | +0.313 |
oc | +0.294 |
oy | +0.293 |
inations | +0.293 |
Neg logit contributions | |
groom | -0.306 |
roses | -0.301 |
decides | -0.289 |
register | -0.285 |
Angel | -0.281 |
Token | upon |
Token ID | 2402 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
orse | +0.249 |
oc | +0.211 |
weapon | +0.200 |
puck | +0.195 |
anas | +0.193 |
Neg logit contributions | |
groom | -0.223 |
roses | -0.214 |
register | -0.210 |
decides | -0.207 |
ponies | -0.198 |
Token | a |
Token ID | 257 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
orse | +0.672 |
oc | +0.587 |
uddy | +0.572 |
weapon | +0.561 |
oy | +0.547 |
Neg logit contributions | |
groom | -0.317 |
roses | -0.285 |
herself | -0.266 |
her | -0.264 |
ponies | -0.264 |
Token | time |
Token ID | 640 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
orse | +0.027 |
weapon | +0.022 |
bullets | +0.021 |
Carl | +0.020 |
puck | +0.020 |
Neg logit contributions | |
groom | -0.029 |
decides | -0.027 |
roses | -0.027 |
ponies | -0.026 |
nine | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
orse | +0.372 |
oc | +0.318 |
weapon | +0.317 |
puck | +0.313 |
bullets | +0.307 |
Neg logit contributions | |
roses | -0.198 |
groom | -0.191 |
register | -0.180 |
Angel | -0.179 |
her | -0.177 |
Token | in |
Token ID | 287 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.019 |
register | +0.019 |
decides | +0.018 |
ponies | +0.018 |
Neg logit contributions | |
orse | -0.023 |
weapon | -0.018 |
oc | -0.018 |
bone | -0.017 |
uddy | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
orse | +0.120 |
weapon | +0.097 |
oc | +0.097 |
uddy | +0.092 |
unch | +0.092 |
Neg logit contributions | |
groom | -0.080 |
roses | -0.073 |
ponies | -0.067 |
register | -0.066 |
decides | -0.065 |
Token | Thank |
Token ID | 10449 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
groom | +0.186 |
roses | +0.164 |
decides | +0.160 |
register | +0.156 |
ponies | +0.147 |
Neg logit contributions | |
orse | -0.302 |
weapon | -0.250 |
oc | -0.241 |
uddy | -0.239 |
bone | -0.235 |
Token | you |
Token ID | 345 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
groom | +0.100 |
roses | +0.099 |
als | +0.090 |
register | +0.090 |
al | +0.090 |
Neg logit contributions | |
orse | -0.236 |
weapon | -0.203 |
puck | -0.203 |
inations | -0.192 |
rig | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
orse | +0.250 |
weapon | +0.194 |
puck | +0.190 |
unch | +0.185 |
oc | +0.185 |
Neg logit contributions | |
groom | -0.185 |
register | -0.179 |
roses | -0.174 |
ponies | -0.163 |
decides | -0.163 |
Token | Billy |
Token ID | 15890 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
groom | +0.046 |
roses | +0.042 |
Angel | +0.041 |
nurses | +0.041 |
decides | +0.040 |
Neg logit contributions | |
orse | -0.031 |
oc | -0.022 |
rd | -0.021 |
ggy | -0.021 |
orses | -0.021 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
orse | +0.482 |
weapon | +0.370 |
unch | +0.366 |
puck | +0.358 |
uddy | +0.355 |
Neg logit contributions | |
groom | -0.378 |
roses | -0.348 |
decides | -0.345 |
register | -0.337 |
ponies | -0.326 |
Token | Tim |
Token ID | 5045 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
her | +0.116 |
roses | +0.111 |
groom | +0.111 |
She | +0.109 |
herself | +0.109 |
Neg logit contributions | |
orse | -0.093 |
gh | -0.080 |
inations | -0.076 |
ggy | -0.073 |
weapon | -0.073 |
Token | my |
Token ID | 1820 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
orse | +0.812 |
weapon | +0.685 |
oc | +0.677 |
unch | +0.661 |
puck | +0.659 |
Neg logit contributions | |
groom | -0.284 |
decides | -0.243 |
roses | -0.231 |
register | -0.222 |
ponies | -0.206 |
Token | said |
Token ID | 531 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
groom | +0.101 |
decides | +0.085 |
her | +0.083 |
roses | +0.080 |
back | +0.079 |
Neg logit contributions | |
orse | -0.150 |
uddy | -0.140 |
igsaw | -0.138 |
unch | -0.138 |
inations | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
orse | +0.204 |
weapon | +0.173 |
oc | +0.168 |
emy | +0.168 |
puck | +0.166 |
Neg logit contributions | |
groom | -0.129 |
register | -0.115 |
back | -0.111 |
roses | -0.110 |
her | -0.107 |
Token | " |
Token ID | 366 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
orse | +0.031 |
weapon | +0.025 |
oc | +0.025 |
ggy | +0.024 |
inations | +0.024 |
Neg logit contributions | |
groom | -0.019 |
roses | -0.017 |
decides | -0.017 |
register | -0.017 |
ponies | -0.016 |
Token | You |
Token ID | 1639 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
groom | +0.135 |
She | +0.105 |
roses | +0.103 |
decides | +0.099 |
ponies | +0.090 |
Neg logit contributions | |
orse | -0.335 |
weapon | -0.302 |
uddy | -0.288 |
oy | -0.284 |
bone | -0.281 |
Token | explore |
Token ID | 7301 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
orse | +0.033 |
oc | +0.027 |
weapon | +0.026 |
uddy | +0.026 |
unch | +0.025 |
Neg logit contributions | |
groom | -0.032 |
roses | -0.030 |
decides | -0.028 |
register | -0.027 |
ponies | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
orse | +0.138 |
weapon | +0.107 |
oc | +0.106 |
uddy | +0.105 |
unch | +0.103 |
Neg logit contributions | |
groom | -0.111 |
roses | -0.107 |
ponies | -0.099 |
decides | -0.099 |
register | -0.099 |
Token | One |
Token ID | 1881 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
orse | +0.021 |
ggy | +0.019 |
inations | +0.018 |
weapon | +0.017 |
bullets | +0.017 |
Neg logit contributions | |
decides | -0.011 |
roses | -0.010 |
groom | -0.009 |
mirror | -0.009 |
shops | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
roses | +0.110 |
groom | +0.108 |
her | +0.103 |
ponies | +0.099 |
decides | +0.098 |
Neg logit contributions | |
orse | -0.136 |
bullets | -0.117 |
puck | -0.113 |
inations | -0.110 |
beard | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
orse | +0.233 |
inations | +0.199 |
oc | +0.199 |
puck | +0.196 |
rig | +0.193 |
Neg logit contributions | |
roses | -0.110 |
her | -0.100 |
groom | -0.098 |
decides | -0.096 |
register | -0.093 |
Token | Joe |
Token ID | 5689 |
Feature activation | +9.72e+00 |
Pos logit contributions | |
her | +0.042 |
roses | +0.038 |
out | +0.037 |
groom | +0.036 |
herself | +0.036 |
Neg logit contributions | |
orse | -0.033 |
oc | -0.029 |
inations | -0.027 |
igsaw | -0.026 |
ggy | -0.026 |
Token | went |
Token ID | 1816 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
orse | +0.659 |
weapon | +0.532 |
oc | +0.527 |
bone | +0.506 |
uddy | +0.503 |
Neg logit contributions | |
groom | -0.490 |
roses | -0.451 |
register | -0.435 |
decides | -0.435 |
ponies | -0.413 |
Token | for |
Token ID | 329 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
groom | +0.282 |
decides | +0.253 |
roses | +0.249 |
register | +0.248 |
ponies | +0.231 |
Neg logit contributions | |
orse | -0.261 |
weapon | -0.225 |
bone | -0.205 |
hockey | -0.204 |
fishing | -0.203 |
Token | a |
Token ID | 257 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
orse | +0.250 |
oc | +0.214 |
uddy | +0.202 |
unch | +0.201 |
weapon | +0.198 |
Neg logit contributions | |
groom | -0.148 |
roses | -0.141 |
ponies | -0.131 |
nurses | -0.126 |
decides | -0.124 |
Token | walk |
Token ID | 2513 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
orse | +0.004 |
oc | +0.004 |
unch | +0.004 |
bullets | +0.003 |
tentacles | +0.003 |
Neg logit contributions | |
groom | -0.003 |
roses | -0.002 |
ponies | -0.002 |
Angel | -0.002 |
nurses | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
orse | +0.334 |
oc | +0.267 |
unch | +0.265 |
weapon | +0.260 |
uddy | +0.260 |
Neg logit contributions | |
groom | -0.160 |
roses | -0.153 |
ponies | -0.143 |
register | -0.142 |
her | -0.135 |
Token | sleep |
Token ID | 3993 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
orse | +0.012 |
oc | +0.010 |
weapon | +0.010 |
uddy | +0.009 |
unch | +0.009 |
Neg logit contributions | |
groom | -0.012 |
roses | -0.011 |
decides | -0.011 |
register | -0.010 |
ponies | -0.010 |
Token | well |
Token ID | 880 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
orse | +0.342 |
weapon | +0.267 |
oc | +0.264 |
ggy | +0.255 |
hockey | +0.254 |
Neg logit contributions | |
groom | -0.382 |
roses | -0.359 |
decides | -0.352 |
register | -0.342 |
ponies | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
orse | +0.005 |
weapon | +0.004 |
oc | +0.004 |
bone | +0.004 |
hockey | +0.004 |
Neg logit contributions | |
groom | -0.006 |
roses | -0.005 |
register | -0.005 |
decides | -0.005 |
ponies | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
orse | +0.038 |
weapon | +0.031 |
oc | +0.029 |
puck | +0.028 |
ggy | +0.028 |
Neg logit contributions | |
groom | -0.038 |
roses | -0.038 |
decides | -0.036 |
register | -0.035 |
Angel | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
orse | +0.030 |
weapon | +0.027 |
puck | +0.025 |
bullets | +0.025 |
tentacles | +0.025 |
Neg logit contributions | |
roses | -0.019 |
She | -0.019 |
Angel | -0.019 |
groom | -0.018 |
decides | -0.018 |
Token | Tim |
Token ID | 14967 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
orse | +0.022 |
weapon | +0.017 |
tentacles | +0.015 |
beard | +0.015 |
puck | +0.014 |
Neg logit contributions | |
She | -0.031 |
groom | -0.031 |
roses | -0.030 |
decides | -0.029 |
nurses | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
orse | +0.671 |
weapon | +0.555 |
oc | +0.553 |
bone | +0.533 |
uddy | +0.526 |
Neg logit contributions | |
groom | -0.397 |
roses | -0.361 |
register | -0.347 |
decides | -0.332 |
ponies | -0.325 |
Token | did |
Token ID | 750 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
groom | +0.118 |
roses | +0.108 |
decides | +0.106 |
register | +0.104 |
ponies | +0.100 |
Neg logit contributions | |
orse | -0.124 |
weapon | -0.098 |
oc | -0.097 |
unch | -0.092 |
uddy | -0.092 |
Token | not |
Token ID | 407 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
orse | +0.262 |
oc | +0.214 |
weapon | +0.210 |
uddy | +0.206 |
unch | +0.197 |
Neg logit contributions | |
groom | -0.228 |
roses | -0.216 |
decides | -0.214 |
register | -0.206 |
herself | -0.203 |
Token | believe |
Token ID | 1975 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
orse | +0.195 |
weapon | +0.155 |
oc | +0.151 |
bone | +0.146 |
oy | +0.144 |
Neg logit contributions | |
groom | -0.163 |
roses | -0.153 |
register | -0.149 |
decides | -0.144 |
ponies | -0.142 |
Token | Mom |
Token ID | 11254 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
orse | +0.495 |
oc | +0.383 |
weapon | +0.376 |
uddy | +0.353 |
bone | +0.353 |
Neg logit contributions | |
groom | -0.535 |
roses | -0.507 |
register | -0.488 |
decides | -0.478 |
ponies | -0.473 |
Token | to |
Token ID | 284 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
groom | +0.030 |
register | +0.028 |
roses | +0.027 |
decides | +0.027 |
ponies | +0.026 |
Neg logit contributions | |
orse | -0.028 |
weapon | -0.022 |
bone | -0.021 |
oc | -0.021 |
hockey | -0.021 |
Token | see |
Token ID | 766 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
orse | +0.067 |
weapon | +0.052 |
oc | +0.049 |
bone | +0.049 |
oy | +0.048 |
Neg logit contributions | |
groom | -0.070 |
register | -0.068 |
roses | -0.067 |
decides | -0.064 |
ponies | -0.063 |
Token | my |
Token ID | 616 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
groom | +0.191 |
register | +0.189 |
decides | +0.179 |
roses | +0.171 |
pan | +0.169 |
Neg logit contributions | |
orse | -0.284 |
weapon | -0.232 |
oc | -0.232 |
hockey | -0.230 |
Benny | -0.230 |
Token | book |
Token ID | 1492 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
orse | +0.017 |
unch | +0.014 |
uddy | +0.013 |
oc | +0.013 |
ggy | +0.013 |
Neg logit contributions | |
groom | -0.011 |
roses | -0.010 |
decides | -0.010 |
ponies | -0.010 |
register | -0.010 |
Token | ? |
Token ID | 30 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
orse | +0.111 |
weapon | +0.093 |
oc | +0.090 |
bone | +0.089 |
hockey | +0.087 |
Neg logit contributions | |
groom | -0.091 |
roses | -0.084 |
register | -0.080 |
decides | -0.079 |
ponies | -0.076 |
Token | It |
Token ID | 632 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
groom | +0.144 |
roses | +0.135 |
register | +0.134 |
decides | +0.128 |
ponies | +0.124 |
Neg logit contributions | |
orse | -0.124 |
oc | -0.098 |
bone | -0.090 |
weapon | -0.090 |
hockey | -0.088 |
Token | is |
Token ID | 318 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
orse | +0.218 |
oc | +0.177 |
weapon | +0.177 |
bone | +0.170 |
Carl | +0.165 |
Neg logit contributions | |
groom | -0.173 |
roses | -0.159 |
register | -0.157 |
decides | -0.148 |
ponies | -0.145 |
Token | about |
Token ID | 546 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
groom | +0.084 |
roses | +0.078 |
register | +0.075 |
decides | +0.075 |
ponies | +0.073 |
Neg logit contributions | |
orse | -0.087 |
oc | -0.068 |
weapon | -0.067 |
uddy | -0.063 |
unch | -0.063 |
Token | animals |
Token ID | 4695 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
orse | +0.222 |
oc | +0.178 |
weapon | +0.176 |
uddy | +0.168 |
unch | +0.167 |
Neg logit contributions | |
groom | -0.175 |
roses | -0.162 |
register | -0.153 |
decides | -0.152 |
ponies | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
orse | +0.002 |
weapon | +0.002 |
oc | +0.002 |
bone | +0.002 |
hockey | +0.002 |
Neg logit contributions | |
groom | -0.002 |
roses | -0.002 |
register | -0.002 |
decides | -0.002 |
ponies | -0.002 |
Token | I |
Token ID | 314 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
orse | +0.058 |
oc | +0.045 |
weapon | +0.042 |
bone | +0.041 |
Carl | +0.040 |
Neg logit contributions | |
groom | -0.066 |
roses | -0.061 |
register | -0.061 |
decides | -0.058 |
ponies | -0.057 |
Token | Ben |
Token ID | 3932 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
groom | +0.107 |
roses | +0.100 |
decides | +0.092 |
register | +0.090 |
ponies | +0.089 |
Neg logit contributions | |
orse | -0.178 |
oc | -0.152 |
weapon | -0.149 |
uddy | -0.143 |
unch | -0.142 |
Token | says |
Token ID | 1139 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
orse | +0.046 |
weapon | +0.038 |
oc | +0.037 |
bone | +0.036 |
Carl | +0.036 |
Neg logit contributions | |
groom | -0.034 |
register | -0.031 |
roses | -0.031 |
ponies | -0.029 |
decides | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
groom | +0.122 |
roses | +0.114 |
register | +0.111 |
decides | +0.110 |
ponies | +0.107 |
Neg logit contributions | |
orse | -0.112 |
weapon | -0.086 |
oc | -0.085 |
bone | -0.080 |
Carl | -0.079 |
Token | cl |
Token ID | 537 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
groom | +0.070 |
roses | +0.067 |
register | +0.066 |
decides | +0.066 |
ponies | +0.063 |
Neg logit contributions | |
orse | -0.064 |
weapon | -0.046 |
oc | -0.046 |
hockey | -0.044 |
bone | -0.044 |
Token | apping |
Token ID | 5912 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
groom | +0.051 |
roses | +0.049 |
ponies | +0.047 |
register | +0.047 |
nurses | +0.046 |
Neg logit contributions | |
orse | -0.038 |
oc | -0.028 |
weapon | -0.026 |
unch | -0.026 |
ggy | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
orse | +0.369 |
weapon | +0.284 |
oc | +0.283 |
bone | +0.267 |
uddy | +0.264 |
Neg logit contributions | |
groom | -0.386 |
roses | -0.359 |
register | -0.349 |
decides | -0.345 |
ponies | -0.335 |
Token | hands |
Token ID | 2832 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
orse | +0.304 |
oc | +0.248 |
weapon | +0.244 |
unch | +0.236 |
uddy | +0.233 |
Neg logit contributions | |
groom | -0.218 |
roses | -0.200 |
decides | -0.188 |
register | -0.187 |
ponies | -0.183 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
orse | +0.161 |
oc | +0.130 |
weapon | +0.127 |
uddy | +0.122 |
Carl | +0.119 |
Neg logit contributions | |
groom | -0.132 |
roses | -0.121 |
register | -0.118 |
decides | -0.114 |
ponies | -0.112 |
Token | " |
Token ID | 366 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.007 |
register | +0.007 |
decides | +0.007 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.007 |
weapon | -0.005 |
oc | -0.005 |
oy | -0.005 |
ggy | -0.005 |
Token | And |
Token ID | 1870 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
groom | +0.225 |
register | +0.221 |
roses | +0.213 |
decides | +0.200 |
ponies | +0.196 |
Neg logit contributions | |
orse | -0.308 |
oc | -0.252 |
weapon | -0.237 |
hockey | -0.234 |
puck | -0.233 |
Token | I |
Token ID | 314 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
groom | +0.012 |
register | +0.012 |
roses | +0.012 |
decides | +0.011 |
ponies | +0.011 |
Neg logit contributions | |
orse | -0.013 |
weapon | -0.010 |
oc | -0.010 |
Carl | -0.009 |
bone | -0.009 |
Token | for |
Token ID | 329 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
orse | +0.394 |
weapon | +0.314 |
oc | +0.308 |
bone | +0.301 |
uddy | +0.292 |
Neg logit contributions | |
groom | -0.391 |
roses | -0.361 |
decides | -0.349 |
register | -0.345 |
ponies | -0.332 |
Token | you |
Token ID | 345 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
orse | +0.203 |
oc | +0.166 |
weapon | +0.164 |
uddy | +0.156 |
bone | +0.153 |
Neg logit contributions | |
groom | -0.163 |
roses | -0.150 |
register | -0.145 |
ponies | -0.140 |
decides | -0.139 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
orse | +0.226 |
weapon | +0.180 |
oc | +0.178 |
bone | +0.172 |
uddy | +0.168 |
Neg logit contributions | |
groom | -0.186 |
roses | -0.172 |
register | -0.166 |
decides | -0.163 |
ponies | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
groom | +0.119 |
roses | +0.115 |
Angel | +0.110 |
register | +0.110 |
her | +0.107 |
Neg logit contributions | |
orse | -0.136 |
weapon | -0.117 |
oc | -0.108 |
inations | -0.108 |
puck | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
groom | +0.010 |
She | +0.010 |
roses | +0.010 |
Angel | +0.009 |
ponies | +0.009 |
Neg logit contributions | |
orse | -0.013 |
weapon | -0.012 |
puck | -0.011 |
tentacles | -0.011 |
bullets | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
groom | +0.012 |
She | +0.011 |
roses | +0.011 |
register | +0.010 |
decides | +0.010 |
Neg logit contributions | |
orse | -0.015 |
weapon | -0.012 |
oc | -0.011 |
burying | -0.011 |
tentacles | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
orse | +0.094 |
weapon | +0.076 |
oc | +0.073 |
bone | +0.072 |
puck | +0.070 |
Neg logit contributions | |
groom | -0.084 |
roses | -0.078 |
register | -0.075 |
decides | -0.075 |
ponies | -0.072 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
orse | +0.110 |
oc | +0.091 |
weapon | +0.090 |
unch | +0.088 |
uddy | +0.087 |
Neg logit contributions | |
groom | -0.052 |
roses | -0.046 |
register | -0.044 |
decides | -0.043 |
ponies | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
orse | +0.157 |
weapon | +0.134 |
unch | +0.125 |
uddy | +0.122 |
bullets | +0.122 |
Neg logit contributions | |
groom | -0.130 |
decides | -0.122 |
roses | -0.115 |
register | -0.114 |
nurses | -0.108 |
Token | so |
Token ID | 523 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
orse | +0.085 |
weapon | +0.066 |
oc | +0.066 |
bone | +0.063 |
ggy | +0.062 |
Neg logit contributions | |
groom | -0.083 |
roses | -0.077 |
register | -0.075 |
decides | -0.074 |
ponies | -0.071 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
orse | +0.007 |
weapon | +0.006 |
puck | +0.006 |
oc | +0.006 |
bone | +0.006 |
Neg logit contributions | |
groom | -0.006 |
decides | -0.006 |
roses | -0.005 |
register | -0.005 |
ponies | -0.005 |
Token | prisoner |
Token ID | 17234 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
groom | +0.037 |
roses | +0.035 |
register | +0.033 |
decides | +0.033 |
ponies | +0.031 |
Neg logit contributions | |
orse | -0.041 |
oc | -0.033 |
weapon | -0.032 |
unch | -0.031 |
uddy | -0.030 |
Token | now |
Token ID | 783 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
orse | +0.189 |
weapon | +0.148 |
oc | +0.146 |
bone | +0.139 |
ggy | +0.137 |
Neg logit contributions | |
groom | -0.190 |
roses | -0.176 |
register | -0.172 |
decides | -0.170 |
ponies | -0.164 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
groom | +0.303 |
roses | +0.278 |
register | +0.271 |
decides | +0.268 |
ponies | +0.260 |
Neg logit contributions | |
orse | -0.333 |
oc | -0.262 |
weapon | -0.260 |
uddy | -0.248 |
unch | -0.248 |
Token | it |
Token ID | 340 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
groom | +0.113 |
roses | +0.104 |
register | +0.099 |
decides | +0.098 |
ponies | +0.092 |
Neg logit contributions | |
orse | -0.151 |
oc | -0.125 |
weapon | -0.123 |
bone | -0.119 |
uddy | -0.119 |
Token | said |
Token ID | 531 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
orse | +0.025 |
unch | +0.020 |
weapon | +0.020 |
oc | +0.020 |
bone | +0.019 |
Neg logit contributions | |
groom | -0.022 |
roses | -0.020 |
decides | -0.020 |
register | -0.019 |
Angel | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
orse | +0.164 |
oc | +0.133 |
weapon | +0.131 |
bone | +0.125 |
uddy | +0.123 |
Neg logit contributions | |
groom | -0.144 |
roses | -0.132 |
register | -0.129 |
decides | -0.124 |
ponies | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
orse | +0.005 |
weapon | +0.004 |
oc | +0.004 |
bone | +0.004 |
oy | +0.004 |
Neg logit contributions | |
groom | -0.005 |
roses | -0.005 |
register | -0.004 |
decides | -0.004 |
ponies | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.008 |
decides | +0.008 |
register | +0.007 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.008 |
weapon | -0.006 |
oc | -0.006 |
bone | -0.006 |
puck | -0.006 |
Token | J |
Token ID | 41 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.007 |
register | +0.007 |
decides | +0.007 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.007 |
weapon | -0.006 |
oc | -0.006 |
bone | -0.005 |
ggy | -0.005 |
Token | ill |
Token ID | 359 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
orse | +0.112 |
oc | +0.092 |
weapon | +0.089 |
bone | +0.087 |
puck | +0.085 |
Neg logit contributions | |
groom | -0.089 |
roses | -0.084 |
register | -0.083 |
decides | -0.082 |
ponies | -0.075 |
Token | was |
Token ID | 373 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
orse | +0.100 |
weapon | +0.079 |
oc | +0.078 |
bone | +0.075 |
unch | +0.075 |
Neg logit contributions | |
groom | -0.100 |
roses | -0.092 |
decides | -0.090 |
register | -0.089 |
ponies | -0.085 |
Token | be |
Token ID | 307 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
orse | +0.018 |
oc | +0.014 |
weapon | +0.014 |
bone | +0.014 |
uddy | +0.013 |
Neg logit contributions | |
groom | -0.014 |
roses | -0.012 |
register | -0.012 |
decides | -0.012 |
ponies | -0.011 |
Token | flexible |
Token ID | 12846 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
orse | +0.229 |
hockey | +0.174 |
weapon | +0.173 |
ggy | +0.167 |
burying | +0.164 |
Neg logit contributions | |
groom | -0.291 |
register | -0.289 |
roses | -0.288 |
decides | -0.282 |
als | -0.281 |
Token | and |
Token ID | 290 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
orse | +0.127 |
weapon | +0.103 |
oc | +0.100 |
bone | +0.097 |
hockey | +0.096 |
Neg logit contributions | |
groom | -0.128 |
roses | -0.118 |
register | -0.116 |
decides | -0.114 |
ponies | -0.109 |
Token | do |
Token ID | 466 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
groom | +0.027 |
roses | +0.025 |
register | +0.024 |
decides | +0.023 |
ponies | +0.023 |
Neg logit contributions | |
orse | -0.030 |
weapon | -0.024 |
oc | -0.024 |
bone | -0.023 |
Carl | -0.022 |
Token | different |
Token ID | 1180 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
orse | +0.382 |
weapon | +0.302 |
oc | +0.297 |
ggy | +0.285 |
bone | +0.283 |
Neg logit contributions | |
groom | -0.345 |
roses | -0.316 |
register | -0.313 |
decides | -0.303 |
ponies | -0.295 |
Token | things |
Token ID | 1243 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
orse | +0.045 |
weapon | +0.036 |
oc | +0.035 |
bone | +0.034 |
Carl | +0.033 |
Neg logit contributions | |
groom | -0.041 |
roses | -0.038 |
register | -0.037 |
decides | -0.036 |
ponies | -0.035 |
Token | for |
Token ID | 329 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
orse | +0.103 |
weapon | +0.082 |
oc | +0.080 |
hockey | +0.078 |
bone | +0.078 |
Neg logit contributions | |
groom | -0.101 |
roses | -0.093 |
register | -0.090 |
decides | -0.090 |
ponies | -0.087 |
Token | fun |
Token ID | 1257 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
orse | +0.195 |
weapon | +0.156 |
oc | +0.154 |
bone | +0.148 |
ggy | +0.147 |
Neg logit contributions | |
groom | -0.154 |
roses | -0.142 |
register | -0.138 |
decides | -0.136 |
ponies | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
orse | +0.302 |
weapon | +0.241 |
oc | +0.239 |
bone | +0.228 |
ggy | +0.226 |
Neg logit contributions | |
groom | -0.252 |
roses | -0.229 |
register | -0.225 |
decides | -0.221 |
ponies | -0.211 |
Token | That |
Token ID | 1320 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
groom | +0.005 |
roses | +0.005 |
register | +0.005 |
decides | +0.005 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.005 |
weapon | -0.004 |
oc | -0.004 |
bone | -0.003 |
uddy | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
orse | +0.279 |
weapon | +0.223 |
oc | +0.220 |
bone | +0.211 |
ggy | +0.205 |
Neg logit contributions | |
groom | -0.264 |
roses | -0.244 |
register | -0.239 |
decides | -0.231 |
ponies | -0.226 |
Token | have |
Token ID | 423 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
groom | +0.017 |
register | +0.016 |
roses | +0.016 |
decides | +0.015 |
ponies | +0.015 |
Neg logit contributions | |
orse | -0.019 |
weapon | -0.016 |
bone | -0.015 |
Carl | -0.015 |
oc | -0.015 |
Token | fun |
Token ID | 1257 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
orse | +0.083 |
weapon | +0.062 |
oc | +0.060 |
bone | +0.059 |
hockey | +0.057 |
Neg logit contributions | |
groom | -0.102 |
roses | -0.095 |
register | -0.095 |
decides | -0.093 |
ponies | -0.089 |
Token | ." |
Token ID | 526 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
orse | +0.290 |
weapon | +0.230 |
oc | +0.225 |
hockey | +0.220 |
bone | +0.217 |
Neg logit contributions | |
groom | -0.275 |
register | -0.257 |
roses | -0.249 |
decides | -0.244 |
ponies | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
groom | +0.582 |
register | +0.540 |
roses | +0.537 |
decides | +0.524 |
ponies | +0.514 |
Neg logit contributions | |
orse | -0.376 |
oc | -0.263 |
weapon | -0.256 |
Carl | -0.250 |
uddy | -0.243 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
groom | +0.011 |
roses | +0.010 |
decides | +0.010 |
register | +0.010 |
ponies | +0.010 |
Neg logit contributions | |
orse | -0.010 |
weapon | -0.008 |
oc | -0.007 |
puck | -0.007 |
bone | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
groom | +0.011 |
roses | +0.010 |
register | +0.010 |
decides | +0.010 |
ponies | +0.010 |
Neg logit contributions | |
orse | -0.013 |
oc | -0.011 |
weapon | -0.010 |
ggy | -0.010 |
bone | -0.010 |
Token | By |
Token ID | 3886 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
groom | +0.252 |
register | +0.252 |
roses | +0.248 |
decides | +0.241 |
ponies | +0.228 |
Neg logit contributions | |
orse | -0.328 |
hockey | -0.257 |
puck | -0.253 |
unch | -0.249 |
oc | -0.249 |
Token | e |
Token ID | 68 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
orse | +0.071 |
ggy | +0.044 |
oc | +0.044 |
hockey | +0.041 |
oy | +0.040 |
Neg logit contributions | |
groom | -0.150 |
register | -0.150 |
roses | -0.148 |
decides | -0.144 |
ponies | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
orse | +0.452 |
weapon | +0.348 |
oc | +0.345 |
bone | +0.326 |
uddy | +0.321 |
Neg logit contributions | |
groom | -0.481 |
roses | -0.448 |
register | -0.437 |
decides | -0.431 |
ponies | -0.418 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
groom | +0.054 |
register | +0.050 |
roses | +0.050 |
decides | +0.048 |
ponies | +0.046 |
Neg logit contributions | |
orse | -0.068 |
weapon | -0.055 |
oc | -0.054 |
Carl | -0.053 |
bone | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
groom | +0.293 |
roses | +0.271 |
register | +0.267 |
decides | +0.260 |
ponies | +0.252 |
Neg logit contributions | |
orse | -0.286 |
oc | -0.226 |
weapon | -0.219 |
oy | -0.212 |
bone | -0.211 |
Token | moment |
Token ID | 2589 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
groom | +0.017 |
roses | +0.016 |
register | +0.015 |
decides | +0.015 |
ponies | +0.015 |
Neg logit contributions | |
orse | -0.018 |
oc | -0.014 |
uddy | -0.014 |
weapon | -0.014 |
unch | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
orse | +0.174 |
oc | +0.141 |
weapon | +0.138 |
puck | +0.134 |
unch | +0.133 |
Neg logit contributions | |
groom | -0.154 |
register | -0.143 |
roses | -0.143 |
ponies | -0.138 |
her | -0.131 |
Token | He |
Token ID | 679 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
orse | +0.005 |
weapon | +0.005 |
inations | +0.005 |
oy | +0.005 |
bullets | +0.004 |
Neg logit contributions | |
decides | -0.004 |
Angel | -0.004 |
roses | -0.004 |
groom | -0.003 |
ponies | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
orse | +0.262 |
oc | +0.203 |
weapon | +0.198 |
bone | +0.185 |
ggy | +0.184 |
Neg logit contributions | |
groom | -0.291 |
roses | -0.276 |
register | -0.271 |
ponies | -0.258 |
decides | -0.255 |
Token | very |
Token ID | 845 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
orse | +0.088 |
weapon | +0.065 |
ggy | +0.064 |
oc | +0.064 |
hockey | +0.063 |
Neg logit contributions | |
groom | -0.093 |
roses | -0.089 |
register | -0.087 |
decides | -0.085 |
ponies | -0.083 |
Token | glad |
Token ID | 9675 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
groom | +0.171 |
roses | +0.153 |
decides | +0.150 |
register | +0.149 |
ponies | +0.142 |
Neg logit contributions | |
orse | -0.169 |
weapon | -0.135 |
oc | -0.133 |
uddy | -0.129 |
bone | -0.128 |
Token | he |
Token ID | 339 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
groom | +0.073 |
roses | +0.072 |
ponies | +0.066 |
her | +0.066 |
decides | +0.064 |
Neg logit contributions | |
orse | -0.090 |
oc | -0.075 |
uddy | -0.070 |
weapon | -0.070 |
inations | -0.069 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
orse | +0.307 |
weapon | +0.231 |
oc | +0.226 |
unch | +0.217 |
uddy | +0.215 |
Neg logit contributions | |
groom | -0.377 |
roses | -0.346 |
register | -0.343 |
decides | -0.343 |
ponies | -0.327 |
Token | his |
Token ID | 465 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
groom | +0.123 |
roses | +0.116 |
register | +0.111 |
decides | +0.108 |
ponies | +0.107 |
Neg logit contributions | |
orse | -0.150 |
oc | -0.117 |
weapon | -0.116 |
uddy | -0.114 |
unch | -0.112 |
Token | wife |
Token ID | 3656 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
orse | +0.377 |
weapon | +0.316 |
oc | +0.315 |
bone | +0.303 |
uddy | +0.300 |
Neg logit contributions | |
groom | -0.175 |
roses | -0.155 |
register | -0.149 |
decides | -0.145 |
ponies | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
groom | +0.368 |
roses | +0.334 |
register | +0.328 |
decides | +0.322 |
ponies | +0.315 |
Neg logit contributions | |
orse | -0.429 |
weapon | -0.343 |
uddy | -0.343 |
oc | -0.339 |
puck | -0.330 |
Token | there |
Token ID | 612 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
groom | +0.113 |
roses | +0.109 |
ponies | +0.100 |
register | +0.100 |
decides | +0.099 |
Neg logit contributions | |
orse | -0.175 |
oc | -0.141 |
uddy | -0.140 |
weapon | -0.136 |
unch | -0.135 |
Token | was |
Token ID | 373 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
orse | +0.069 |
oc | +0.056 |
weapon | +0.054 |
emy | +0.054 |
oy | +0.053 |
Neg logit contributions | |
groom | -0.049 |
roses | -0.047 |
decides | -0.046 |
register | -0.045 |
ponies | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
orse | +0.106 |
weapon | +0.084 |
oc | +0.084 |
bone | +0.080 |
uddy | +0.079 |
Neg logit contributions | |
groom | -0.087 |
roses | -0.081 |
register | -0.078 |
decides | -0.077 |
ponies | -0.074 |
Token | silver |
Token ID | 8465 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
groom | +0.008 |
roses | +0.007 |
register | +0.007 |
decides | +0.007 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.009 |
oy | -0.007 |
oc | -0.007 |
unch | -0.007 |
uddy | -0.007 |
Token | thing |
Token ID | 1517 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
orse | +0.156 |
oc | +0.123 |
weapon | +0.123 |
uddy | +0.117 |
Carl | +0.116 |
Neg logit contributions | |
groom | -0.127 |
roses | -0.117 |
register | -0.113 |
decides | -0.110 |
ponies | -0.107 |
Token | far |
Token ID | 1290 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
orse | +0.115 |
oc | +0.096 |
weapon | +0.089 |
unch | +0.088 |
oy | +0.088 |
Neg logit contributions | |
groom | -0.076 |
roses | -0.073 |
register | -0.072 |
decides | -0.067 |
ponies | -0.066 |
Token | away |
Token ID | 1497 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
groom | +0.050 |
roses | +0.042 |
register | +0.039 |
decides | +0.038 |
ponies | +0.034 |
Neg logit contributions | |
orse | -0.178 |
weapon | -0.150 |
oc | -0.150 |
unch | -0.145 |
bone | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
groom | +0.165 |
roses | +0.159 |
register | +0.151 |
decides | +0.144 |
ponies | +0.142 |
Neg logit contributions | |
orse | -0.256 |
oc | -0.199 |
unch | -0.197 |
uddy | -0.197 |
weapon | -0.195 |
Token | So |
Token ID | 1406 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
orse | +0.014 |
inations | +0.012 |
oy | +0.012 |
ggy | +0.011 |
rim | +0.011 |
Neg logit contributions | |
She | -0.011 |
Angel | -0.011 |
decides | -0.011 |
roses | -0.011 |
She | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
orse | +0.209 |
unch | +0.171 |
inations | +0.160 |
rig | +0.150 |
rim | +0.146 |
Neg logit contributions | |
groom | -0.240 |
her | -0.237 |
roses | -0.233 |
decides | -0.229 |
Angel | -0.227 |
Token | mouse |
Token ID | 10211 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
groom | +0.004 |
roses | +0.004 |
register | +0.004 |
decides | +0.004 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.007 |
unch | -0.005 |
oy | -0.005 |
oc | -0.005 |
uddy | -0.005 |
Token | And |
Token ID | 843 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
orse | +0.023 |
oc | +0.017 |
weapon | +0.016 |
bone | +0.016 |
Carl | +0.015 |
Neg logit contributions | |
groom | -0.036 |
roses | -0.033 |
register | -0.033 |
ponies | -0.032 |
decides | -0.031 |
Token | maybe |
Token ID | 3863 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
orse | +0.117 |
weapon | +0.090 |
hockey | +0.086 |
Carl | +0.086 |
oc | +0.086 |
Neg logit contributions | |
groom | -0.119 |
register | -0.111 |
roses | -0.110 |
decides | -0.107 |
ponies | -0.105 |
Token | later |
Token ID | 1568 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
groom | +0.487 |
register | +0.460 |
roses | +0.447 |
decides | +0.445 |
ponies | +0.439 |
Neg logit contributions | |
orse | -0.380 |
weapon | -0.282 |
hockey | -0.278 |
oy | -0.271 |
bone | -0.264 |
Token | , |
Token ID | 11 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.006 |
ggy | +0.006 |
bone | +0.006 |
hockey | +0.006 |
Neg logit contributions | |
groom | -0.012 |
roses | -0.011 |
register | -0.011 |
decides | -0.011 |
ponies | -0.011 |
Token | we |
Token ID | 356 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
groom | +0.029 |
register | +0.027 |
roses | +0.027 |
decides | +0.026 |
ponies | +0.025 |
Neg logit contributions | |
orse | -0.029 |
weapon | -0.022 |
hockey | -0.022 |
bone | -0.021 |
oc | -0.021 |
Token | can |
Token ID | 460 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
orse | +0.110 |
oc | +0.091 |
weapon | +0.089 |
bone | +0.084 |
Carl | +0.080 |
Neg logit contributions | |
groom | -0.104 |
roses | -0.099 |
ponies | -0.094 |
register | -0.093 |
pastor | -0.085 |
Token | play |
Token ID | 711 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
groom | +0.343 |
roses | +0.328 |
register | +0.323 |
ponies | +0.319 |
decides | +0.310 |
Neg logit contributions | |
orse | -0.349 |
weapon | -0.266 |
hockey | -0.262 |
Carl | -0.257 |
oc | -0.254 |
Token | dress |
Token ID | 6576 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
orse | +0.176 |
hockey | +0.141 |
weapon | +0.140 |
oc | +0.135 |
puck | +0.133 |
Neg logit contributions | |
groom | -0.173 |
roses | -0.162 |
register | -0.160 |
decides | -0.158 |
ponies | -0.152 |
Token | up |
Token ID | 510 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
groom | +0.127 |
decides | +0.118 |
register | +0.116 |
roses | +0.116 |
ponies | +0.108 |
Neg logit contributions | |
orse | -0.108 |
hockey | -0.089 |
ggy | -0.087 |
oc | -0.087 |
weapon | -0.086 |
Token | with |
Token ID | 351 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
groom | +0.274 |
register | +0.252 |
roses | +0.251 |
decides | +0.244 |
ponies | +0.235 |
Neg logit contributions | |
orse | -0.281 |
weapon | -0.220 |
oc | -0.219 |
bone | -0.209 |
hockey | -0.209 |
Token | your |
Token ID | 534 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
orse | +0.312 |
weapon | +0.247 |
hockey | +0.243 |
bone | +0.238 |
oc | +0.237 |
Neg logit contributions | |
groom | -0.258 |
register | -0.239 |
decides | -0.237 |
roses | -0.236 |
ponies | -0.222 |
Token | ama |
Token ID | 1689 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
groom | +0.398 |
roses | +0.379 |
register | +0.377 |
ponies | +0.359 |
decides | +0.354 |
Neg logit contributions | |
orse | -0.365 |
weapon | -0.293 |
hockey | -0.279 |
puck | -0.277 |
bone | -0.275 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
groom | +0.044 |
roses | +0.041 |
register | +0.039 |
decides | +0.039 |
ponies | +0.038 |
Neg logit contributions | |
orse | -0.043 |
weapon | -0.035 |
oc | -0.035 |
unch | -0.033 |
puck | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
groom | +0.011 |
roses | +0.010 |
decides | +0.010 |
register | +0.009 |
ponies | +0.009 |
Neg logit contributions | |
orse | -0.011 |
weapon | -0.008 |
oc | -0.008 |
unch | -0.008 |
puck | -0.008 |
Token | yes |
Token ID | 3763 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
orse | +0.141 |
oc | +0.110 |
weapon | +0.110 |
bone | +0.103 |
uddy | +0.102 |
Neg logit contributions | |
groom | -0.148 |
roses | -0.137 |
register | -0.133 |
decides | -0.131 |
ponies | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -7.00e-02 |
Pos logit contributions | |
groom | +0.038 |
register | +0.037 |
decides | +0.036 |
back | +0.035 |
roses | +0.035 |
Neg logit contributions | |
orse | -0.058 |
puck | -0.044 |
unch | -0.044 |
oc | -0.044 |
weapon | -0.044 |
Token | She |
Token ID | 1375 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
groom | +0.004 |
roses | +0.004 |
register | +0.004 |
decides | +0.004 |
Angel | +0.003 |
Neg logit contributions | |
orse | -0.004 |
weapon | -0.003 |
ggy | -0.003 |
inations | -0.003 |
oc | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
groom | +0.356 |
roses | +0.326 |
decides | +0.314 |
register | +0.313 |
ponies | +0.302 |
Neg logit contributions | |
orse | -0.361 |
weapon | -0.286 |
oc | -0.283 |
bone | -0.267 |
unch | -0.266 |
Token | a |
Token ID | 257 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
orse | +0.082 |
weapon | +0.062 |
oc | +0.062 |
bone | +0.059 |
ggy | +0.059 |
Neg logit contributions | |
groom | -0.084 |
roses | -0.079 |
register | -0.077 |
decides | -0.076 |
ponies | -0.073 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
groom | +0.021 |
roses | +0.019 |
register | +0.018 |
decides | +0.018 |
ponies | +0.017 |
Neg logit contributions | |
orse | -0.022 |
weapon | -0.017 |
unch | -0.017 |
uddy | -0.017 |
oc | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
orse | +0.009 |
weapon | +0.007 |
oc | +0.007 |
ggy | +0.007 |
puck | +0.007 |
Neg logit contributions | |
groom | -0.008 |
roses | -0.007 |
register | -0.007 |
ponies | -0.007 |
decides | -0.007 |
Token | obedient |
Token ID | 41652 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
groom | +0.061 |
roses | +0.057 |
ponies | +0.053 |
decides | +0.052 |
nurses | +0.051 |
Neg logit contributions | |
orse | -0.064 |
oc | -0.051 |
uddy | -0.050 |
unch | -0.049 |
weapon | -0.049 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
groom | +0.306 |
roses | +0.285 |
register | +0.280 |
decides | +0.268 |
ponies | +0.264 |
Neg logit contributions | |
orse | -0.362 |
weapon | -0.288 |
oc | -0.283 |
bone | -0.272 |
oy | -0.268 |
Token | her |
Token ID | 607 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
groom | +0.255 |
decides | +0.241 |
register | +0.230 |
roses | +0.217 |
als | +0.215 |
Neg logit contributions | |
Tim | -0.303 |
orse | -0.290 |
Andy | -0.287 |
Benny | -0.280 |
His | -0.270 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
groom | +0.318 |
register | +0.284 |
roses | +0.284 |
decides | +0.280 |
ponies | +0.263 |
Neg logit contributions | |
orse | -0.430 |
weapon | -0.365 |
bone | -0.352 |
oc | -0.342 |
Carl | -0.338 |
Token | , |
Token ID | 11 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
groom | +0.330 |
roses | +0.294 |
decides | +0.284 |
register | +0.280 |
pan | +0.277 |
Neg logit contributions | |
orse | -0.194 |
weapon | -0.159 |
bone | -0.152 |
Carl | -0.149 |
Benny | -0.147 |
Token | " |
Token ID | 366 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
groom | +0.040 |
decides | +0.037 |
roses | +0.037 |
register | +0.037 |
ponies | +0.035 |
Neg logit contributions | |
orse | -0.033 |
weapon | -0.025 |
Carl | -0.025 |
bone | -0.024 |
Andy | -0.024 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
register | +0.182 |
roses | +0.180 |
groom | +0.179 |
pan | +0.175 |
ponies | +0.172 |
Neg logit contributions | |
orse | -0.234 |
oc | -0.229 |
Tim | -0.210 |
Joe | -0.204 |
bone | -0.198 |
Token | you |
Token ID | 345 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
groom | +0.710 |
register | +0.667 |
roses | +0.648 |
decides | +0.639 |
ponies | +0.618 |
Neg logit contributions | |
orse | -0.518 |
weapon | -0.379 |
Carl | -0.361 |
bone | -0.358 |
Andy | -0.354 |
Token | show |
Token ID | 905 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
orse | +0.279 |
oc | +0.228 |
weapon | +0.224 |
uddy | +0.220 |
unch | +0.218 |
Neg logit contributions | |
groom | -0.177 |
roses | -0.157 |
decides | -0.150 |
register | -0.149 |
ponies | -0.140 |
Token | me |
Token ID | 502 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
register | +0.026 |
decides | +0.025 |
groom | +0.025 |
pan | +0.024 |
salon | +0.023 |
Neg logit contributions | |
orse | -0.025 |
Benny | -0.022 |
Carl | -0.022 |
Andy | -0.022 |
Sammy | -0.021 |
Token | some |
Token ID | 617 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
groom | +0.144 |
register | +0.134 |
decides | +0.131 |
roses | +0.127 |
ponies | +0.125 |
Neg logit contributions | |
orse | -0.148 |
weapon | -0.120 |
Carl | -0.112 |
bone | -0.110 |
hockey | -0.109 |
Token | animals |
Token ID | 4695 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
groom | +0.187 |
roses | +0.182 |
decides | +0.168 |
ponies | +0.165 |
register | +0.165 |
Neg logit contributions | |
orse | -0.225 |
oc | -0.174 |
uddy | -0.171 |
weapon | -0.169 |
unch | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
groom | +0.111 |
roses | +0.106 |
decides | +0.101 |
register | +0.100 |
ponies | +0.096 |
Neg logit contributions | |
orse | -0.140 |
oc | -0.114 |
weapon | -0.113 |
oy | -0.108 |
uddy | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
groom | +0.005 |
roses | +0.005 |
register | +0.005 |
decides | +0.005 |
ponies | +0.005 |
Neg logit contributions | |
orse | -0.004 |
weapon | -0.003 |
oc | -0.003 |
bone | -0.003 |
uddy | -0.003 |
Token | Tom |
Token ID | 13787 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
groom | +0.005 |
roses | +0.005 |
register | +0.005 |
decides | +0.005 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.005 |
oc | -0.004 |
weapon | -0.004 |
ggy | -0.004 |
bone | -0.004 |
Token | hugged |
Token ID | 41130 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
orse | +0.245 |
weapon | +0.196 |
oc | +0.195 |
unch | +0.187 |
hockey | +0.182 |
Neg logit contributions | |
groom | -0.201 |
decides | -0.185 |
roses | -0.183 |
register | -0.175 |
Angel | -0.165 |
Token | her |
Token ID | 607 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
groom | +0.361 |
register | +0.333 |
roses | +0.327 |
decides | +0.308 |
ponies | +0.304 |
Neg logit contributions | |
orse | -0.240 |
Tim | -0.204 |
weapon | -0.202 |
Benny | -0.202 |
His | -0.198 |
Token | back |
Token ID | 736 |
Feature activation | -8.97e+00 |
Pos logit contributions | |
groom | +0.378 |
roses | +0.343 |
register | +0.336 |
decides | +0.331 |
ponies | +0.312 |
Neg logit contributions | |
orse | -0.399 |
weapon | -0.338 |
bone | -0.328 |
oc | -0.321 |
hockey | -0.308 |
Token | and |
Token ID | 290 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
groom | +0.570 |
roses | +0.524 |
register | +0.515 |
decides | +0.504 |
ponies | +0.485 |
Neg logit contributions | |
orse | -0.505 |
weapon | -0.394 |
oc | -0.393 |
bone | -0.370 |
uddy | -0.362 |
Token | said |
Token ID | 531 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
groom | +0.015 |
roses | +0.014 |
register | +0.013 |
decides | +0.013 |
ponies | +0.013 |
Neg logit contributions | |
orse | -0.015 |
weapon | -0.011 |
oc | -0.011 |
bone | -0.011 |
uddy | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
orse | +0.156 |
weapon | +0.120 |
oc | +0.118 |
bone | +0.112 |
ggy | +0.111 |
Neg logit contributions | |
groom | -0.168 |
roses | -0.156 |
register | -0.152 |
decides | -0.150 |
ponies | -0.146 |
Token | " |
Token ID | 366 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
groom | +0.043 |
roses | +0.040 |
register | +0.039 |
decides | +0.038 |
ponies | +0.037 |
Neg logit contributions | |
orse | -0.052 |
weapon | -0.042 |
oc | -0.042 |
bone | -0.040 |
uddy | -0.039 |
Token | It |
Token ID | 1026 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
groom | +0.155 |
roses | +0.131 |
She | +0.129 |
decides | +0.129 |
Angel | +0.115 |
Neg logit contributions | |
orse | -0.339 |
weapon | -0.298 |
oy | -0.288 |
burying | -0.284 |
inations | -0.282 |
Token | and |
Token ID | 290 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
groom | +0.026 |
roses | +0.024 |
register | +0.024 |
decides | +0.023 |
ponies | +0.023 |
Neg logit contributions | |
orse | -0.024 |
weapon | -0.019 |
oc | -0.018 |
bone | -0.018 |
hockey | -0.017 |
Token | laughed |
Token ID | 13818 |
Feature activation | +4.97e+00 |
Pos logit contributions | |
groom | +0.032 |
roses | +0.029 |
register | +0.029 |
decides | +0.028 |
ponies | +0.027 |
Neg logit contributions | |
orse | -0.033 |
weapon | -0.026 |
oc | -0.026 |
bone | -0.024 |
Carl | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
orse | +0.262 |
weapon | +0.199 |
oc | +0.192 |
bone | +0.189 |
hockey | +0.188 |
Neg logit contributions | |
groom | -0.325 |
register | -0.301 |
roses | -0.300 |
decides | -0.293 |
ponies | -0.280 |
Token | They |
Token ID | 1119 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
groom | +0.008 |
register | +0.007 |
roses | +0.007 |
decides | +0.007 |
ponies | +0.007 |
Neg logit contributions | |
orse | -0.005 |
oc | -0.003 |
weapon | -0.003 |
Carl | -0.003 |
bone | -0.003 |
Token | cut |
Token ID | 2005 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
orse | +0.035 |
weapon | +0.026 |
oc | +0.026 |
bone | +0.025 |
puck | +0.024 |
Neg logit contributions | |
groom | -0.038 |
roses | -0.036 |
register | -0.036 |
decides | -0.035 |
ponies | -0.034 |
Token | out |
Token ID | 503 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
orse | +0.011 |
weapon | +0.009 |
oc | +0.009 |
Carl | +0.009 |
bone | +0.009 |
Neg logit contributions | |
groom | -0.009 |
roses | -0.008 |
register | -0.008 |
decides | -0.008 |
ponies | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
groom | +0.415 |
roses | +0.375 |
register | +0.375 |
decides | +0.368 |
ponies | +0.350 |
Neg logit contributions | |
orse | -0.522 |
weapon | -0.422 |
oc | -0.417 |
bone | -0.402 |
Carl | -0.395 |
Token | favorite |
Token ID | 4004 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
groom | +0.011 |
roses | +0.011 |
decides | +0.009 |
ponies | +0.009 |
register | +0.009 |
Neg logit contributions | |
orse | -0.021 |
unch | -0.018 |
Carl | -0.017 |
uddy | -0.017 |
oc | -0.017 |
Token | pictures |
Token ID | 5986 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
orse | +0.186 |
weapon | +0.150 |
oc | +0.149 |
uddy | +0.143 |
bone | +0.142 |
Neg logit contributions | |
groom | -0.133 |
roses | -0.122 |
register | -0.117 |
decides | -0.115 |
ponies | -0.111 |
Token | and |
Token ID | 290 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
groom | +0.168 |
roses | +0.156 |
register | +0.152 |
decides | +0.149 |
ponies | +0.145 |
Neg logit contributions | |
orse | -0.169 |
weapon | -0.132 |
oc | -0.131 |
bone | -0.124 |
uddy | -0.123 |
Token | glued |
Token ID | 39783 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
groom | +0.028 |
roses | +0.026 |
register | +0.025 |
decides | +0.025 |
ponies | +0.024 |
Neg logit contributions | |
orse | -0.033 |
weapon | -0.026 |
oc | -0.026 |
bone | -0.025 |
uddy | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
orse | +0.031 |
weapon | +0.026 |
puck | +0.024 |
oy | +0.024 |
bullets | +0.023 |
Neg logit contributions | |
groom | -0.025 |
roses | -0.024 |
decides | -0.023 |
She | -0.022 |
register | -0.022 |
Token | They |
Token ID | 2990 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
orse | +0.029 |
oc | +0.023 |
weapon | +0.022 |
bone | +0.021 |
ggy | +0.021 |
Neg logit contributions | |
groom | -0.032 |
roses | -0.030 |
register | -0.029 |
decides | -0.028 |
ponies | -0.028 |
Token | went |
Token ID | 1816 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
groom | +0.055 |
roses | +0.053 |
decides | +0.050 |
register | +0.050 |
ponies | +0.050 |
Neg logit contributions | |
orse | -0.056 |
oc | -0.043 |
weapon | -0.043 |
oy | -0.042 |
bone | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
groom | +0.275 |
decides | +0.253 |
roses | +0.251 |
register | +0.239 |
ponies | +0.229 |
Neg logit contributions | |
orse | -0.209 |
weapon | -0.169 |
fishing | -0.169 |
hockey | -0.166 |
bone | -0.160 |
Token | the |
Token ID | 262 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
orse | +0.066 |
weapon | +0.053 |
oc | +0.052 |
bone | +0.051 |
hockey | +0.050 |
Neg logit contributions | |
groom | -0.057 |
roses | -0.053 |
register | -0.052 |
decides | -0.051 |
ponies | -0.049 |
Token | store |
Token ID | 3650 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
bone | +0.026 |
hockey | +0.025 |
golf | +0.025 |
weapon | +0.025 |
orse | +0.023 |
Neg logit contributions | |
groom | -0.022 |
roses | -0.021 |
la | -0.021 |
decides | -0.021 |
pan | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
groom | +0.453 |
roses | +0.420 |
register | +0.414 |
decides | +0.401 |
ponies | +0.389 |
Neg logit contributions | |
orse | -0.537 |
weapon | -0.425 |
oc | -0.420 |
bone | -0.399 |
Carl | -0.398 |
Token | found |
Token ID | 1043 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
orse | +0.022 |
weapon | +0.016 |
oc | +0.016 |
Carl | +0.016 |
Benny | +0.016 |
Neg logit contributions | |
groom | -0.024 |
roses | -0.022 |
register | -0.021 |
decides | -0.021 |
ponies | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
orse | +0.065 |
weapon | +0.055 |
bone | +0.055 |
Carl | +0.054 |
Benny | +0.053 |
Neg logit contributions | |
groom | -0.080 |
decides | -0.073 |
roses | -0.070 |
register | -0.068 |
ponies | -0.068 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
orse | +0.031 |
weapon | +0.024 |
oc | +0.024 |
bone | +0.023 |
puck | +0.022 |
Neg logit contributions | |
groom | -0.033 |
roses | -0.030 |
register | -0.030 |
decides | -0.030 |
ponies | -0.029 |
Token | pink |
Token ID | 11398 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
orse | +0.069 |
weapon | +0.058 |
oc | +0.055 |
bone | +0.055 |
hockey | +0.052 |
Neg logit contributions | |
groom | -0.062 |
register | -0.057 |
decides | -0.057 |
roses | -0.056 |
ponies | -0.054 |
Token | brave |
Token ID | 14802 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
groom | +0.024 |
roses | +0.021 |
decides | +0.020 |
register | +0.020 |
nurses | +0.019 |
Neg logit contributions | |
orse | -0.027 |
unch | -0.022 |
oy | -0.021 |
uddy | -0.020 |
oc | -0.020 |
Token | cat |
Token ID | 3797 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
groom | +0.071 |
roses | +0.062 |
register | +0.061 |
decides | +0.060 |
nurses | +0.059 |
Neg logit contributions | |
orse | -0.098 |
unch | -0.079 |
inations | -0.078 |
orses | -0.076 |
oc | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
orse | +0.000 |
inations | +0.000 |
unch | +0.000 |
emo | +0.000 |
puck | +0.000 |
Neg logit contributions | |
groom | -0.000 |
roses | -0.000 |
register | -0.000 |
ponies | -0.000 |
al | -0.000 |
Token | so |
Token ID | 523 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
groom | +0.062 |
roses | +0.058 |
decides | +0.056 |
register | +0.054 |
ponies | +0.053 |
Neg logit contributions | |
orse | -0.074 |
oc | -0.059 |
weapon | -0.058 |
uddy | -0.055 |
unch | -0.055 |
Token | he |
Token ID | 339 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
orse | +0.001 |
unch | +0.001 |
inations | +0.001 |
uddy | +0.001 |
weapon | +0.001 |
Neg logit contributions | |
groom | -0.002 |
her | -0.002 |
decides | -0.002 |
roses | -0.002 |
ponies | -0.002 |
Token | slowly |
Token ID | 6364 |
Feature activation | -9.37e+00 |
Pos logit contributions | |
orse | +0.353 |
weapon | +0.280 |
oc | +0.280 |
bone | +0.266 |
unch | +0.265 |
Neg logit contributions | |
groom | -0.301 |
roses | -0.275 |
register | -0.265 |
decides | -0.264 |
ponies | -0.253 |
Token | opened |
Token ID | 4721 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
groom | +0.517 |
roses | +0.475 |
register | +0.466 |
decides | +0.457 |
ponies | +0.444 |
Neg logit contributions | |
orse | -0.596 |
weapon | -0.472 |
oc | -0.468 |
bone | -0.444 |
oy | -0.438 |
Token | the |
Token ID | 262 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
groom | +0.005 |
roses | +0.005 |
register | +0.005 |
decides | +0.005 |
ponies | +0.004 |
Neg logit contributions | |
orse | -0.005 |
weapon | -0.003 |
oc | -0.003 |
uddy | -0.003 |
bone | -0.003 |
Token | box |
Token ID | 3091 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
groom | +0.027 |
roses | +0.024 |
decides | +0.023 |
ponies | +0.023 |
register | +0.022 |
Neg logit contributions | |
orse | -0.027 |
weapon | -0.026 |
bone | -0.025 |
oc | -0.024 |
hockey | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
orse | +0.024 |
oc | +0.019 |
weapon | +0.019 |
ggy | +0.018 |
emy | +0.018 |
Neg logit contributions | |
groom | -0.015 |
register | -0.015 |
roses | -0.015 |
decides | -0.014 |
ponies | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
groom | +0.006 |
roses | +0.006 |
decides | +0.006 |
Angel | +0.006 |
register | +0.006 |
Neg logit contributions | |
orse | -0.009 |
weapon | -0.007 |
inations | -0.007 |
oc | -0.007 |
oy | -0.007 |