Token | mighty |
Token ID | 18680 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
Ben | +0.154 |
Lily | +0.151 |
Mom | +0.151 |
Tom | +0.149 |
Sam | +0.143 |
Neg logit contributions | |
'd | -0.260 |
ave | -0.210 |
eded | -0.201 |
forgot | -0.194 |
managed | -0.193 |
Token | lion |
Token ID | 18744 |
Feature activation | +2.34e+01 |
Pos logit contributions | |
'd | +0.159 |
ave | +0.127 |
eded | +0.124 |
would | +0.119 |
forgot | +0.118 |
Neg logit contributions | |
Ben | -0.081 |
Mom | -0.081 |
Lily | -0.080 |
Tom | -0.078 |
Anna | -0.075 |
Token | named |
Token ID | 3706 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Lily | +0.661 |
Mom | +0.655 |
Ben | +0.655 |
Tom | +0.625 |
Anna | +0.609 |
Neg logit contributions | |
'd | -0.972 |
ave | -0.835 |
eded | -0.777 |
managed | -0.740 |
tted | -0.723 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.208 |
ave | +0.171 |
would | +0.161 |
eded | +0.161 |
've | +0.161 |
Neg logit contributions | |
ados | -0.066 |
ries | -0.056 |
accidents | -0.056 |
yourselves | -0.056 |
Mom | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Lily | +0.745 |
Ben | +0.737 |
Mom | +0.732 |
Tom | +0.689 |
Anna | +0.665 |
Neg logit contributions | |
'd | -1.709 |
ave | -1.514 |
eded | -1.419 |
managed | -1.369 |
tted | -1.353 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.52e+01 |
Pos logit contributions | |
Lily | +0.067 |
Mom | +0.064 |
Ben | +0.053 |
Sara | +0.049 |
Anna | +0.048 |
Neg logit contributions | |
'd | -0.310 |
ave | -0.273 |
eded | -0.259 |
managed | -0.253 |
would | -0.247 |
Token | lived |
Token ID | 5615 |
Feature activation | -9.79e+00 |
Pos logit contributions | |
Lily | +1.132 |
his | +1.109 |
the | +1.109 |
Ben | +1.102 |
Mom | +1.088 |
Neg logit contributions | |
ave | -1.142 |
'd | -1.132 |
ited | -1.010 |
tted | -1.005 |
ounded | -0.906 |
Token | in |
Token ID | 287 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
'd | +0.395 |
ave | +0.333 |
eded | +0.305 |
managed | +0.288 |
tted | +0.283 |
Neg logit contributions | |
Lily | -0.303 |
Ben | -0.300 |
Mom | -0.297 |
Tom | -0.286 |
Anna | -0.281 |
Token | a |
Token ID | 257 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
'd | +0.340 |
eded | +0.281 |
managed | +0.269 |
ave | +0.265 |
sy | +0.257 |
Neg logit contributions | |
Lily | -0.206 |
Mom | -0.205 |
ados | -0.202 |
Ben | -0.192 |
Dad | -0.191 |
Token | big |
Token ID | 1263 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Mom | +0.174 |
Lily | +0.174 |
Ben | +0.173 |
Tom | +0.168 |
Sara | +0.162 |
Neg logit contributions | |
'd | -0.249 |
ave | -0.202 |
eded | -0.195 |
managed | -0.185 |
sy | -0.181 |
Token | jungle |
Token ID | 20712 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
'd | +0.071 |
ave | +0.054 |
eded | +0.054 |
encountered | +0.051 |
managed | +0.051 |
Neg logit contributions | |
Lily | -0.057 |
Ben | -0.056 |
Mom | -0.055 |
Sara | -0.054 |
Anna | -0.054 |
Token | playing |
Token ID | 2712 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
'd | +0.658 |
ave | +0.568 |
eded | +0.532 |
managed | +0.502 |
tted | +0.495 |
Neg logit contributions | |
Lily | -0.394 |
Ben | -0.390 |
Mom | -0.389 |
Tom | -0.371 |
Anna | -0.360 |
Token | near |
Token ID | 1474 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
'd | +0.178 |
ave | +0.151 |
eded | +0.140 |
managed | +0.134 |
tted | +0.129 |
Neg logit contributions | |
Mom | -0.146 |
Lily | -0.143 |
Ben | -0.143 |
Tom | -0.137 |
Anna | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
'd | +0.414 |
eded | +0.344 |
would | +0.336 |
managed | +0.334 |
worked | +0.332 |
Neg logit contributions | |
ados | -0.307 |
ummy | -0.236 |
Uncle | -0.235 |
avail | -0.221 |
Mom | -0.218 |
Token | river |
Token ID | 7850 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
Lily | +0.417 |
Ben | +0.414 |
Mom | +0.411 |
Tom | +0.398 |
Anna | +0.389 |
Neg logit contributions | |
'd | -0.660 |
ave | -0.550 |
eded | -0.520 |
tted | -0.494 |
managed | -0.489 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Lily | +0.178 |
Ben | +0.171 |
Mom | +0.167 |
Tom | +0.165 |
Sam | +0.158 |
Neg logit contributions | |
'd | -0.414 |
ave | -0.370 |
eded | -0.351 |
tted | -0.329 |
managed | -0.327 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.52e+01 |
Pos logit contributions | |
ados | +0.116 |
God | +0.106 |
Mom | +0.106 |
Uncle | +0.104 |
his | +0.102 |
Neg logit contributions | |
'd | -0.234 |
ave | -0.204 |
tted | -0.187 |
forgot | -0.186 |
'll | -0.185 |
Token | had |
Token ID | 550 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
Ben | +1.335 |
Lily | +1.305 |
Max | +1.275 |
Mom | +1.263 |
Tom | +1.262 |
Neg logit contributions | |
'd | -1.017 |
ave | -0.924 |
tted | -0.860 |
eded | -0.814 |
aved | -0.790 |
Token | a |
Token ID | 257 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
'd | +0.674 |
ave | +0.603 |
eded | +0.567 |
tted | +0.536 |
managed | +0.534 |
Neg logit contributions | |
Lily | -0.256 |
Ben | -0.251 |
Mom | -0.249 |
Tom | -0.238 |
Anna | -0.225 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
Lily | +0.165 |
Mom | +0.164 |
Ben | +0.163 |
Tom | +0.153 |
Max | +0.152 |
Neg logit contributions | |
'd | -0.268 |
ave | -0.244 |
eded | -0.222 |
managed | -0.209 |
tted | -0.209 |
Token | idea |
Token ID | 2126 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
'd | +0.156 |
ave | +0.131 |
eded | +0.123 |
managed | +0.118 |
tted | +0.113 |
Neg logit contributions | |
Ben | -0.101 |
Lily | -0.101 |
Mom | -0.100 |
Tom | -0.096 |
Anna | -0.095 |
Token | to |
Token ID | 284 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
'd | +0.280 |
ave | +0.246 |
eded | +0.230 |
managed | +0.218 |
tted | +0.218 |
Neg logit contributions | |
Lily | -0.150 |
Ben | -0.148 |
Mom | -0.147 |
Tom | -0.142 |
Max | -0.136 |
Token | The |
Token ID | 383 |
Feature activation | +8.44e+00 |
Pos logit contributions | |
Lily | +0.100 |
Mom | +0.098 |
Ben | +0.090 |
Sara | +0.086 |
Tom | +0.084 |
Neg logit contributions | |
'd | -0.249 |
ave | -0.223 |
eded | -0.205 |
managed | -0.201 |
forgot | -0.195 |
Token | chef |
Token ID | 21221 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
Lily | +0.204 |
Ben | +0.203 |
Mom | +0.200 |
Tom | +0.189 |
Anna | +0.187 |
Neg logit contributions | |
'd | -0.390 |
ave | -0.340 |
eded | -0.319 |
managed | -0.304 |
tted | -0.298 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
Lily | +0.526 |
Mom | +0.520 |
Ben | +0.520 |
Tom | +0.510 |
Max | +0.500 |
Neg logit contributions | |
'd | -0.404 |
ave | -0.341 |
eded | -0.300 |
tted | -0.293 |
rated | -0.279 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
'd | +0.556 |
ave | +0.481 |
eded | +0.448 |
managed | +0.426 |
tted | +0.415 |
Neg logit contributions | |
Lily | -0.324 |
Mom | -0.319 |
Ben | -0.317 |
Tom | -0.301 |
Anna | -0.293 |
Token | for |
Token ID | 329 |
Feature activation | -8.13e+00 |
Pos logit contributions | |
'd | +0.096 |
ave | +0.077 |
eded | +0.071 |
would | +0.070 |
managed | +0.068 |
Neg logit contributions | |
Mom | -0.077 |
Lily | -0.075 |
Ben | -0.075 |
Tom | -0.073 |
Anna | -0.072 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.408 |
eded | +0.333 |
managed | +0.328 |
would | +0.322 |
encountered | +0.300 |
Neg logit contributions | |
Mom | -0.127 |
Lily | -0.117 |
ados | -0.107 |
Dad | -0.101 |
Uncle | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Lily | +0.944 |
Ben | +0.935 |
Mom | +0.928 |
Tom | +0.889 |
Anna | +0.865 |
Neg logit contributions | |
'd | -1.515 |
ave | -1.312 |
eded | -1.224 |
managed | -1.164 |
tted | -1.150 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
'd | +0.038 |
ave | +0.031 |
eded | +0.029 |
managed | +0.027 |
forgot | +0.026 |
Neg logit contributions | |
Mom | -0.041 |
Ben | -0.040 |
Lily | -0.040 |
Tom | -0.039 |
Anna | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
'd | +0.479 |
ave | +0.401 |
eded | +0.375 |
managed | +0.360 |
forgot | +0.345 |
Neg logit contributions | |
Ben | -0.382 |
Mom | -0.381 |
Lily | -0.375 |
Anna | -0.358 |
Tom | -0.357 |
Token | cook |
Token ID | 4255 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
'd | +0.268 |
ave | +0.231 |
eded | +0.203 |
managed | +0.193 |
tted | +0.191 |
Neg logit contributions | |
Lily | -0.248 |
Mom | -0.244 |
Ben | -0.240 |
Tom | -0.234 |
Max | -0.230 |
Token | him |
Token ID | 683 |
Feature activation | +1.69e+01 |
Pos logit contributions | |
'd | +0.285 |
eded | +0.244 |
managed | +0.236 |
ave | +0.232 |
would | +0.229 |
Neg logit contributions | |
Lily | -0.106 |
Mom | -0.104 |
ados | -0.100 |
Kim | -0.093 |
Uncle | -0.090 |
Token | was |
Token ID | 373 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
Lily | +0.299 |
Mom | +0.297 |
Ben | +0.295 |
Tom | +0.288 |
Anna | +0.281 |
Neg logit contributions | |
'd | -0.214 |
ave | -0.178 |
eded | -0.158 |
managed | -0.142 |
tted | -0.139 |
Token | a |
Token ID | 257 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
'd | +0.538 |
ave | +0.458 |
eded | +0.426 |
managed | +0.410 |
sy | +0.410 |
Neg logit contributions | |
ados | -0.322 |
Ben | -0.314 |
Mom | -0.308 |
Lily | -0.302 |
Uncle | -0.301 |
Token | mighty |
Token ID | 18680 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
Ben | +0.154 |
Lily | +0.151 |
Mom | +0.151 |
Tom | +0.149 |
Sam | +0.143 |
Neg logit contributions | |
'd | -0.260 |
ave | -0.210 |
eded | -0.201 |
forgot | -0.194 |
managed | -0.193 |
Token | lion |
Token ID | 18744 |
Feature activation | +2.34e+01 |
Pos logit contributions | |
'd | +0.159 |
ave | +0.127 |
eded | +0.124 |
would | +0.119 |
forgot | +0.118 |
Neg logit contributions | |
Ben | -0.081 |
Mom | -0.081 |
Lily | -0.080 |
Tom | -0.078 |
Anna | -0.075 |
Token | named |
Token ID | 3706 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Lily | +0.661 |
Mom | +0.655 |
Ben | +0.655 |
Tom | +0.625 |
Anna | +0.609 |
Neg logit contributions | |
'd | -0.972 |
ave | -0.835 |
eded | -0.777 |
managed | -0.740 |
tted | -0.723 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.208 |
ave | +0.171 |
would | +0.161 |
eded | +0.161 |
've | +0.161 |
Neg logit contributions | |
ados | -0.066 |
ries | -0.056 |
accidents | -0.056 |
yourselves | -0.056 |
Mom | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Lily | +0.745 |
Ben | +0.737 |
Mom | +0.732 |
Tom | +0.689 |
Anna | +0.665 |
Neg logit contributions | |
'd | -1.709 |
ave | -1.514 |
eded | -1.419 |
managed | -1.369 |
tted | -1.353 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.52e+01 |
Pos logit contributions | |
Lily | +0.067 |
Mom | +0.064 |
Ben | +0.053 |
Sara | +0.049 |
Anna | +0.048 |
Neg logit contributions | |
'd | -0.310 |
ave | -0.273 |
eded | -0.259 |
managed | -0.253 |
would | -0.247 |
Token | lived |
Token ID | 5615 |
Feature activation | -9.79e+00 |
Pos logit contributions | |
Lily | +1.132 |
his | +1.109 |
the | +1.109 |
Ben | +1.102 |
Mom | +1.088 |
Neg logit contributions | |
ave | -1.142 |
'd | -1.132 |
ited | -1.010 |
tted | -1.005 |
ounded | -0.906 |
Token | in |
Token ID | 287 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
'd | +0.395 |
ave | +0.333 |
eded | +0.305 |
managed | +0.288 |
tted | +0.283 |
Neg logit contributions | |
Lily | -0.303 |
Ben | -0.300 |
Mom | -0.297 |
Tom | -0.286 |
Anna | -0.281 |
Token | a |
Token ID | 257 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
'd | +0.340 |
eded | +0.281 |
managed | +0.269 |
ave | +0.265 |
sy | +0.257 |
Neg logit contributions | |
Lily | -0.206 |
Mom | -0.205 |
ados | -0.202 |
Ben | -0.192 |
Dad | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ados | +0.144 |
avail | +0.137 |
ries | +0.133 |
TV | +0.132 |
cartoons | +0.125 |
Neg logit contributions | |
'd | -0.185 |
ave | -0.144 |
'll | -0.141 |
would | -0.138 |
'm | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ados | +0.099 |
Lily | +0.088 |
TV | +0.086 |
Uncle | +0.085 |
Mom | +0.084 |
Neg logit contributions | |
'd | -0.111 |
ave | -0.089 |
tted | -0.086 |
eded | -0.085 |
'll | -0.081 |
Token | " |
Token ID | 1 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
Mom | +0.106 |
Lily | +0.106 |
Ben | +0.099 |
Max | +0.098 |
Uncle | +0.097 |
Neg logit contributions | |
'd | -0.115 |
ave | -0.096 |
eded | -0.088 |
tted | -0.087 |
managed | -0.086 |
Token | Hi |
Token ID | 17250 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Lily | +0.261 |
Mom | +0.260 |
Ben | +0.258 |
Tom | +0.249 |
Max | +0.244 |
Neg logit contributions | |
'd | -0.292 |
ave | -0.244 |
eded | -0.222 |
managed | -0.209 |
tted | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
'd | +0.115 |
'll | +0.087 |
would | +0.085 |
will | +0.081 |
forgot | +0.080 |
Neg logit contributions | |
ados | -0.093 |
Glass | -0.086 |
TV | -0.085 |
Lily | -0.084 |
his | -0.083 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
ados | +0.044 |
Lily | +0.035 |
Mom | +0.032 |
Uncle | +0.030 |
Tim | +0.029 |
Neg logit contributions | |
'd | -0.107 |
'll | -0.083 |
would | -0.082 |
will | -0.079 |
forgot | -0.078 |
Token | ," |
Token ID | 553 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
Lily | +0.876 |
Mom | +0.874 |
Ben | +0.868 |
Tom | +0.822 |
Anna | +0.800 |
Neg logit contributions | |
'd | -1.574 |
ave | -1.348 |
eded | -1.275 |
managed | -1.214 |
sy | -1.172 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.27e+01 |
Pos logit contributions | |
ados | +0.137 |
TV | +0.109 |
ummy | +0.106 |
adoes | +0.103 |
television | +0.101 |
Neg logit contributions | |
'd | -0.287 |
would | -0.244 |
forgot | -0.233 |
had | -0.230 |
managed | -0.222 |
Token | whispered |
Token ID | 25029 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
Lily | +1.100 |
Ben | +1.098 |
Mom | +1.090 |
Tom | +1.056 |
Anna | +1.032 |
Neg logit contributions | |
'd | -1.207 |
ave | -1.008 |
eded | -0.946 |
tted | -0.888 |
managed | -0.877 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
'd | +0.197 |
ave | +0.179 |
eded | +0.151 |
sy | +0.150 |
managed | +0.150 |
Neg logit contributions | |
Ben | -0.152 |
Lily | -0.149 |
Uncle | -0.146 |
Mom | -0.146 |
Max | -0.145 |
Token | " |
Token ID | 366 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ados | +0.134 |
avail | +0.119 |
Mom | +0.116 |
Lily | +0.116 |
grandma | +0.114 |
Neg logit contributions | |
'd | -0.229 |
ave | -0.184 |
would | -0.174 |
managed | -0.170 |
tted | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ados | +0.138 |
TV | +0.128 |
television | +0.124 |
avail | +0.123 |
Mom | +0.116 |
Neg logit contributions | |
'd | -0.194 |
ave | -0.176 |
'll | -0.155 |
tted | -0.153 |
eded | -0.148 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
Lily | +0.068 |
Ben | +0.068 |
Mom | +0.067 |
Tom | +0.063 |
Max | +0.062 |
Neg logit contributions | |
'd | -0.155 |
ave | -0.135 |
eded | -0.127 |
tted | -0.122 |
managed | -0.121 |
Token | " |
Token ID | 1 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
Lily | +0.082 |
Ben | +0.082 |
Mom | +0.079 |
Tom | +0.078 |
Anna | +0.077 |
Neg logit contributions | |
'd | -0.144 |
ave | -0.125 |
eded | -0.118 |
managed | -0.112 |
succeeded | -0.108 |
Token | Hi |
Token ID | 17250 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Lily | +0.248 |
Ben | +0.247 |
Mom | +0.246 |
Tom | +0.237 |
Anna | +0.232 |
Neg logit contributions | |
'd | -0.303 |
ave | -0.257 |
eded | -0.238 |
managed | -0.224 |
tted | -0.218 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
'd | +0.139 |
'll | +0.109 |
would | +0.108 |
managed | +0.104 |
ave | +0.103 |
Neg logit contributions | |
ados | -0.072 |
Lily | -0.067 |
Mom | -0.066 |
Uncle | -0.064 |
Glass | -0.062 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
ados | +0.033 |
Lily | +0.028 |
Mom | +0.028 |
Uncle | +0.024 |
her | +0.023 |
Neg logit contributions | |
'd | -0.119 |
'll | -0.094 |
would | -0.093 |
ave | -0.091 |
've | -0.090 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Mom | +0.998 |
Lily | +0.991 |
Ben | +0.986 |
Tom | +0.938 |
Anna | +0.916 |
Neg logit contributions | |
'd | -1.440 |
ave | -1.194 |
eded | -1.145 |
managed | -1.082 |
sy | -1.053 |
Token | Sara |
Token ID | 24799 |
Feature activation | +2.75e+01 |
Pos logit contributions | |
ados | +0.062 |
ummy | +0.055 |
Mom | +0.052 |
Max | +0.048 |
Uncle | +0.048 |
Neg logit contributions | |
'd | -0.155 |
ave | -0.144 |
forgot | -0.135 |
managed | -0.132 |
succeeded | -0.130 |
Token | said |
Token ID | 531 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Lily | +0.907 |
Ben | +0.902 |
Mom | +0.899 |
Tom | +0.868 |
Anna | +0.849 |
Neg logit contributions | |
'd | -1.029 |
ave | -0.864 |
eded | -0.803 |
managed | -0.748 |
tted | -0.742 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
'd | +0.070 |
ave | +0.061 |
eded | +0.055 |
managed | +0.055 |
sy | +0.052 |
Neg logit contributions | |
Lily | -0.050 |
Ben | -0.048 |
Mom | -0.048 |
ados | -0.046 |
Uncle | -0.046 |
Token | " |
Token ID | 366 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
ados | +0.112 |
Lily | +0.109 |
Mom | +0.105 |
grandma | +0.101 |
avail | +0.098 |
Neg logit contributions | |
'd | -0.231 |
ave | -0.189 |
managed | -0.176 |
would | -0.173 |
eded | -0.171 |
Token | that |
Token ID | 326 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
'd | +0.069 |
ave | +0.056 |
eded | +0.056 |
managed | +0.053 |
would | +0.051 |
Neg logit contributions | |
Ben | -0.044 |
Mom | -0.042 |
Lily | -0.042 |
Tom | -0.040 |
Anna | -0.039 |
Token | he |
Token ID | 339 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
Mom | +0.071 |
Lily | +0.070 |
ados | +0.069 |
Ben | +0.064 |
Sara | +0.062 |
Neg logit contributions | |
'd | -0.296 |
would | -0.246 |
managed | -0.245 |
ave | -0.242 |
eded | -0.237 |
Token | was |
Token ID | 373 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
Lily | +0.675 |
Ben | +0.675 |
Max | +0.661 |
Tom | +0.660 |
Sam | +0.656 |
Neg logit contributions | |
ave | -0.484 |
'd | -0.466 |
ited | -0.426 |
rated | -0.410 |
tted | -0.407 |
Token | faster |
Token ID | 5443 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
'd | +0.532 |
ave | +0.453 |
eded | +0.417 |
managed | +0.392 |
tted | +0.384 |
Neg logit contributions | |
Lily | -0.426 |
Ben | -0.423 |
Mom | -0.422 |
Tom | -0.406 |
Anna | -0.396 |
Token | than |
Token ID | 621 |
Feature activation | -7.89e+00 |
Pos logit contributions | |
'd | +0.164 |
ave | +0.139 |
eded | +0.130 |
managed | +0.121 |
tted | +0.120 |
Neg logit contributions | |
Lily | -0.125 |
Ben | -0.125 |
Mom | -0.123 |
Tom | -0.120 |
Anna | -0.116 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.422 |
ave | +0.350 |
managed | +0.340 |
eded | +0.337 |
would | +0.335 |
Neg logit contributions | |
Mom | -0.123 |
Lily | -0.101 |
Uncle | -0.098 |
Mama | -0.098 |
ados | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Ben | +0.840 |
Lily | +0.836 |
Mom | +0.817 |
Tom | +0.793 |
Anna | +0.764 |
Neg logit contributions | |
'd | -1.595 |
ave | -1.419 |
eded | -1.324 |
tted | -1.254 |
managed | -1.251 |
Token | He |
Token ID | 679 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
ados | +0.117 |
her | +0.113 |
avail | +0.113 |
Mom | +0.112 |
Lily | +0.111 |
Neg logit contributions | |
'd | -0.225 |
ave | -0.203 |
'll | -0.177 |
managed | -0.172 |
would | -0.172 |
Token | won |
Token ID | 1839 |
Feature activation | -1.75e+01 |
Pos logit contributions | |
Ben | +0.480 |
Lily | +0.478 |
Tom | +0.473 |
Sam | +0.470 |
Max | +0.463 |
Neg logit contributions | |
'd | -0.327 |
ave | -0.307 |
rated | -0.294 |
ited | -0.290 |
uch | -0.279 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
'd | +0.979 |
ave | +0.857 |
eded | +0.840 |
managed | +0.822 |
tted | +0.799 |
Neg logit contributions | |
Mom | -0.225 |
Ben | -0.213 |
Lily | -0.212 |
Anna | -0.181 |
Tom | -0.179 |
Token | race |
Token ID | 3234 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Lily | +0.517 |
Ben | +0.513 |
Mom | +0.510 |
Tom | +0.495 |
Anna | +0.481 |
Neg logit contributions | |
'd | -0.582 |
ave | -0.496 |
eded | -0.454 |
managed | -0.426 |
tted | -0.415 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Lily | +0.039 |
Mom | +0.039 |
Ben | +0.038 |
Tom | +0.036 |
Anna | +0.035 |
Neg logit contributions | |
'd | -0.084 |
ave | -0.073 |
eded | -0.069 |
managed | -0.066 |
tted | -0.064 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
ados | +0.146 |
Ben | +0.124 |
Uncle | +0.115 |
Lily | +0.115 |
Max | +0.114 |
Neg logit contributions | |
'd | -0.199 |
ave | -0.171 |
'm | -0.163 |
tted | -0.161 |
'll | -0.155 |
Token | M |
Token ID | 44 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Mom | +0.133 |
Lily | +0.129 |
Uncle | +0.127 |
Ben | +0.125 |
Tom | +0.121 |
Neg logit contributions | |
'd | -0.227 |
ave | -0.191 |
tted | -0.178 |
eded | -0.177 |
'll | -0.170 |
Token | ia |
Token ID | 544 |
Feature activation | +2.18e+01 |
Pos logit contributions | |
Lily | +0.139 |
Max | +0.135 |
Ben | +0.132 |
Anna | +0.130 |
ados | +0.130 |
Neg logit contributions | |
'd | -0.166 |
ave | -0.131 |
eded | -0.122 |
managed | -0.116 |
forgot | -0.115 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Ben | +0.621 |
Lily | +0.617 |
Tom | +0.616 |
Mom | +0.569 |
Anna | +0.566 |
Neg logit contributions | |
'd | -0.878 |
ave | -0.751 |
eded | -0.715 |
tted | -0.705 |
sy | -0.693 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.058 |
've | +0.048 |
ave | +0.048 |
managed | +0.048 |
would | +0.048 |
Neg logit contributions | |
ados | -0.014 |
TV | -0.014 |
ummy | -0.012 |
Farmer | -0.011 |
avail | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
Tom | +1.327 |
Ben | +1.323 |
Lily | +1.313 |
Tim | +1.233 |
Mom | +1.227 |
Neg logit contributions | |
'd | -1.017 |
ave | -0.905 |
tted | -0.782 |
eded | -0.762 |
sy | -0.759 |
Token | twins |
Token ID | 20345 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
'd | +0.564 |
ave | +0.473 |
eded | +0.436 |
managed | +0.415 |
succeeded | +0.399 |
Neg logit contributions | |
Lily | -0.450 |
Mom | -0.440 |
Ben | -0.439 |
Tom | -0.423 |
Anna | -0.416 |
Token | who |
Token ID | 508 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Lily | +0.380 |
Mom | +0.377 |
Ben | +0.376 |
Tom | +0.356 |
Anna | +0.345 |
Neg logit contributions | |
'd | -0.719 |
ave | -0.627 |
eded | -0.587 |
managed | -0.561 |
tted | -0.549 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.90e+01 |
Pos logit contributions | |
Lily | +0.161 |
Ben | +0.159 |
Tom | +0.158 |
Mom | +0.155 |
Max | +0.151 |
Neg logit contributions | |
'd | -0.090 |
ave | -0.076 |
eded | -0.066 |
managed | -0.059 |
ited | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
'd | +0.561 |
would | +0.410 |
ave | +0.408 |
eded | +0.375 |
managed | +0.357 |
Neg logit contributions | |
Ben | -0.665 |
Lily | -0.655 |
Anna | -0.637 |
Mom | -0.633 |
Tom | -0.625 |
Token | day |
Token ID | 1110 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
'd | +0.012 |
ave | +0.010 |
eded | +0.010 |
managed | +0.009 |
tted | +0.009 |
Neg logit contributions | |
Lily | -0.008 |
Mom | -0.008 |
Ben | -0.008 |
Tom | -0.008 |
Anna | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Lily | +0.041 |
Mom | +0.041 |
Ben | +0.040 |
Tom | +0.038 |
Anna | +0.037 |
Neg logit contributions | |
'd | -0.079 |
ave | -0.069 |
eded | -0.064 |
managed | -0.062 |
forgot | -0.059 |
Token | while |
Token ID | 981 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
Lily | +0.025 |
Mom | +0.023 |
ados | +0.020 |
Ben | +0.019 |
Sara | +0.019 |
Neg logit contributions | |
'd | -0.123 |
ave | -0.106 |
managed | -0.101 |
eded | -0.101 |
would | -0.101 |
Token | swinging |
Token ID | 25635 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
'd | +0.331 |
managed | +0.272 |
ave | +0.272 |
encountered | +0.270 |
eded | +0.267 |
Neg logit contributions | |
Lily | -0.104 |
Mom | -0.093 |
Sara | -0.089 |
ados | -0.085 |
Anna | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
'd | +0.138 |
ave | +0.118 |
eded | +0.108 |
managed | +0.107 |
tted | +0.104 |
Neg logit contributions | |
Mom | -0.084 |
Ben | -0.084 |
Lily | -0.081 |
Uncle | -0.079 |
Anna | -0.078 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
ados | +0.034 |
Lily | +0.032 |
grandma | +0.031 |
Mom | +0.030 |
ummy | +0.029 |
Neg logit contributions | |
'd | -0.108 |
would | -0.089 |
managed | -0.087 |
encountered | -0.085 |
ave | -0.084 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
Ben | +1.358 |
Lily | +1.299 |
Tom | +1.259 |
Sam | +1.223 |
Max | +1.209 |
Neg logit contributions | |
'd | -1.037 |
ave | -0.862 |
tted | -0.862 |
eded | -0.840 |
sy | -0.780 |
Token | a |
Token ID | 257 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
'd | +0.469 |
ave | +0.397 |
managed | +0.379 |
would | +0.371 |
eded | +0.364 |
Neg logit contributions | |
ados | -0.364 |
ummy | -0.334 |
Uncle | -0.334 |
Mom | -0.334 |
Lee | -0.331 |
Token | trap |
Token ID | 12840 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Lily | +0.151 |
Mom | +0.150 |
Ben | +0.150 |
Tom | +0.142 |
Anna | +0.138 |
Neg logit contributions | |
'd | -0.276 |
ave | -0.241 |
eded | -0.225 |
managed | -0.215 |
tted | -0.210 |
Token | on |
Token ID | 319 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Lily | +0.057 |
Ben | +0.057 |
Tom | +0.055 |
Max | +0.053 |
Mom | +0.053 |
Neg logit contributions | |
'd | -0.108 |
ave | -0.097 |
eded | -0.090 |
managed | -0.086 |
ited | -0.085 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
'd | +0.329 |
eded | +0.292 |
bit | +0.286 |
worked | +0.284 |
never | +0.283 |
Neg logit contributions | |
ummy | -0.205 |
ados | -0.204 |
Dad | -0.197 |
Mom | -0.192 |
Jenny | -0.191 |
Token | it |
Token ID | 340 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
'd | +0.536 |
would | +0.456 |
eded | +0.432 |
deserved | +0.406 |
should | +0.404 |
Neg logit contributions | |
ados | -0.239 |
Lily | -0.224 |
Ben | -0.218 |
Mom | -0.215 |
Sam | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Lily | +0.475 |
Mom | +0.475 |
Ben | +0.472 |
Tom | +0.449 |
Anna | +0.441 |
Neg logit contributions | |
'd | -0.812 |
ave | -0.691 |
eded | -0.652 |
managed | -0.619 |
would | -0.599 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Mom | +0.063 |
Lily | +0.063 |
Ben | +0.062 |
Tom | +0.059 |
Anna | +0.059 |
Neg logit contributions | |
'd | -0.087 |
ave | -0.071 |
eded | -0.066 |
managed | -0.065 |
forgot | -0.063 |
Token | they |
Token ID | 484 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
'd | +0.051 |
ave | +0.044 |
eded | +0.041 |
managed | +0.040 |
forgot | +0.038 |
Neg logit contributions | |
Lily | -0.031 |
Mom | -0.031 |
Ben | -0.031 |
Tom | -0.029 |
Anna | -0.029 |
Token | realized |
Token ID | 6939 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Ben | +0.659 |
Mom | +0.647 |
Lily | +0.632 |
Tom | +0.624 |
Dad | +0.594 |
Neg logit contributions | |
'd | -0.510 |
tted | -0.481 |
sc | -0.449 |
ave | -0.445 |
rated | -0.443 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.423 |
would | +0.354 |
wouldn | +0.331 |
eded | +0.326 |
managed | +0.322 |
Neg logit contributions | |
ados | -0.268 |
Lily | -0.251 |
Ben | -0.249 |
Mom | -0.241 |
Anna | -0.239 |
Token | was |
Token ID | 373 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
Lily | +1.350 |
Ben | +1.343 |
Mom | +1.317 |
Tom | +1.299 |
Max | +1.272 |
Neg logit contributions | |
'd | -1.052 |
ave | -0.922 |
eded | -0.791 |
tted | -0.766 |
managed | -0.720 |
Token | right |
Token ID | 826 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
'd | +0.519 |
ave | +0.430 |
eded | +0.405 |
managed | +0.387 |
succeeded | +0.373 |
Neg logit contributions | |
Mom | -0.421 |
Lily | -0.414 |
Ben | -0.411 |
Tom | -0.394 |
Max | -0.388 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
'd | +0.278 |
ave | +0.238 |
eded | +0.224 |
managed | +0.212 |
sy | +0.206 |
Neg logit contributions | |
Lily | -0.157 |
Ben | -0.154 |
Mom | -0.151 |
Max | -0.147 |
Tom | -0.145 |
Token | They |
Token ID | 1119 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
ados | +0.169 |
avail | +0.166 |
ries | +0.157 |
groceries | +0.150 |
bed | +0.150 |
Neg logit contributions | |
'd | -0.143 |
ave | -0.114 |
'll | -0.108 |
tted | -0.105 |
managed | -0.096 |
Token | had |
Token ID | 550 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
Ben | +0.381 |
Lily | +0.376 |
Mom | +0.374 |
Tom | +0.368 |
Sam | +0.345 |
Neg logit contributions | |
'd | -0.249 |
ave | -0.228 |
tted | -0.223 |
rated | -0.217 |
uch | -0.214 |
Token | much |
Token ID | 881 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
Ben | +0.027 |
Lily | +0.027 |
Mom | +0.027 |
Tom | +0.025 |
Anna | +0.025 |
Neg logit contributions | |
'd | -0.052 |
ave | -0.045 |
eded | -0.043 |
managed | -0.041 |
tted | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
'd | +0.248 |
ave | +0.216 |
eded | +0.197 |
managed | +0.189 |
would | +0.184 |
Neg logit contributions | |
Mom | -0.162 |
Ben | -0.157 |
Lily | -0.155 |
Anna | -0.146 |
Tom | -0.143 |
Token | They |
Token ID | 1119 |
Feature activation | +9.51e+00 |
Pos logit contributions | |
Lily | +0.121 |
ados | +0.117 |
her | +0.116 |
Max | +0.115 |
Mom | +0.115 |
Neg logit contributions | |
'd | -0.206 |
ave | -0.185 |
'll | -0.171 |
tted | -0.166 |
eded | -0.165 |
Token | said |
Token ID | 531 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Lily | +0.385 |
Ben | +0.383 |
Tom | +0.372 |
Mom | +0.371 |
Max | +0.350 |
Neg logit contributions | |
'd | -0.272 |
ave | -0.235 |
tted | -0.229 |
eded | -0.218 |
sy | -0.209 |
Token | to |
Token ID | 284 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
'd | +0.083 |
ave | +0.069 |
managed | +0.065 |
would | +0.064 |
eded | +0.064 |
Neg logit contributions | |
Ben | -0.045 |
Mom | -0.045 |
Lily | -0.044 |
Uncle | -0.043 |
Tom | -0.042 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.337 |
eded | +0.271 |
would | +0.269 |
managed | +0.252 |
never | +0.249 |
Neg logit contributions | |
ados | -0.131 |
Lily | -0.109 |
ummy | -0.099 |
groceries | -0.096 |
Mom | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Mom | +0.811 |
Lily | +0.806 |
Ben | +0.797 |
Tom | +0.754 |
Anna | +0.730 |
Neg logit contributions | |
'd | -1.634 |
ave | -1.408 |
eded | -1.329 |
managed | -1.276 |
forgot | -1.231 |
Token | " |
Token ID | 366 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Mom | +0.044 |
Ben | +0.044 |
Lily | +0.044 |
ados | +0.043 |
Tom | +0.041 |
Neg logit contributions | |
'd | -0.106 |
ave | -0.086 |
would | -0.081 |
eded | -0.080 |
managed | -0.080 |
Token | No |
Token ID | 2949 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
Lily | +0.170 |
Ben | +0.169 |
Mom | +0.166 |
Tom | +0.162 |
Anna | +0.159 |
Neg logit contributions | |
'd | -0.209 |
ave | -0.175 |
eded | -0.166 |
managed | -0.155 |
sy | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
'd | +0.224 |
would | +0.171 |
eded | +0.164 |
forgot | +0.161 |
ave | +0.158 |
Neg logit contributions | |
Mom | -0.168 |
Lily | -0.164 |
Ben | -0.161 |
Dad | -0.155 |
Anna | -0.154 |
Token | you |
Token ID | 345 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
Mom | +0.044 |
Lily | +0.043 |
Ben | +0.040 |
Uncle | +0.039 |
ados | +0.038 |
Neg logit contributions | |
'd | -0.111 |
ave | -0.089 |
managed | -0.087 |
eded | -0.086 |
forgot | -0.085 |
Token | boss |
Token ID | 6478 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
'd | +0.480 |
ave | +0.405 |
eded | +0.373 |
managed | +0.351 |
tted | +0.342 |
Neg logit contributions | |
Lily | -0.413 |
Ben | -0.410 |
Mom | -0.410 |
Tom | -0.393 |
Anna | -0.385 |
Token | y |
Token ID | 88 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
'd | +0.141 |
ave | +0.111 |
eded | +0.100 |
managed | +0.091 |
tted | +0.087 |
Neg logit contributions | |
Lily | -0.207 |
Ben | -0.206 |
Mom | -0.206 |
Tom | -0.200 |
Anna | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Lily | +0.158 |
Mom | +0.156 |
Ben | +0.156 |
Tom | +0.148 |
Anna | +0.144 |
Neg logit contributions | |
'd | -0.285 |
ave | -0.249 |
eded | -0.233 |
managed | -0.222 |
tted | -0.218 |
Token | She |
Token ID | 1375 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
ados | +0.117 |
Lily | +0.107 |
grandma | +0.103 |
Uncle | +0.102 |
bed | +0.099 |
Neg logit contributions | |
'd | -0.208 |
'll | -0.171 |
ave | -0.167 |
'm | -0.162 |
would | -0.160 |
Token | tells |
Token ID | 4952 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
Ben | +0.530 |
Tom | +0.505 |
Lily | +0.498 |
Mom | +0.488 |
Anna | +0.481 |
Neg logit contributions | |
'd | -0.447 |
ave | -0.420 |
tted | -0.398 |
eded | -0.369 |
sy | -0.354 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.531 |
would | +0.457 |
stayed | +0.429 |
ave | +0.427 |
listened | +0.416 |
Neg logit contributions | |
ados | -0.167 |
Lily | -0.131 |
Glass | -0.120 |
Tim | -0.115 |
ummy | -0.109 |
Token | what |
Token ID | 644 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
Mom | +1.117 |
Lily | +1.101 |
Ben | +1.100 |
Tom | +1.055 |
Anna | +1.021 |
Neg logit contributions | |
'd | -1.342 |
ave | -1.097 |
eded | -1.018 |
managed | -0.967 |
would | -0.939 |
Token | to |
Token ID | 284 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
Mom | +0.138 |
Lily | +0.137 |
Ben | +0.135 |
Tom | +0.127 |
Anna | +0.126 |
Neg logit contributions | |
'd | -0.193 |
ave | -0.153 |
would | -0.144 |
eded | -0.142 |
managed | -0.138 |
Token | do |
Token ID | 466 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
'd | +0.174 |
ave | +0.117 |
eded | +0.104 |
managed | +0.092 |
would | +0.091 |
Neg logit contributions | |
Mom | -0.324 |
Lily | -0.321 |
Ben | -0.319 |
Anna | -0.309 |
Uncle | -0.306 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
'd | +0.896 |
ave | +0.787 |
eded | +0.740 |
managed | +0.709 |
tted | +0.694 |
Neg logit contributions | |
Lily | -0.411 |
Mom | -0.406 |
Ben | -0.406 |
Tom | -0.382 |
Anna | -0.370 |
Token | how |
Token ID | 703 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
'd | +0.047 |
ave | +0.039 |
eded | +0.036 |
managed | +0.035 |
forgot | +0.035 |
Neg logit contributions | |
Lily | -0.031 |
Mom | -0.030 |
Ben | -0.029 |
Tom | -0.028 |
Max | -0.027 |
Token | on |
Token ID | 319 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
Lily | +0.055 |
Mom | +0.054 |
Ben | +0.054 |
Tom | +0.052 |
Anna | +0.051 |
Neg logit contributions | |
'd | -0.065 |
ave | -0.055 |
eded | -0.051 |
managed | -0.048 |
tted | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
'd | +0.356 |
would | +0.272 |
eded | +0.254 |
managed | +0.248 |
forgot | +0.236 |
Neg logit contributions | |
Lily | -0.305 |
Mom | -0.301 |
Sara | -0.288 |
Dad | -0.287 |
Tom | -0.286 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
Lily | +0.025 |
Mom | +0.024 |
Ben | +0.020 |
ados | +0.019 |
Dad | +0.019 |
Neg logit contributions | |
'd | -0.123 |
ave | -0.103 |
eded | -0.102 |
managed | -0.102 |
would | -0.101 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.31e+01 |
Pos logit contributions | |
Lily | +0.355 |
Mom | +0.353 |
Ben | +0.349 |
Tom | +0.330 |
Anna | +0.318 |
Neg logit contributions | |
'd | -0.744 |
ave | -0.658 |
eded | -0.612 |
managed | -0.588 |
tted | -0.577 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Lily | +0.678 |
Ben | +0.658 |
the | +0.647 |
Sam | +0.628 |
Mom | +0.627 |
Neg logit contributions | |
'd | -0.867 |
ave | -0.766 |
tted | -0.719 |
eded | -0.685 |
ited | -0.684 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.064 |
eded | +0.053 |
ave | +0.052 |
managed | +0.052 |
would | +0.052 |
Neg logit contributions | |
Lily | -0.016 |
Mom | -0.015 |
Dad | -0.013 |
Sara | -0.012 |
Uncle | -0.012 |
Token | became |
Token ID | 2627 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
the | +1.268 |
Ben | +1.259 |
Lily | +1.248 |
Mom | +1.220 |
her | +1.213 |
Neg logit contributions | |
'd | -0.940 |
ave | -0.879 |
tted | -0.793 |
ited | -0.780 |
rated | -0.775 |
Token | best |
Token ID | 1266 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
'd | +0.454 |
eded | +0.360 |
managed | +0.357 |
ave | +0.353 |
succeeded | +0.340 |
Neg logit contributions | |
Mom | -0.351 |
Ben | -0.350 |
Lily | -0.343 |
Tom | -0.341 |
Anna | -0.333 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
Lily | +0.005 |
Ben | +0.005 |
Mom | +0.005 |
Tom | +0.005 |
Anna | +0.005 |
Neg logit contributions | |
'd | -0.011 |
ave | -0.010 |
eded | -0.009 |
managed | -0.009 |
tted | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Lily | +0.348 |
Mom | +0.345 |
Ben | +0.344 |
Tom | +0.326 |
Anna | +0.317 |
Neg logit contributions | |
'd | -0.636 |
ave | -0.553 |
eded | -0.518 |
managed | -0.495 |
tted | -0.482 |
Token | They |
Token ID | 1119 |
Feature activation | +9.64e+00 |
Pos logit contributions | |
Lily | +0.128 |
Mom | +0.123 |
Ben | +0.115 |
Dad | +0.113 |
Sara | +0.112 |
Neg logit contributions | |
'd | -0.230 |
ave | -0.196 |
eded | -0.185 |
managed | -0.175 |
tted | -0.175 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
'd | +0.356 |
managed | +0.318 |
bit | +0.310 |
heard | +0.302 |
eded | +0.293 |
Neg logit contributions | |
ados | -0.178 |
Uncle | -0.154 |
ummy | -0.133 |
novels | -0.133 |
grandma | -0.128 |
Token | air |
Token ID | 1633 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Lily | +0.327 |
Mom | +0.324 |
Ben | +0.322 |
Tom | +0.300 |
Anna | +0.290 |
Neg logit contributions | |
'd | -0.766 |
ave | -0.673 |
eded | -0.634 |
managed | -0.609 |
tted | -0.592 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Lily | +0.027 |
Ben | +0.027 |
Mom | +0.027 |
Tom | +0.025 |
Anna | +0.024 |
Neg logit contributions | |
'd | -0.065 |
ave | -0.057 |
eded | -0.054 |
managed | -0.051 |
tted | -0.051 |
Token | Mia |
Token ID | 32189 |
Feature activation | +3.11e+01 |
Pos logit contributions | |
ados | +0.133 |
ries | +0.119 |
groceries | +0.115 |
grandma | +0.110 |
avail | +0.110 |
Neg logit contributions | |
'd | -0.205 |
ave | -0.177 |
tted | -0.170 |
managed | -0.164 |
'll | -0.160 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Ben | +0.753 |
Lily | +0.680 |
Tom | +0.671 |
Anna | +0.667 |
Mom | +0.656 |
Neg logit contributions | |
'd | -1.388 |
ave | -1.239 |
eded | -1.224 |
rated | -1.221 |
tted | -1.206 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.052 |
managed | +0.045 |
ave | +0.043 |
forgot | +0.043 |
encountered | +0.042 |
Neg logit contributions | |
Lily | -0.019 |
ummy | -0.019 |
ados | -0.016 |
Sara | -0.016 |
Mom | -0.015 |
Token | cl |
Token ID | 537 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
Ben | +1.236 |
the | +1.158 |
Tom | +1.138 |
Mom | +1.132 |
Lily | +1.123 |
Neg logit contributions | |
'd | -1.044 |
rated | -0.978 |
ave | -0.952 |
tted | -0.920 |
wn | -0.889 |
Token | apped |
Token ID | 6320 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
'd | +0.594 |
ave | +0.460 |
eded | +0.455 |
managed | +0.417 |
forgot | +0.410 |
Neg logit contributions | |
Mom | -0.477 |
Ben | -0.466 |
Lily | -0.462 |
Tom | -0.448 |
Sam | -0.439 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
'd | +0.518 |
ave | +0.449 |
eded | +0.418 |
managed | +0.411 |
forgot | +0.395 |
Neg logit contributions | |
Ben | -0.234 |
Lily | -0.234 |
Mom | -0.232 |
Tom | -0.226 |
Uncle | -0.222 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
'd | +0.034 |
ave | +0.027 |
eded | +0.025 |
tted | +0.023 |
sy | +0.021 |
Neg logit contributions | |
Lily | -0.048 |
Ben | -0.048 |
Mom | -0.047 |
Tom | -0.046 |
Max | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
'd | +0.422 |
ave | +0.359 |
eded | +0.325 |
managed | +0.317 |
would | +0.308 |
Neg logit contributions | |
Ben | -0.307 |
Uncle | -0.304 |
Lily | -0.303 |
Mom | -0.303 |
Tom | -0.297 |
Token | " |
Token ID | 366 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Lily | +0.036 |
Mom | +0.036 |
Ben | +0.036 |
Tom | +0.033 |
Anna | +0.032 |
Neg logit contributions | |
'd | -0.112 |
ave | -0.097 |
eded | -0.092 |
managed | -0.090 |
forgot | -0.086 |
Token | Don |
Token ID | 3987 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
Lily | +0.187 |
Mom | +0.186 |
Ben | +0.182 |
Tom | +0.176 |
Anna | +0.173 |
Neg logit contributions | |
'd | -0.188 |
ave | -0.155 |
eded | -0.140 |
managed | -0.133 |
tted | -0.126 |
Token | 't |
Token ID | 470 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
'd | +0.391 |
ave | +0.326 |
eded | +0.303 |
managed | +0.286 |
tted | +0.280 |
Neg logit contributions | |
Lily | -0.327 |
Ben | -0.325 |
Mom | -0.324 |
Tom | -0.310 |
Anna | -0.305 |
Token | cry |
Token ID | 3960 |
Feature activation | -9.84e+00 |
Pos logit contributions | |
'd | +0.244 |
ave | +0.200 |
eded | +0.182 |
managed | +0.170 |
tted | +0.163 |
Neg logit contributions | |
Lily | -0.268 |
Mom | -0.267 |
Ben | -0.267 |
Tom | -0.257 |
Anna | -0.253 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
'd | +0.339 |
ave | +0.270 |
be | +0.249 |
forgot | +0.244 |
sy | +0.244 |
Neg logit contributions | |
Ben | -0.271 |
Mom | -0.270 |
Uncle | -0.269 |
Lily | -0.267 |
ados | -0.265 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
ados | +0.029 |
Lily | +0.025 |
Mom | +0.024 |
Uncle | +0.020 |
grandma | +0.019 |
Neg logit contributions | |
'd | -0.121 |
forgot | -0.098 |
managed | -0.097 |
would | -0.095 |
'll | -0.094 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Lily | +0.779 |
Mom | +0.773 |
Ben | +0.770 |
Tom | +0.725 |
Anna | +0.703 |
Neg logit contributions | |
'd | -1.672 |
ave | -1.461 |
eded | -1.376 |
managed | -1.319 |
tted | -1.285 |
Token | it |
Token ID | 340 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
Mom | +0.046 |
Ben | +0.045 |
Lily | +0.045 |
Tom | +0.043 |
Uncle | +0.041 |
Neg logit contributions | |
'd | -0.109 |
ave | -0.092 |
eded | -0.087 |
managed | -0.086 |
forgot | -0.083 |
Token | 's |
Token ID | 338 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
Lily | +0.504 |
Max | +0.470 |
Ben | +0.463 |
Anna | +0.459 |
Mom | +0.452 |
Neg logit contributions | |
'd | -0.709 |
ave | -0.656 |
tted | -0.610 |
anticipated | -0.609 |
eded | -0.598 |
Token | okay |
Token ID | 8788 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
'd | +0.145 |
ave | +0.120 |
eded | +0.110 |
managed | +0.104 |
tted | +0.099 |
Neg logit contributions | |
Lily | -0.142 |
Ben | -0.142 |
Mom | -0.141 |
Tom | -0.136 |
Anna | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
'd | +0.199 |
ave | +0.164 |
eded | +0.155 |
managed | +0.149 |
would | +0.148 |
Neg logit contributions | |
Ben | -0.113 |
Lily | -0.112 |
Mom | -0.111 |
Tom | -0.106 |
Max | -0.103 |
Token | ring |
Token ID | 5858 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Lily | +0.164 |
Mom | +0.162 |
Ben | +0.161 |
Tom | +0.153 |
Anna | +0.149 |
Neg logit contributions | |
'd | -0.257 |
ave | -0.224 |
eded | -0.207 |
managed | -0.197 |
tted | -0.193 |
Token | for |
Token ID | 329 |
Feature activation | -8.22e+00 |
Pos logit contributions | |
'd | +0.097 |
ave | +0.082 |
eded | +0.076 |
managed | +0.073 |
sy | +0.071 |
Neg logit contributions | |
Lily | -0.063 |
Ben | -0.063 |
Mom | -0.062 |
Tom | -0.059 |
Anna | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
'd | +0.365 |
managed | +0.307 |
eded | +0.300 |
succeeded | +0.292 |
anticipated | +0.282 |
Neg logit contributions | |
Lily | -0.116 |
ados | -0.106 |
Mom | -0.106 |
ummy | -0.102 |
Uncle | -0.097 |
Token | finger |
Token ID | 7660 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Ben | +0.468 |
Lily | +0.467 |
Mom | +0.460 |
Tom | +0.446 |
Anna | +0.436 |
Neg logit contributions | |
'd | -0.780 |
ave | -0.665 |
eded | -0.625 |
managed | -0.595 |
tted | -0.577 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
Lily | +0.070 |
Mom | +0.069 |
Ben | +0.069 |
Tom | +0.065 |
Anna | +0.062 |
Neg logit contributions | |
'd | -0.147 |
ave | -0.129 |
eded | -0.122 |
managed | -0.116 |
tted | -0.114 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
ados | +0.139 |
avail | +0.126 |
ries | +0.122 |
ummy | +0.120 |
her | +0.118 |
Neg logit contributions | |
'd | -0.185 |
ave | -0.162 |
tted | -0.146 |
'll | -0.145 |
managed | -0.140 |
Token | is |
Token ID | 318 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
Ben | +1.162 |
Lily | +1.109 |
Mom | +1.099 |
Tom | +1.078 |
Anna | +1.074 |
Neg logit contributions | |
'd | -1.286 |
ave | -1.165 |
eded | -1.033 |
tted | -1.029 |
managed | -0.961 |
Token | very |
Token ID | 845 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
'd | +0.467 |
ave | +0.394 |
eded | +0.362 |
managed | +0.337 |
tted | +0.330 |
Neg logit contributions | |
Lily | -0.423 |
Mom | -0.421 |
Ben | -0.420 |
Tom | -0.404 |
Anna | -0.396 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
'd | +0.378 |
ave | +0.326 |
eded | +0.304 |
managed | +0.274 |
encountered | +0.274 |
Neg logit contributions | |
Mom | -0.267 |
Lily | -0.263 |
Ben | -0.260 |
Tom | -0.247 |
Anna | -0.240 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
'd | +0.225 |
ave | +0.183 |
eded | +0.167 |
managed | +0.165 |
would | +0.161 |
Neg logit contributions | |
Mom | -0.181 |
Lily | -0.181 |
Ben | -0.177 |
Tom | -0.171 |
Max | -0.170 |
Token | says |
Token ID | 1139 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
'd | +0.050 |
ave | +0.043 |
eded | +0.041 |
managed | +0.038 |
tted | +0.038 |
Neg logit contributions | |
Lily | -0.031 |
Ben | -0.031 |
Mom | -0.030 |
Tom | -0.029 |
Anna | -0.028 |
Token | ." |
Token ID | 526 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
'd | +0.210 |
ave | +0.183 |
eded | +0.171 |
managed | +0.163 |
tted | +0.159 |
Neg logit contributions | |
Lily | -0.110 |
Ben | -0.110 |
Mom | -0.109 |
Tom | -0.104 |
Anna | -0.101 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
ados | +0.097 |
avail | +0.091 |
my | +0.082 |
TV | +0.080 |
ries | +0.077 |
Neg logit contributions | |
'd | -0.083 |
ave | -0.075 |
forgot | -0.067 |
'm | -0.067 |
tted | -0.065 |
Token | M |
Token ID | 44 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
Mom | +0.140 |
Uncle | +0.135 |
Lily | +0.134 |
Ben | +0.128 |
Tom | +0.127 |
Neg logit contributions | |
'd | -0.215 |
ave | -0.181 |
eded | -0.168 |
tted | -0.167 |
'll | -0.160 |
Token | ia |
Token ID | 544 |
Feature activation | +2.18e+01 |
Pos logit contributions | |
Lily | +0.149 |
Ben | +0.145 |
Max | +0.140 |
Anna | +0.140 |
Mom | +0.140 |
Neg logit contributions | |
'd | -0.159 |
ave | -0.129 |
eded | -0.121 |
managed | -0.111 |
forgot | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Ben | +0.691 |
Lily | +0.674 |
Tom | +0.655 |
Anna | +0.633 |
Mom | +0.631 |
Neg logit contributions | |
'd | -0.864 |
ave | -0.735 |
eded | -0.690 |
tted | -0.668 |
sy | -0.646 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.064 |
've | +0.053 |
ave | +0.053 |
forgot | +0.053 |
managed | +0.052 |
Neg logit contributions | |
ados | -0.013 |
TV | -0.012 |
Anna | -0.009 |
ummy | -0.009 |
Lily | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
Ben | +1.304 |
Tom | +1.274 |
Lily | +1.269 |
Mom | +1.178 |
her | +1.165 |
Neg logit contributions | |
'd | -1.100 |
ave | -0.976 |
eded | -0.857 |
tted | -0.844 |
sy | -0.840 |
Token | playing |
Token ID | 2712 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
'd | +0.576 |
ave | +0.488 |
eded | +0.449 |
managed | +0.428 |
sy | +0.411 |
Neg logit contributions | |
Lily | -0.438 |
Mom | -0.428 |
Ben | -0.427 |
Tom | -0.412 |
Sam | -0.403 |
Token | in |
Token ID | 287 |
Feature activation | -8.84e+00 |
Pos logit contributions | |
'd | +0.155 |
ave | +0.130 |
eded | +0.118 |
managed | +0.114 |
tted | +0.110 |
Neg logit contributions | |
Mom | -0.159 |
Lily | -0.154 |
Uncle | -0.154 |
Ben | -0.154 |
Tom | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
'd | +0.300 |
had | +0.268 |
gathered | +0.260 |
packed | +0.255 |
collected | +0.253 |
Neg logit contributions | |
ados | -0.207 |
Uncle | -0.177 |
rier | -0.168 |
Farmer | -0.167 |
sir | -0.162 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
ados | +0.472 |
Ben | +0.465 |
Tom | +0.462 |
Sara | +0.461 |
Lily | +0.458 |
Neg logit contributions | |
'd | -0.497 |
ave | -0.376 |
would | -0.369 |
encountered | -0.367 |
sy | -0.366 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Lily | +0.010 |
Ben | +0.010 |
Mom | +0.010 |
Tom | +0.010 |
Anna | +0.009 |
Neg logit contributions | |
'd | -0.021 |
ave | -0.019 |
eded | -0.018 |
managed | -0.017 |
tted | -0.017 |
Token | cute |
Token ID | 13779 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
'd | +0.051 |
ave | +0.041 |
eded | +0.039 |
managed | +0.038 |
forgot | +0.037 |
Neg logit contributions | |
Mom | -0.035 |
Lily | -0.035 |
Ben | -0.035 |
Tom | -0.033 |
Anna | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
'd | +0.017 |
ave | +0.014 |
would | +0.013 |
'll | +0.013 |
eded | +0.013 |
Neg logit contributions | |
Mom | -0.013 |
Lily | -0.013 |
Ben | -0.013 |
Sam | -0.013 |
Tom | -0.013 |
Token | Mia |
Token ID | 32189 |
Feature activation | +3.10e+01 |
Pos logit contributions | |
ados | +0.149 |
TV | +0.113 |
groceries | +0.112 |
avail | +0.111 |
ries | +0.107 |
Neg logit contributions | |
'd | -0.206 |
ave | -0.165 |
'll | -0.156 |
've | -0.153 |
would | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Ben | +1.138 |
Lily | +1.106 |
Mom | +1.085 |
Anna | +1.078 |
Tom | +1.071 |
Neg logit contributions | |
'd | -1.032 |
ave | -0.903 |
tted | -0.813 |
eded | -0.813 |
managed | -0.778 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.055 |
would | +0.045 |
managed | +0.045 |
forgot | +0.044 |
ave | +0.043 |
Neg logit contributions | |
ados | -0.017 |
Lily | -0.014 |
TV | -0.014 |
ummy | -0.013 |
Mom | -0.013 |
Token | love |
Token ID | 1842 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
Ben | +1.160 |
Lily | +1.137 |
Mom | +1.117 |
the | +1.079 |
Tom | +1.079 |
Neg logit contributions | |
'd | -1.163 |
ave | -1.156 |
tted | -0.997 |
ited | -0.967 |
eded | -0.962 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.50e+01 |
Pos logit contributions | |
'd | +0.756 |
would | +0.654 |
ave | +0.580 |
forgot | +0.548 |
managed | +0.545 |
Neg logit contributions | |
ados | -0.382 |
Lily | -0.351 |
Mom | -0.346 |
Uncle | -0.342 |
Sara | -0.341 |
Token | very |
Token ID | 845 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
Lily | +0.982 |
Ben | +0.978 |
Mom | +0.976 |
Tom | +0.933 |
Anna | +0.904 |
Neg logit contributions | |
'd | -1.452 |
ave | -1.241 |
eded | -1.156 |
managed | -1.095 |
tted | -1.061 |
Token | much |
Token ID | 881 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
'd | +0.260 |
ave | +0.213 |
eded | +0.199 |
sy | +0.180 |
tted | +0.177 |
Neg logit contributions | |
Ben | -0.332 |
Lily | -0.315 |
Sam | -0.315 |
Mom | -0.315 |
Tom | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
'd | +0.235 |
ave | +0.203 |
eded | +0.186 |
would | +0.175 |
managed | +0.172 |
Neg logit contributions | |
Ben | -0.163 |
Mom | -0.162 |
Lily | -0.159 |
Sam | -0.157 |
Tom | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Lily | +0.158 |
Mom | +0.156 |
Ben | +0.156 |
Tom | +0.147 |
Anna | +0.143 |
Neg logit contributions | |
'd | -0.310 |
ave | -0.271 |
eded | -0.254 |
managed | -0.243 |
tted | -0.237 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
Lily | +0.121 |
Mom | +0.115 |
Ben | +0.110 |
ados | +0.108 |
Sara | +0.105 |
Neg logit contributions | |
'd | -0.238 |
ave | -0.208 |
eded | -0.191 |
managed | -0.185 |
'll | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Lily | +0.071 |
Ben | +0.070 |
Mom | +0.069 |
ados | +0.066 |
Tom | +0.064 |
Neg logit contributions | |
'd | -0.146 |
ave | -0.125 |
eded | -0.119 |
managed | -0.112 |
tted | -0.112 |
Token | But |
Token ID | 1537 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
Ben | +0.082 |
Mom | +0.079 |
Lily | +0.079 |
Tom | +0.078 |
Anna | +0.076 |
Neg logit contributions | |
'd | -0.141 |
ave | -0.124 |
eded | -0.115 |
managed | -0.111 |
tted | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
'd | +0.369 |
ave | +0.313 |
eded | +0.304 |
managed | +0.301 |
would | +0.289 |
Neg logit contributions | |
Lily | -0.124 |
Mom | -0.115 |
Ben | -0.113 |
Tom | -0.105 |
Sara | -0.104 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
Lily | +0.039 |
Mom | +0.037 |
Ben | +0.036 |
Tom | +0.034 |
Sara | +0.033 |
Neg logit contributions | |
'd | -0.113 |
ave | -0.097 |
eded | -0.093 |
managed | -0.091 |
would | -0.088 |
Token | had |
Token ID | 550 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Ben | +1.313 |
Lily | +1.287 |
Tom | +1.228 |
Mom | +1.222 |
Max | +1.216 |
Neg logit contributions | |
'd | -0.983 |
ave | -0.880 |
tted | -0.863 |
aved | -0.772 |
wn | -0.751 |
Token | a |
Token ID | 257 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
'd | +0.655 |
ave | +0.579 |
eded | +0.545 |
managed | +0.520 |
tted | +0.516 |
Neg logit contributions | |
Lily | -0.277 |
Ben | -0.275 |
Mom | -0.274 |
Tom | -0.259 |
Anna | -0.248 |
Token | problem |
Token ID | 1917 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
Lily | +0.159 |
Mom | +0.157 |
Ben | +0.153 |
Max | +0.146 |
Anna | +0.141 |
Neg logit contributions | |
'd | -0.262 |
ave | -0.254 |
eded | -0.221 |
tted | -0.216 |
managed | -0.207 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
'd | +0.322 |
ave | +0.283 |
eded | +0.266 |
managed | +0.255 |
tted | +0.249 |
Neg logit contributions | |
Lily | -0.144 |
Mom | -0.143 |
Ben | -0.143 |
Tom | -0.134 |
Anna | -0.130 |
Token | The |
Token ID | 383 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
Lily | +0.104 |
Mom | +0.097 |
Ben | +0.095 |
Tom | +0.089 |
Sara | +0.088 |
Neg logit contributions | |
'd | -0.261 |
ave | -0.233 |
eded | -0.215 |
managed | -0.208 |
tted | -0.206 |
Token | fierce |
Token ID | 14800 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Ben | +0.062 |
Lily | +0.062 |
Mom | +0.062 |
Tom | +0.059 |
Anna | +0.058 |
Neg logit contributions | |
'd | -0.086 |
ave | -0.072 |
eded | -0.067 |
managed | -0.064 |
tted | -0.062 |
Token | lion |
Token ID | 18744 |
Feature activation | +2.33e+01 |
Pos logit contributions | |
'd | +0.101 |
ave | +0.078 |
eded | +0.076 |
would | +0.076 |
forgot | +0.072 |
Neg logit contributions | |
Mom | -0.057 |
Ben | -0.056 |
Lily | -0.055 |
Tom | -0.053 |
Anna | -0.053 |
Token | named |
Token ID | 3706 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
Lily | +0.733 |
Mom | +0.728 |
Ben | +0.727 |
Tom | +0.697 |
Anna | +0.682 |
Neg logit contributions | |
'd | -0.892 |
ave | -0.755 |
eded | -0.697 |
managed | -0.658 |
tted | -0.638 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
'd | +0.208 |
ave | +0.166 |
would | +0.161 |
eded | +0.159 |
've | +0.158 |
Neg logit contributions | |
ados | -0.064 |
ries | -0.057 |
yourselves | -0.056 |
Mom | -0.056 |
ment | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Lily | +0.778 |
Mom | +0.773 |
Ben | +0.769 |
Tom | +0.725 |
Anna | +0.703 |
Neg logit contributions | |
'd | -1.675 |
ave | -1.465 |
eded | -1.379 |
managed | -1.318 |
tted | -1.285 |
Token | Leo |
Token ID | 19632 |
Feature activation | +3.51e+01 |
Pos logit contributions | |
Lily | +0.082 |
Mom | +0.079 |
Sara | +0.066 |
grandma | +0.064 |
Ben | +0.063 |
Neg logit contributions | |
'd | -0.281 |
ave | -0.238 |
eded | -0.225 |
would | -0.222 |
managed | -0.220 |
Token | lived |
Token ID | 5615 |
Feature activation | -9.89e+00 |
Pos logit contributions | |
Lily | +1.157 |
his | +1.133 |
Ben | +1.122 |
Mom | +1.120 |
the | +1.116 |
Neg logit contributions | |
ave | -1.129 |
'd | -1.124 |
ited | -1.013 |
tted | -1.005 |
managed | -0.909 |
Token | in |
Token ID | 287 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
'd | +0.408 |
ave | +0.344 |
eded | +0.316 |
managed | +0.299 |
forgot | +0.294 |
Neg logit contributions | |
Lily | -0.299 |
Ben | -0.296 |
Mom | -0.292 |
Tom | -0.281 |
Anna | -0.276 |
Token | a |
Token ID | 257 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
'd | +0.358 |
eded | +0.297 |
ave | +0.285 |
managed | +0.282 |
sy | +0.272 |
Neg logit contributions | |
Mom | -0.199 |
Lily | -0.197 |
ados | -0.195 |
Ben | -0.186 |
Dad | -0.185 |
Token | jungle |
Token ID | 20712 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
Mom | +0.172 |
Lily | +0.172 |
Ben | +0.172 |
Tom | +0.165 |
Sara | +0.160 |
Neg logit contributions | |
'd | -0.246 |
ave | -0.203 |
eded | -0.194 |
managed | -0.183 |
sy | -0.179 |
Token | with |
Token ID | 351 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
Lily | +0.207 |
Ben | +0.207 |
Mom | +0.205 |
Tom | +0.199 |
Anna | +0.191 |
Neg logit contributions | |
'd | -0.387 |
ave | -0.336 |
eded | -0.313 |
managed | -0.302 |
tted | -0.293 |
Token | my |
Token ID | 1820 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
'd | +0.739 |
ave | +0.652 |
eded | +0.599 |
be | +0.595 |
uch | +0.581 |
Neg logit contributions | |
Lily | -0.409 |
Uncle | -0.406 |
Ben | -0.395 |
Mom | -0.387 |
Tom | -0.385 |
Token | was |
Token ID | 373 |
Feature activation | -2.02e+01 |
Pos logit contributions | |
Lily | +0.078 |
Ben | +0.078 |
Mom | +0.077 |
Tom | +0.075 |
Max | +0.073 |
Neg logit contributions | |
'd | -0.076 |
ave | -0.064 |
tted | -0.061 |
eded | -0.061 |
sy | -0.055 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
'd | +0.801 |
ave | +0.683 |
eded | +0.632 |
managed | +0.596 |
tted | +0.583 |
Neg logit contributions | |
Lily | -0.616 |
Mom | -0.612 |
Ben | -0.610 |
Tom | -0.584 |
Anna | -0.571 |
Token | and |
Token ID | 290 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
'd | +0.473 |
ave | +0.389 |
eded | +0.352 |
would | +0.347 |
managed | +0.346 |
Neg logit contributions | |
Ben | -0.343 |
Lily | -0.336 |
Mom | -0.334 |
Tom | -0.327 |
Anna | -0.321 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
'd | +0.255 |
ave | +0.216 |
eded | +0.200 |
tted | +0.186 |
managed | +0.183 |
Neg logit contributions | |
Lily | -0.237 |
Mom | -0.236 |
Ben | -0.232 |
Tom | -0.224 |
Max | -0.220 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.58e+01 |
Pos logit contributions | |
'd | +0.205 |
eded | +0.104 |
sy | +0.083 |
andering | +0.082 |
've | +0.078 |
Neg logit contributions | |
Lily | -0.698 |
Ben | -0.650 |
Tom | -0.633 |
Max | -0.624 |
Anna | -0.612 |
Token | his |
Token ID | 465 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
'd | +1.467 |
would | +1.291 |
wouldn | +1.216 |
ave | +1.211 |
'll | +1.180 |
Neg logit contributions | |
Glass | -0.471 |
Leo | -0.463 |
Farmer | -0.457 |
ados | -0.448 |
Water | -0.443 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
Ben | +0.233 |
Tom | +0.224 |
Lily | +0.219 |
Anna | +0.212 |
Sara | +0.205 |
Neg logit contributions | |
'd | -0.633 |
ave | -0.538 |
eded | -0.520 |
forgot | -0.497 |
managed | -0.493 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Mom | +0.330 |
Ben | +0.328 |
Lily | +0.327 |
Tom | +0.315 |
Anna | +0.306 |
Neg logit contributions | |
'd | -0.573 |
ave | -0.500 |
eded | -0.462 |
managed | -0.441 |
forgot | -0.427 |
Token | The |
Token ID | 383 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
avail | +0.018 |
ados | +0.017 |
ries | +0.017 |
groceries | +0.016 |
TV | +0.016 |
Neg logit contributions | |
'd | -0.020 |
ave | -0.016 |
hadn | -0.015 |
'll | -0.015 |
've | -0.015 |
Token | end |
Token ID | 886 |
Feature activation | -8.19e+00 |
Pos logit contributions | |
Lily | +0.108 |
Ben | +0.108 |
Mom | +0.106 |
Tom | +0.105 |
Anna | +0.101 |
Neg logit contributions | |
'd | -0.156 |
ave | -0.130 |
eded | -0.122 |
managed | -0.115 |
tted | -0.111 |
Token | zo |
Token ID | 40565 |
Feature activation | -8.66e+00 |
Pos logit contributions | |
Lily | +0.202 |
Ben | +0.199 |
Mom | +0.198 |
Tom | +0.191 |
Anna | +0.184 |
Neg logit contributions | |
'd | -0.365 |
ave | -0.306 |
eded | -0.291 |
managed | -0.276 |
tted | -0.269 |
Token | oke |
Token ID | 2088 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
'd | +0.260 |
ave | +0.208 |
eded | +0.190 |
managed | +0.176 |
tted | +0.167 |
Neg logit contributions | |
Ben | -0.342 |
Lily | -0.342 |
Mom | -0.338 |
Tom | -0.332 |
Anna | -0.326 |
Token | ep |
Token ID | 538 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
'd | +0.539 |
ave | +0.463 |
eded | +0.428 |
managed | +0.402 |
tted | +0.398 |
Neg logit contributions | |
Lily | -0.390 |
Ben | -0.390 |
Mom | -0.387 |
Tom | -0.378 |
Anna | -0.363 |
Token | ers |
Token ID | 364 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
'd | +0.098 |
ave | +0.079 |
eded | +0.074 |
managed | +0.068 |
ited | +0.067 |
Neg logit contributions | |
Lily | -0.111 |
Mom | -0.110 |
Ben | -0.110 |
Tom | -0.109 |
Sam | -0.105 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
Ben | +0.197 |
Lily | +0.193 |
Tom | +0.192 |
Mom | +0.191 |
Max | +0.181 |
Neg logit contributions | |
'd | -0.203 |
ave | -0.174 |
eded | -0.161 |
managed | -0.147 |
tted | -0.146 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.56e+01 |
Pos logit contributions | |
'd | +0.240 |
eded | +0.163 |
sy | +0.132 |
managed | +0.130 |
ited | +0.119 |
Neg logit contributions | |
Lily | -0.624 |
Ben | -0.609 |
Tom | -0.594 |
Sam | -0.572 |
Anna | -0.567 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.58e+01 |
Pos logit contributions | |
'd | +1.613 |
would | +1.331 |
ave | +1.328 |
eded | +1.305 |
wouldn | +1.243 |
Neg logit contributions | |
Mom | -0.490 |
Glass | -0.432 |
Lily | -0.425 |
Ben | -0.411 |
Dad | -0.396 |
Token | and |
Token ID | 290 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
Lily | +0.656 |
Mom | +0.655 |
Ben | +0.648 |
Tom | +0.613 |
Anna | +0.602 |
Neg logit contributions | |
'd | -1.138 |
ave | -0.984 |
eded | -0.917 |
managed | -0.874 |
tted | -0.846 |
Token | said |
Token ID | 531 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
'd | +0.289 |
ave | +0.251 |
eded | +0.236 |
managed | +0.235 |
forgot | +0.230 |
Neg logit contributions | |
Mom | -0.118 |
Ben | -0.114 |
Lily | -0.114 |
Tom | -0.105 |
Anna | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
'd | +0.282 |
ave | +0.236 |
eded | +0.221 |
managed | +0.220 |
would | +0.212 |
Neg logit contributions | |
Ben | -0.155 |
Mom | -0.155 |
Lily | -0.154 |
Anna | -0.146 |
Tom | -0.146 |
Token | " |
Token ID | 366 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
'd | +0.111 |
ave | +0.091 |
eded | +0.086 |
managed | +0.086 |
would | +0.084 |
Neg logit contributions | |
Ben | -0.043 |
Lily | -0.043 |
Mom | -0.042 |
Tom | -0.040 |
Anna | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
'd | +0.861 |
ave | +0.775 |
would | +0.721 |
eded | +0.682 |
forgot | +0.676 |
Neg logit contributions | |
Mom | -0.340 |
Ben | -0.339 |
ados | -0.338 |
Farmer | -0.336 |
Uncle | -0.322 |
Token | She |
Token ID | 1375 |
Feature activation | +8.03e+00 |
Pos logit contributions | |
'd | +0.047 |
ave | +0.038 |
'll | +0.036 |
've | +0.035 |
hadn | +0.035 |
Neg logit contributions | |
ados | -0.025 |
avail | -0.023 |
ries | -0.021 |
Ben | -0.021 |
TV | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
Ben | +0.295 |
Lily | +0.294 |
Mom | +0.286 |
Tom | +0.278 |
Anna | +0.278 |
Neg logit contributions | |
'd | -0.266 |
ave | -0.233 |
tted | -0.222 |
sy | -0.208 |
eded | -0.207 |
Token | she |
Token ID | 673 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
'd | +0.313 |
ave | +0.262 |
managed | +0.244 |
would | +0.244 |
eded | +0.237 |
Neg logit contributions | |
Ben | -0.170 |
Mom | -0.169 |
Lily | -0.168 |
Uncle | -0.166 |
ados | -0.164 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
Lily | +0.604 |
Mom | +0.590 |
Ben | +0.575 |
Tom | +0.565 |
Anna | +0.552 |
Neg logit contributions | |
ited | -0.339 |
'd | -0.339 |
tted | -0.334 |
ave | -0.321 |
rated | -0.313 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.56e+01 |
Pos logit contributions | |
'd | +0.183 |
eded | +0.111 |
sy | +0.097 |
managed | +0.083 |
tted | +0.076 |
Neg logit contributions | |
Lily | -0.684 |
Ben | -0.669 |
Tom | -0.646 |
Anna | -0.634 |
Sam | -0.626 |
Token | him |
Token ID | 683 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
'd | +1.442 |
would | +1.242 |
wouldn | +1.167 |
ave | +1.160 |
eded | +1.119 |
Neg logit contributions | |
Glass | -0.531 |
Farmer | -0.511 |
Water | -0.481 |
ados | -0.476 |
Uncle | -0.471 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Mom | +0.313 |
Ben | +0.309 |
Lily | +0.306 |
Tom | +0.298 |
Sam | +0.285 |
Neg logit contributions | |
'd | -0.496 |
ave | -0.419 |
eded | -0.389 |
managed | -0.367 |
sy | -0.363 |
Token | Then |
Token ID | 3244 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
ados | +0.016 |
avail | +0.016 |
ries | +0.015 |
groceries | +0.015 |
things | +0.014 |
Neg logit contributions | |
'd | -0.020 |
ave | -0.016 |
hadn | -0.015 |
'll | -0.015 |
could | -0.015 |
Token | Joe |
Token ID | 5689 |
Feature activation | +2.74e+01 |
Pos logit contributions | |
'd | +0.353 |
managed | +0.298 |
forgot | +0.296 |
ave | +0.291 |
would | +0.291 |
Neg logit contributions | |
ados | -0.130 |
TV | -0.127 |
Ben | -0.123 |
Mom | -0.122 |
Farmer | -0.120 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.48e+01 |
Pos logit contributions | |
Ben | +1.076 |
Lily | +1.055 |
Tom | +1.012 |
Mom | +1.009 |
Anna | +1.008 |
Neg logit contributions | |
'd | -0.810 |
ave | -0.677 |
tted | -0.631 |
eded | -0.627 |
aved | -0.583 |
Token | an |
Token ID | 281 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
'd | +0.748 |
ave | +0.615 |
eded | +0.587 |
managed | +0.566 |
succeeded | +0.533 |
Neg logit contributions | |
Lily | -0.568 |
Ben | -0.567 |
Mom | -0.567 |
Tom | -0.542 |
Anna | -0.535 |
Token | accident |
Token ID | 5778 |
Feature activation | -6.91e+00 |
Pos logit contributions | |
'd | +0.131 |
ave | +0.111 |
eded | +0.103 |
managed | +0.098 |
tted | +0.095 |
Neg logit contributions | |
Lily | -0.095 |
Ben | -0.095 |
Mom | -0.095 |
Tom | -0.090 |
Anna | -0.089 |
Token | ." |
Token ID | 526 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
'd | +0.321 |
ave | +0.280 |
eded | +0.263 |
managed | +0.251 |
tted | +0.245 |
Neg logit contributions | |
Lily | -0.161 |
Mom | -0.160 |
Ben | -0.159 |
Tom | -0.150 |
Anna | -0.146 |
Token | Billy |
Token ID | 15890 |
Feature activation | +2.61e+01 |
Pos logit contributions | |
'd | +0.079 |
ave | +0.072 |
forgot | +0.064 |
managed | +0.063 |
've | +0.062 |
Neg logit contributions | |
ados | -0.046 |
avail | -0.041 |
ries | -0.039 |
TV | -0.038 |
novels | -0.036 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.25e+01 |
Pos logit contributions | |
Ben | +0.966 |
Lily | +0.966 |
Mom | +0.930 |
Tom | +0.925 |
Max | +0.912 |
Neg logit contributions | |
'd | -0.866 |
ave | -0.719 |
tted | -0.675 |
eded | -0.661 |
aved | -0.606 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.52e+01 |
Pos logit contributions | |
'd | +0.202 |
've | +0.100 |
eded | +0.092 |
uch | +0.078 |
'll | +0.073 |
Neg logit contributions | |
Lily | -0.664 |
Ben | -0.637 |
Tom | -0.617 |
Sam | -0.614 |
Max | -0.603 |
Token | her |
Token ID | 607 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
'd | +1.342 |
would | +1.127 |
eded | +1.118 |
ave | +1.104 |
managed | +1.086 |
Neg logit contributions | |
Anna | -0.624 |
Sara | -0.593 |
Mir | -0.572 |
Sunny | -0.561 |
Leo | -0.551 |
Token | and |
Token ID | 290 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
Ben | +0.454 |
Lily | +0.446 |
Mom | +0.439 |
Tom | +0.438 |
Anna | +0.427 |
Neg logit contributions | |
'd | -0.629 |
ave | -0.530 |
eded | -0.490 |
managed | -0.459 |
sy | -0.457 |
Token | they |
Token ID | 484 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
'd | +0.272 |
ave | +0.239 |
eded | +0.225 |
managed | +0.213 |
tted | +0.213 |
Neg logit contributions | |
Lily | -0.122 |
Ben | -0.120 |
Mom | -0.120 |
Tom | -0.113 |
Max | -0.109 |
Token | continued |
Token ID | 3767 |
Feature activation | -1.70e+01 |
Pos logit contributions | |
Lily | +0.522 |
Mom | +0.519 |
Ben | +0.518 |
Tom | +0.495 |
Max | +0.491 |
Neg logit contributions | |
'd | -0.420 |
ave | -0.339 |
eded | -0.307 |
tted | -0.301 |
anticipated | -0.281 |
Token | playing |
Token ID | 2712 |
Feature activation | -8.81e+00 |
Pos logit contributions | |
'd | +0.749 |
ave | +0.649 |
eded | +0.610 |
managed | +0.583 |
tted | +0.565 |
Neg logit contributions | |
Lily | -0.431 |
Ben | -0.429 |
Mom | -0.426 |
Tom | -0.407 |
Anna | -0.399 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Lily | +0.014 |
Ben | +0.014 |
Mom | +0.014 |
Tom | +0.014 |
Anna | +0.013 |
Neg logit contributions | |
'd | -0.030 |
ave | -0.025 |
eded | -0.024 |
sy | -0.023 |
managed | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
Ben | +0.557 |
Lily | +0.555 |
Tom | +0.545 |
Mom | +0.544 |
Anna | +0.534 |
Neg logit contributions | |
'd | -0.467 |
ave | -0.397 |
tted | -0.364 |
eded | -0.360 |
aved | -0.346 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
'd | +0.312 |
forgot | +0.274 |
managed | +0.268 |
would | +0.261 |
ave | +0.258 |
Neg logit contributions | |
ummy | -0.081 |
ados | -0.077 |
TV | -0.058 |
ries | -0.049 |
yourselves | -0.049 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
Lily | +0.245 |
Ben | +0.241 |
Mom | +0.234 |
Tom | +0.234 |
Anna | +0.227 |
Neg logit contributions | |
'd | -0.479 |
ave | -0.395 |
eded | -0.380 |
would | -0.361 |
managed | -0.360 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
Mom | +0.588 |
Ben | +0.585 |
Lily | +0.573 |
Tom | +0.571 |
Sam | +0.546 |
Neg logit contributions | |
'd | -0.422 |
ave | -0.360 |
tted | -0.330 |
eded | -0.321 |
sy | -0.299 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.51e+01 |
Pos logit contributions | |
'd | +0.202 |
eded | +0.110 |
uch | +0.098 |
've | +0.095 |
ited | +0.094 |
Neg logit contributions | |
Lily | -0.618 |
Ben | -0.606 |
Tom | -0.578 |
Sam | -0.574 |
Max | -0.569 |
Token | Spike |
Token ID | 26309 |
Feature activation | +1.95e+01 |
Pos logit contributions | |
'd | +1.401 |
eded | +1.223 |
would | +1.217 |
ave | +1.157 |
managed | +1.135 |
Neg logit contributions | |
ados | -0.543 |
Glass | -0.528 |
Ben | -0.488 |
Lily | -0.483 |
Anna | -0.464 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Mom | +0.559 |
Ben | +0.533 |
Lily | +0.533 |
Tom | +0.519 |
Dad | +0.498 |
Neg logit contributions | |
'd | -0.769 |
ave | -0.663 |
eded | -0.610 |
sy | -0.571 |
would | -0.569 |
Token | They |
Token ID | 1119 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
avail | +0.027 |
ados | +0.027 |
ries | +0.027 |
Uncle | +0.026 |
her | +0.026 |
Neg logit contributions | |
'd | -0.036 |
ave | -0.030 |
tted | -0.029 |
'll | -0.028 |
managed | -0.027 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.73e+01 |
Pos logit contributions | |
Lily | +0.218 |
Ben | +0.218 |
Mom | +0.214 |
Tom | +0.210 |
Max | +0.205 |
Neg logit contributions | |
'd | -0.146 |
ave | -0.124 |
tted | -0.110 |
eded | -0.107 |
rated | -0.104 |
Token | he |
Token ID | 339 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
'd | +0.808 |
eded | +0.659 |
managed | +0.654 |
would | +0.646 |
ave | +0.644 |
Neg logit contributions | |
Mom | -0.333 |
Ben | -0.325 |
Lily | -0.320 |
Anna | -0.310 |
ados | -0.308 |
Token | They |
Token ID | 2990 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
'd | +0.078 |
ave | +0.064 |
eded | +0.060 |
tted | +0.058 |
managed | +0.056 |
Neg logit contributions | |
Mom | -0.071 |
Lily | -0.070 |
Ben | -0.070 |
Tom | -0.066 |
ados | -0.066 |
Token | hugged |
Token ID | 41130 |
Feature activation | -2.20e+01 |
Pos logit contributions | |
'd | +0.004 |
ave | +0.004 |
eded | +0.003 |
tted | +0.003 |
sy | +0.003 |
Neg logit contributions | |
Ben | -0.006 |
Lily | -0.005 |
Mom | -0.005 |
Tom | -0.005 |
Max | -0.005 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.73e+01 |
Pos logit contributions | |
'd | +0.688 |
ave | +0.584 |
would | +0.582 |
eded | +0.579 |
wouldn | +0.527 |
Neg logit contributions | |
ados | -0.541 |
Glass | -0.531 |
avail | -0.492 |
ummy | -0.487 |
Lily | -0.482 |
Token | and |
Token ID | 290 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
Lily | +0.881 |
Mom | +0.876 |
Ben | +0.867 |
Tom | +0.848 |
Sara | +0.842 |
Neg logit contributions | |
'd | -0.941 |
ave | -0.769 |
eded | -0.713 |
would | -0.663 |
sy | -0.663 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
'd | +0.204 |
ave | +0.170 |
eded | +0.155 |
managed | +0.148 |
forgot | +0.144 |
Neg logit contributions | |
Mom | -0.204 |
Lily | -0.203 |
Ben | -0.203 |
Tom | -0.195 |
Anna | -0.193 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.51e+01 |
Pos logit contributions | |
'd | +0.191 |
've | +0.102 |
eded | +0.098 |
managed | +0.082 |
succeeded | +0.075 |
Neg logit contributions | |
Lily | -0.641 |
Ben | -0.629 |
Tom | -0.608 |
Max | -0.598 |
Sam | -0.590 |
Token | him |
Token ID | 683 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
'd | +1.386 |
would | +1.207 |
ave | +1.096 |
eded | +1.066 |
wouldn | +1.043 |
Neg logit contributions | |
ados | -0.702 |
Glass | -0.677 |
Sara | -0.676 |
Lily | -0.663 |
Mom | -0.660 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Mom | +0.331 |
Ben | +0.329 |
Lily | +0.327 |
Tom | +0.318 |
Anna | +0.309 |
Neg logit contributions | |
'd | -0.494 |
ave | -0.419 |
eded | -0.391 |
would | -0.367 |
sy | -0.367 |
Token | They |
Token ID | 1119 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
ados | +0.033 |
ries | +0.029 |
avail | +0.029 |
groceries | +0.027 |
avocado | +0.025 |
Neg logit contributions | |
'd | -0.036 |
ave | -0.028 |
would | -0.027 |
'll | -0.027 |
hadn | -0.026 |
Token | decided |
Token ID | 3066 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
Lily | +0.211 |
Ben | +0.208 |
Mom | +0.207 |
Tom | +0.201 |
Max | +0.195 |
Neg logit contributions | |
'd | -0.152 |
ave | -0.128 |
tted | -0.123 |
rated | -0.119 |
eded | -0.111 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
'd | +0.671 |
ave | +0.569 |
eded | +0.531 |
managed | +0.509 |
forgot | +0.488 |
Neg logit contributions | |
Lily | -0.480 |
Mom | -0.478 |
Ben | -0.478 |
Tom | -0.452 |
Anna | -0.450 |
Token | apologized |
Token ID | 22893 |
Feature activation | -1.81e+01 |
Pos logit contributions | |
'd | +0.212 |
ave | +0.174 |
eded | +0.158 |
managed | +0.149 |
forgot | +0.141 |
Neg logit contributions | |
Mom | -0.235 |
Ben | -0.234 |
Lily | -0.234 |
Tom | -0.226 |
Anna | -0.222 |
Token | . |
Token ID | 13 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
'd | +0.682 |
ave | +0.585 |
eded | +0.539 |
would | +0.514 |
managed | +0.500 |
Neg logit contributions | |
Mom | -0.522 |
Ben | -0.518 |
Lily | -0.505 |
Tom | -0.495 |
Anna | -0.492 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
avail | +0.010 |
ados | +0.010 |
TV | +0.010 |
things | +0.009 |
ries | +0.009 |
Neg logit contributions | |
'd | -0.019 |
ave | -0.017 |
forgot | -0.015 |
'll | -0.015 |
managed | -0.015 |
Token | ens |
Token ID | 641 |
Feature activation | +1.91e+01 |
Pos logit contributions | |
Mom | +0.343 |
Lily | +0.338 |
Ben | +0.336 |
Tom | +0.318 |
Anna | +0.312 |
Neg logit contributions | |
'd | -0.720 |
ave | -0.634 |
eded | -0.592 |
managed | -0.567 |
forgot | -0.550 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
Lily | +0.802 |
Ben | +0.786 |
Mom | +0.769 |
Tom | +0.755 |
Max | +0.751 |
Neg logit contributions | |
'd | -0.547 |
ave | -0.444 |
eded | -0.383 |
tted | -0.378 |
aved | -0.373 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.50e+01 |
Pos logit contributions | |
'd | +0.225 |
've | +0.119 |
eded | +0.108 |
'll | +0.104 |
andering | +0.099 |
Neg logit contributions | |
Lily | -0.627 |
Ben | -0.584 |
Max | -0.571 |
Tom | -0.569 |
Sam | -0.558 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.79e+01 |
Pos logit contributions | |
'd | +1.503 |
would | +1.327 |
ave | +1.318 |
wouldn | +1.284 |
eded | +1.265 |
Neg logit contributions | |
ados | -0.512 |
Dad | -0.497 |
Mom | -0.478 |
novels | -0.451 |
France | -0.450 |
Token | and |
Token ID | 290 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
Mom | +0.813 |
Ben | +0.798 |
Lily | +0.795 |
Tom | +0.769 |
Anna | +0.751 |
Neg logit contributions | |
'd | -1.107 |
ave | -0.955 |
eded | -0.880 |
managed | -0.840 |
forgot | -0.806 |
Token | they |
Token ID | 484 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
'd | +0.238 |
ave | +0.206 |
eded | +0.193 |
managed | +0.184 |
tted | +0.180 |
Neg logit contributions | |
Lily | -0.140 |
Mom | -0.138 |
Ben | -0.138 |
Tom | -0.131 |
Anna | -0.128 |
Token | played |
Token ID | 2826 |
Feature activation | -2.16e+01 |
Pos logit contributions | |
Lily | +0.569 |
Mom | +0.560 |
Ben | +0.557 |
Tom | +0.539 |
Max | +0.538 |
Neg logit contributions | |
'd | -0.393 |
ave | -0.321 |
eded | -0.275 |
tted | -0.267 |
ited | -0.253 |
Token | together |
Token ID | 1978 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
'd | +0.720 |
ave | +0.627 |
eded | +0.591 |
managed | +0.559 |
tted | +0.553 |
Neg logit contributions | |
Mom | -0.703 |
Ben | -0.679 |
Uncle | -0.665 |
Lily | -0.665 |
Tom | -0.657 |
Token | with |
Token ID | 351 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
'd | +0.803 |
ave | +0.673 |
eded | +0.627 |
managed | +0.606 |
tted | +0.601 |
Neg logit contributions | |
Mom | -0.713 |
Ben | -0.693 |
Uncle | -0.690 |
Tom | -0.670 |
Dad | -0.666 |
Token | Spot |
Token ID | 15899 |
Feature activation | +2.40e+01 |
Pos logit contributions | |
'd | +0.655 |
managed | +0.580 |
would | +0.579 |
ave | +0.557 |
tasted | +0.546 |
Neg logit contributions | |
Uncle | -0.230 |
ummy | -0.216 |
Lee | -0.210 |
ados | -0.205 |
Mother | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Mom | +0.589 |
Lily | +0.589 |
Ben | +0.584 |
Tom | +0.557 |
Anna | +0.540 |
Neg logit contributions | |
'd | -1.074 |
ave | -0.929 |
eded | -0.873 |
managed | -0.831 |
sy | -0.805 |
Token | They |
Token ID | 1119 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ados | +0.016 |
avail | +0.015 |
her | +0.015 |
ries | +0.014 |
Mom | +0.013 |
Neg logit contributions | |
'd | -0.031 |
ave | -0.027 |
'll | -0.025 |
tted | -0.025 |
've | -0.024 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
Lily | +0.221 |
Ben | +0.216 |
Mom | +0.212 |
Tom | +0.210 |
Max | +0.205 |
Neg logit contributions | |
'd | -0.128 |
ave | -0.115 |
tted | -0.100 |
eded | -0.097 |
rated | -0.088 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.49e+01 |
Pos logit contributions | |
'd | +0.200 |
eded | +0.098 |
've | +0.093 |
'll | +0.084 |
ited | +0.075 |
Neg logit contributions | |
Lily | -0.626 |
Ben | -0.601 |
Max | -0.593 |
Tom | -0.591 |
Sam | -0.580 |
Token | him |
Token ID | 683 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
'd | +1.600 |
would | +1.396 |
eded | +1.365 |
ave | +1.345 |
wouldn | +1.266 |
Neg logit contributions | |
ados | -0.506 |
Lily | -0.494 |
Mom | -0.491 |
Lisa | -0.458 |
Anna | -0.455 |
Token | for |
Token ID | 329 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
Mom | +0.377 |
Ben | +0.374 |
Lily | +0.373 |
Tom | +0.356 |
Anna | +0.354 |
Neg logit contributions | |
'd | -0.485 |
ave | -0.411 |
eded | -0.381 |
managed | -0.357 |
sy | -0.347 |
Token | tearing |
Token ID | 24447 |
Feature activation | -1.82e+01 |
Pos logit contributions | |
'd | +0.417 |
eded | +0.332 |
managed | +0.315 |
ave | +0.306 |
succeeded | +0.293 |
Neg logit contributions | |
Mom | -0.392 |
Ben | -0.382 |
Lily | -0.379 |
Anna | -0.374 |
Sara | -0.368 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
'd | +0.701 |
ave | +0.636 |
'll | +0.625 |
ched | +0.617 |
would | +0.614 |
Neg logit contributions | |
Uncle | -0.281 |
Mom | -0.274 |
Mother | -0.264 |
God | -0.260 |
Ben | -0.253 |
Token | map |
Token ID | 3975 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
Lily | +0.274 |
Mom | +0.272 |
Ben | +0.271 |
Tom | +0.257 |
Anna | +0.250 |
Neg logit contributions | |
'd | -0.538 |
ave | -0.468 |
eded | -0.439 |
managed | -0.420 |
tted | -0.410 |
Token |
|
Token ID | 198 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
'd | +0.071 |
ave | +0.057 |
eded | +0.056 |
tted | +0.054 |
managed | +0.052 |
Neg logit contributions | |
ados | -0.051 |
Lily | -0.047 |
Ben | -0.047 |
Mom | -0.046 |
Max | -0.044 |
Token | Mom |
Token ID | 29252 |
Feature activation | +8.12e+00 |
Pos logit contributions | |
'd | +0.061 |
ave | +0.051 |
eded | +0.047 |
tted | +0.046 |
managed | +0.045 |
Neg logit contributions | |
Mom | -0.052 |
Lily | -0.051 |
Ben | -0.050 |
Tom | -0.048 |
Max | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
Ben | +0.273 |
Lily | +0.267 |
Tom | +0.266 |
Mom | +0.262 |
Anna | +0.254 |
Neg logit contributions | |
'd | -0.296 |
ave | -0.256 |
eded | -0.237 |
tted | -0.230 |
managed | -0.216 |
Token | Dad |
Token ID | 17415 |
Feature activation | +2.59e+01 |
Pos logit contributions | |
'd | +0.288 |
forgot | +0.249 |
ave | +0.245 |
managed | +0.245 |
would | +0.237 |
Neg logit contributions | |
ados | -0.069 |
ummy | -0.066 |
TV | -0.058 |
Lily | -0.055 |
avail | -0.055 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
Ben | +1.005 |
Tom | +1.000 |
Mom | +0.959 |
Lily | +0.942 |
the | +0.915 |
Neg logit contributions | |
'd | -0.736 |
ave | -0.666 |
tted | -0.591 |
sy | -0.579 |
rated | -0.573 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.49e+01 |
Pos logit contributions | |
'd | +0.200 |
eded | +0.108 |
sy | +0.094 |
've | +0.094 |
managed | +0.086 |
Neg logit contributions | |
Ben | -0.616 |
Lily | -0.614 |
Tom | -0.602 |
Anna | -0.575 |
Max | -0.575 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.84e+01 |
Pos logit contributions | |
'd | +1.388 |
would | +1.180 |
ave | +1.110 |
eded | +1.090 |
'll | +1.090 |
Neg logit contributions | |
Glass | -0.509 |
ados | -0.486 |
Water | -0.448 |
sofa | -0.425 |
novels | -0.410 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
Mom | +0.834 |
Lily | +0.830 |
Ben | +0.818 |
Tom | +0.782 |
Anna | +0.771 |
Neg logit contributions | |
'd | -1.120 |
ave | -0.955 |
eded | -0.880 |
managed | -0.838 |
forgot | -0.805 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.56e+01 |
Pos logit contributions | |
'd | +0.247 |
ave | +0.214 |
eded | +0.200 |
managed | +0.199 |
forgot | +0.194 |
Neg logit contributions | |
Mom | -0.113 |
Lily | -0.111 |
Ben | -0.110 |
Tom | -0.104 |
Max | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Ben | +0.592 |
Lily | +0.588 |
Mom | +0.586 |
Tom | +0.560 |
Max | +0.531 |
Neg logit contributions | |
'd | -1.213 |
ave | -1.061 |
eded | -1.009 |
tted | -0.967 |
managed | -0.946 |
Token | They |
Token ID | 1119 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
ados | +0.043 |
avail | +0.039 |
ries | +0.036 |
my | +0.035 |
groceries | +0.034 |
Neg logit contributions | |
'd | -0.044 |
ave | -0.038 |
'll | -0.035 |
forgot | -0.033 |
would | -0.033 |
Token | him |
Token ID | 683 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
'd | +0.585 |
eded | +0.507 |
managed | +0.500 |
ave | +0.484 |
succeeded | +0.473 |
Neg logit contributions | |
Ben | -0.207 |
Anna | -0.205 |
Mom | -0.203 |
Lily | -0.196 |
Uncle | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Lily | +0.290 |
Ben | +0.287 |
Mom | +0.287 |
Tom | +0.274 |
Max | +0.266 |
Neg logit contributions | |
'd | -0.543 |
ave | -0.477 |
eded | -0.445 |
managed | -0.422 |
tted | -0.415 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
ados | +0.018 |
avail | +0.017 |
her | +0.016 |
Ben | +0.016 |
ries | +0.016 |
Neg logit contributions | |
'd | -0.029 |
ave | -0.024 |
'll | -0.023 |
hadn | -0.022 |
've | -0.022 |
Token | my |
Token ID | 1820 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
Lily | +0.619 |
Ben | +0.609 |
Tom | +0.593 |
Max | +0.593 |
Sam | +0.568 |
Neg logit contributions | |
'd | -0.996 |
ave | -0.890 |
tted | -0.871 |
eded | -0.836 |
anticipated | -0.786 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
Ben | +0.180 |
Lily | +0.175 |
Max | +0.172 |
the | +0.172 |
Tom | +0.172 |
Neg logit contributions | |
'd | -0.173 |
ave | -0.153 |
tted | -0.150 |
eded | -0.141 |
aved | -0.136 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.48e+01 |
Pos logit contributions | |
'd | +0.201 |
eded | +0.113 |
sy | +0.101 |
andering | +0.095 |
've | +0.092 |
Neg logit contributions | |
Lily | -0.620 |
Ben | -0.596 |
Tom | -0.586 |
Max | -0.577 |
Sam | -0.567 |
Token | Bobby |
Token ID | 17155 |
Feature activation | +2.22e+01 |
Pos logit contributions | |
'd | +1.373 |
would | +1.203 |
wouldn | +1.167 |
ave | +1.140 |
eded | +1.119 |
Neg logit contributions | |
Anna | -0.507 |
Ben | -0.485 |
ados | -0.481 |
Glass | -0.472 |
sofa | -0.453 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
Mom | +0.647 |
Ben | +0.639 |
Lily | +0.639 |
Tom | +0.610 |
Anna | +0.610 |
Neg logit contributions | |
'd | -0.865 |
ave | -0.742 |
eded | -0.678 |
sy | -0.649 |
managed | -0.649 |
Token | they |
Token ID | 484 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
'd | +0.256 |
ave | +0.225 |
eded | +0.212 |
managed | +0.203 |
tted | +0.199 |
Neg logit contributions | |
Lily | -0.109 |
Mom | -0.108 |
Ben | -0.108 |
Tom | -0.101 |
Anna | -0.098 |
Token | played |
Token ID | 2826 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
Lily | +0.550 |
Ben | +0.544 |
Mom | +0.544 |
Tom | +0.531 |
Max | +0.525 |
Neg logit contributions | |
'd | -0.409 |
ave | -0.339 |
eded | -0.296 |
tted | -0.285 |
ited | -0.270 |
Token | together |
Token ID | 1978 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
'd | +0.714 |
ave | +0.594 |
eded | +0.572 |
managed | +0.544 |
tted | +0.542 |
Neg logit contributions | |
Mom | -0.700 |
Ben | -0.682 |
Lily | -0.676 |
Uncle | -0.671 |
Mama | -0.651 |
Token | to |
Token ID | 284 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
'd | +0.512 |
ave | +0.425 |
would | +0.372 |
eded | +0.370 |
managed | +0.364 |
Neg logit contributions | |
Mom | -0.497 |
Lily | -0.484 |
Ben | -0.480 |
Anna | -0.461 |
Mama | -0.457 |
Token | ." |
Token ID | 526 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
'd | +0.381 |
ave | +0.291 |
forgot | +0.274 |
eded | +0.271 |
managed | +0.258 |
Neg logit contributions | |
Mom | -0.421 |
Ben | -0.419 |
Uncle | -0.415 |
Lily | -0.405 |
Anna | -0.400 |
Token | His |
Token ID | 2399 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
'd | +0.062 |
ave | +0.057 |
forgot | +0.053 |
managed | +0.051 |
eded | +0.050 |
Neg logit contributions | |
avail | -0.034 |
ados | -0.033 |
TV | -0.031 |
novels | -0.029 |
ries | -0.029 |
Token | friend |
Token ID | 1545 |
Feature activation | +7.89e+00 |
Pos logit contributions | |
Lily | +0.034 |
Ben | +0.033 |
Tom | +0.030 |
Anna | +0.028 |
ados | +0.027 |
Neg logit contributions | |
'd | -0.158 |
ave | -0.139 |
eded | -0.133 |
managed | -0.129 |
forgot | -0.128 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
Lily | +0.288 |
Mom | +0.286 |
Ben | +0.285 |
Tom | +0.276 |
Anna | +0.270 |
Neg logit contributions | |
'd | -0.265 |
ave | -0.218 |
eded | -0.199 |
managed | -0.185 |
tted | -0.180 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.48e+01 |
Pos logit contributions | |
'd | +0.182 |
eded | +0.089 |
've | +0.083 |
sy | +0.070 |
uch | +0.066 |
Neg logit contributions | |
Lily | -0.649 |
Ben | -0.634 |
Tom | -0.616 |
Sam | -0.609 |
Max | -0.605 |
Token | him |
Token ID | 683 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
'd | +1.242 |
would | +1.068 |
ave | +1.054 |
eded | +0.983 |
cared | +0.936 |
Neg logit contributions | |
Mom | -0.699 |
Uncle | -0.683 |
Glass | -0.683 |
Dad | -0.641 |
Mama | -0.640 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
Mom | +0.357 |
Ben | +0.355 |
Lily | +0.352 |
Tom | +0.338 |
Anna | +0.332 |
Neg logit contributions | |
'd | -0.511 |
ave | -0.440 |
eded | -0.405 |
managed | -0.385 |
sy | -0.373 |
Token | they |
Token ID | 484 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
'd | +0.249 |
ave | +0.218 |
eded | +0.205 |
managed | +0.196 |
tted | +0.192 |
Neg logit contributions | |
Lily | -0.117 |
Mom | -0.115 |
Ben | -0.115 |
Tom | -0.108 |
Anna | -0.105 |
Token | continued |
Token ID | 3767 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
Lily | +0.513 |
Mom | +0.509 |
Ben | +0.498 |
Tom | +0.481 |
Max | +0.477 |
Neg logit contributions | |
'd | -0.456 |
ave | -0.375 |
tted | -0.343 |
eded | -0.337 |
rated | -0.320 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
'd | +0.735 |
ave | +0.636 |
eded | +0.595 |
managed | +0.567 |
tted | +0.553 |
Neg logit contributions | |
Lily | -0.433 |
Mom | -0.430 |
Ben | -0.429 |
Tom | -0.408 |
Anna | -0.397 |
Token | ed |
Token ID | 276 |
Feature activation | -1.76e+01 |
Pos logit contributions | |
'd | +0.289 |
ave | +0.217 |
eded | +0.206 |
managed | +0.189 |
forgot | +0.186 |
Neg logit contributions | |
Lily | -0.373 |
Mom | -0.367 |
Ben | -0.367 |
Tom | -0.357 |
Max | -0.349 |
Token | happily |
Token ID | 18177 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
'd | +0.709 |
ave | +0.620 |
eded | +0.574 |
managed | +0.549 |
sy | +0.522 |
Neg logit contributions | |
Ben | -0.467 |
Lily | -0.454 |
Mom | -0.453 |
Tom | -0.442 |
Anna | -0.434 |
Token | . |
Token ID | 13 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
'd | +0.307 |
ave | +0.269 |
eded | +0.255 |
managed | +0.246 |
tted | +0.241 |
Neg logit contributions | |
Lily | -0.117 |
Mom | -0.116 |
Ben | -0.115 |
Tom | -0.108 |
Anna | -0.102 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
ados | +0.021 |
ries | +0.020 |
her | +0.018 |
avail | +0.017 |
Sara | +0.017 |
Neg logit contributions | |
'd | -0.035 |
ave | -0.031 |
'll | -0.027 |
managed | -0.027 |
tted | -0.027 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
Ben | +0.968 |
Lily | +0.948 |
Tom | +0.918 |
Max | +0.915 |
Mom | +0.914 |
Neg logit contributions | |
'd | -0.729 |
ave | -0.641 |
tted | -0.615 |
eded | -0.576 |
aved | -0.568 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.48e+01 |
Pos logit contributions | |
'd | +0.200 |
've | +0.101 |
eded | +0.091 |
'll | +0.084 |
sy | +0.073 |
Neg logit contributions | |
Lily | -0.623 |
Ben | -0.597 |
Tom | -0.584 |
Max | -0.582 |
Sam | -0.579 |
Token | him |
Token ID | 683 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
'd | +1.312 |
would | +1.136 |
ave | +1.055 |
wouldn | +1.045 |
eded | +0.982 |
Neg logit contributions | |
ados | -0.638 |
Sara | -0.595 |
Glass | -0.573 |
Mom | -0.547 |
Lily | -0.532 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
Mom | +0.376 |
Lily | +0.375 |
Ben | +0.371 |
Tom | +0.359 |
Anna | +0.355 |
Neg logit contributions | |
'd | -0.488 |
ave | -0.404 |
eded | -0.377 |
managed | -0.354 |
sy | -0.352 |
Token | they |
Token ID | 484 |
Feature activation | +1.38e+01 |
Pos logit contributions | |
'd | +0.236 |
ave | +0.205 |
eded | +0.192 |
managed | +0.183 |
tted | +0.180 |
Neg logit contributions | |
Lily | -0.130 |
Mom | -0.128 |
Ben | -0.128 |
Tom | -0.122 |
Anna | -0.118 |
Token | continued |
Token ID | 3767 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
Lily | +0.549 |
Mom | +0.546 |
Ben | +0.545 |
Tom | +0.524 |
Max | +0.519 |
Neg logit contributions | |
'd | -0.411 |
ave | -0.334 |
eded | -0.295 |
tted | -0.290 |
rated | -0.272 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
'd | +0.673 |
ave | +0.574 |
eded | +0.539 |
managed | +0.513 |
tted | +0.491 |
Neg logit contributions | |
Lily | -0.476 |
Ben | -0.473 |
Mom | -0.472 |
Tom | -0.452 |
Anna | -0.447 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
'd | +0.068 |
ave | +0.063 |
forgot | +0.058 |
managed | +0.057 |
'll | +0.054 |
Neg logit contributions | |
ados | -0.036 |
avail | -0.034 |
novels | -0.032 |
TV | -0.032 |
ries | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
'd | +0.046 |
ave | +0.039 |
eded | +0.036 |
tted | +0.036 |
sy | +0.033 |
Neg logit contributions | |
ados | -0.045 |
Ben | -0.037 |
TV | -0.036 |
Lily | -0.035 |
broccoli | -0.035 |
Token | L |
Token ID | 43 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
'd | +0.046 |
ave | +0.040 |
eded | +0.037 |
tted | +0.036 |
sy | +0.034 |
Neg logit contributions | |
Ben | -0.038 |
Lily | -0.037 |
Mom | -0.037 |
ados | -0.036 |
Tom | -0.035 |
Token | ily |
Token ID | 813 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
Mom | +0.095 |
Lily | +0.093 |
Ben | +0.093 |
Tom | +0.088 |
Max | +0.087 |
Neg logit contributions | |
'd | -0.161 |
ave | -0.141 |
eded | -0.130 |
managed | -0.124 |
tted | -0.121 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
Ben | +0.293 |
Lily | +0.291 |
Mom | +0.284 |
Tom | +0.279 |
Max | +0.276 |
Neg logit contributions | |
'd | -0.272 |
ave | -0.222 |
tted | -0.222 |
eded | -0.208 |
've | -0.204 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.47e+01 |
Pos logit contributions | |
'd | +0.207 |
've | +0.115 |
eded | +0.094 |
uch | +0.084 |
'll | +0.078 |
Neg logit contributions | |
Lily | -0.627 |
Ben | -0.606 |
Tom | -0.586 |
Sam | -0.577 |
Max | -0.576 |
Token | him |
Token ID | 683 |
Feature activation | +1.27e+01 |
Pos logit contributions | |
'd | +1.168 |
would | +1.060 |
wouldn | +1.019 |
didn | +0.992 |
ave | +0.987 |
Neg logit contributions | |
ados | -0.483 |
Glass | -0.470 |
Water | -0.425 |
yourselves | -0.405 |
eros | -0.400 |
Token | and |
Token ID | 290 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
Ben | +0.360 |
Mom | +0.360 |
Lily | +0.355 |
Tom | +0.347 |
Sara | +0.340 |
Neg logit contributions | |
'd | -0.494 |
ave | -0.426 |
eded | -0.389 |
sy | -0.368 |
managed | -0.367 |
Token | they |
Token ID | 484 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
'd | +0.226 |
ave | +0.196 |
eded | +0.183 |
managed | +0.174 |
tted | +0.170 |
Neg logit contributions | |
Lily | -0.134 |
Mom | -0.133 |
Ben | -0.132 |
Tom | -0.126 |
Anna | -0.123 |
Token | continued |
Token ID | 3767 |
Feature activation | -1.66e+01 |
Pos logit contributions | |
Lily | +0.555 |
Mom | +0.545 |
Ben | +0.542 |
Tom | +0.523 |
Max | +0.518 |
Neg logit contributions | |
'd | -0.419 |
ave | -0.330 |
tted | -0.302 |
eded | -0.300 |
rated | -0.280 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
'd | +0.695 |
ave | +0.597 |
eded | +0.558 |
managed | +0.531 |
tted | +0.515 |
Neg logit contributions | |
Lily | -0.461 |
Ben | -0.459 |
Mom | -0.458 |
Tom | -0.437 |
Anna | -0.428 |
Token | and |
Token ID | 290 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
'd | +0.080 |
ave | +0.069 |
eded | +0.065 |
managed | +0.062 |
tted | +0.060 |
Neg logit contributions | |
Lily | -0.050 |
Mom | -0.049 |
Ben | -0.049 |
Tom | -0.047 |
Anna | -0.046 |
Token | bravery |
Token ID | 37808 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
'd | +0.233 |
ave | +0.199 |
eded | +0.185 |
managed | +0.176 |
tted | +0.171 |
Neg logit contributions | |
Lily | -0.165 |
Mom | -0.164 |
Ben | -0.164 |
Tom | -0.157 |
Anna | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
'd | +0.355 |
ave | +0.312 |
eded | +0.293 |
managed | +0.281 |
tted | +0.274 |
Neg logit contributions | |
Lily | -0.164 |
Mom | -0.163 |
Ben | -0.162 |
Tom | -0.153 |
Anna | -0.148 |
Token | He |
Token ID | 679 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
Ben | +0.023 |
avail | +0.023 |
ados | +0.022 |
TV | +0.022 |
her | +0.021 |
Neg logit contributions | |
'd | -0.043 |
ave | -0.037 |
hadn | -0.034 |
'll | -0.033 |
managed | -0.033 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
Lily | +0.304 |
Ben | +0.302 |
Mom | +0.299 |
Tom | +0.294 |
Max | +0.291 |
Neg logit contributions | |
'd | -0.227 |
ave | -0.210 |
tted | -0.201 |
rated | -0.188 |
aved | -0.180 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.46e+01 |
Pos logit contributions | |
'd | +0.187 |
eded | +0.079 |
uch | +0.077 |
've | +0.069 |
'll | +0.067 |
Neg logit contributions | |
Lily | -0.605 |
Ben | -0.581 |
Tom | -0.571 |
Sam | -0.570 |
Max | -0.570 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.44e+01 |
Pos logit contributions | |
'd | +1.433 |
would | +1.231 |
ave | +1.205 |
eded | +1.187 |
managed | +1.181 |
Neg logit contributions | |
Ben | -0.484 |
Anna | -0.461 |
Uncle | -0.453 |
Mom | -0.438 |
Lee | -0.423 |
Token | my |
Token ID | 1820 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Mom | +0.928 |
Ben | +0.923 |
Lily | +0.921 |
Tom | +0.888 |
Anna | +0.881 |
Neg logit contributions | |
'd | -0.773 |
ave | -0.627 |
eded | -0.556 |
managed | -0.513 |
sy | -0.497 |
Token | and |
Token ID | 290 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
Lily | +0.168 |
Mom | +0.167 |
Ben | +0.166 |
Tom | +0.159 |
Anna | +0.157 |
Neg logit contributions | |
'd | -0.229 |
ave | -0.195 |
eded | -0.181 |
managed | -0.172 |
sy | -0.164 |
Token | even |
Token ID | 772 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
'd | +0.207 |
ave | +0.177 |
eded | +0.165 |
managed | +0.160 |
forgot | +0.153 |
Neg logit contributions | |
Mom | -0.139 |
Lily | -0.138 |
Ben | -0.138 |
Tom | -0.132 |
Anna | -0.129 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.41e+01 |
Pos logit contributions | |
'd | +0.259 |
ave | +0.199 |
tted | +0.191 |
eded | +0.184 |
sy | +0.175 |
Neg logit contributions | |
Lily | -0.410 |
Ben | -0.397 |
Mom | -0.382 |
Tom | -0.378 |
Sam | -0.377 |
Token | ." |
Token ID | 526 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
'd | +0.504 |
ave | +0.439 |
eded | +0.396 |
forgot | +0.381 |
managed | +0.378 |
Neg logit contributions | |
Ben | -0.316 |
Mom | -0.312 |
Lily | -0.304 |
Tom | -0.302 |
Uncle | -0.293 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.66e+01 |
Pos logit contributions | |
'd | +0.040 |
ave | +0.037 |
forgot | +0.032 |
managed | +0.031 |
hadn | +0.031 |
Neg logit contributions | |
avail | -0.031 |
ados | -0.030 |
TV | -0.029 |
ries | -0.027 |
novels | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
Lily | +1.061 |
Ben | +1.048 |
Mom | +1.031 |
Tom | +0.992 |
Anna | +0.991 |
Neg logit contributions | |
'd | -0.824 |
ave | -0.670 |
tted | -0.630 |
eded | -0.615 |
aved | -0.589 |
Token | Sue |
Token ID | 26089 |
Feature activation | +2.73e+01 |
Pos logit contributions | |
'd | +0.266 |
forgot | +0.244 |
managed | +0.229 |
would | +0.226 |
ave | +0.222 |
Neg logit contributions | |
ados | -0.068 |
ummy | -0.068 |
TV | -0.043 |
olk | -0.042 |
yourselves | -0.040 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
Mom | +0.987 |
Lily | +0.986 |
Ben | +0.969 |
Tom | +0.922 |
the | +0.894 |
Neg logit contributions | |
'd | -0.839 |
tted | -0.718 |
ave | -0.709 |
supposed | -0.663 |
wn | -0.656 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.44e+01 |
Pos logit contributions | |
'd | +0.204 |
've | +0.110 |
eded | +0.093 |
uch | +0.086 |
andering | +0.082 |
Neg logit contributions | |
Lily | -0.599 |
Ben | -0.563 |
Tom | -0.551 |
Max | -0.546 |
Sam | -0.534 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.85e+01 |
Pos logit contributions | |
'd | +1.428 |
would | +1.260 |
eded | +1.194 |
ave | +1.167 |
wouldn | +1.135 |
Neg logit contributions | |
ados | -0.597 |
Glass | -0.515 |
my | -0.491 |
Lily | -0.485 |
Anna | -0.460 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Mom | +0.763 |
Lily | +0.760 |
Ben | +0.758 |
Tom | +0.726 |
Anna | +0.711 |
Neg logit contributions | |
'd | -1.189 |
ave | -1.028 |
eded | -0.952 |
managed | -0.911 |
forgot | -0.875 |
Token | and |
Token ID | 290 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
'd | +0.059 |
ave | +0.050 |
eded | +0.047 |
managed | +0.044 |
tted | +0.043 |
Neg logit contributions | |
Lily | -0.043 |
Mom | -0.043 |
Ben | -0.043 |
Tom | -0.041 |
Anna | -0.040 |
Token | they |
Token ID | 484 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
'd | +0.240 |
ave | +0.211 |
eded | +0.200 |
managed | +0.193 |
forgot | +0.187 |
Neg logit contributions | |
Lily | -0.093 |
Mom | -0.093 |
Ben | -0.092 |
Tom | -0.086 |
Anna | -0.083 |
Token | all |
Token ID | 477 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Lily | +0.552 |
Mom | +0.546 |
Ben | +0.537 |
Tom | +0.511 |
Max | +0.510 |
Neg logit contributions | |
'd | -0.438 |
ave | -0.361 |
tted | -0.341 |
eded | -0.324 |
rated | -0.308 |
Token | back |
Token ID | 736 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Ben | +0.407 |
Lily | +0.403 |
Tom | +0.401 |
Sara | +0.389 |
Sam | +0.388 |
Neg logit contributions | |
'd | -0.414 |
ave | -0.341 |
eded | -0.319 |
sy | -0.311 |
managed | -0.292 |
Token | and |
Token ID | 290 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
Ben | +0.084 |
Lily | +0.081 |
Anna | +0.077 |
Tom | +0.077 |
ados | +0.077 |
Neg logit contributions | |
'd | -0.077 |
ave | -0.069 |
eded | -0.062 |
would | -0.058 |
sy | -0.056 |
Token | said |
Token ID | 531 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
'd | +0.163 |
ave | +0.132 |
eded | +0.119 |
managed | +0.109 |
tted | +0.109 |
Neg logit contributions | |
Lily | -0.201 |
Mom | -0.200 |
Ben | -0.199 |
Tom | -0.192 |
Anna | -0.189 |
Token | she |
Token ID | 673 |
Feature activation | +1.65e+01 |
Pos logit contributions | |
'd | +0.239 |
ave | +0.203 |
eded | +0.188 |
managed | +0.184 |
would | +0.181 |
Neg logit contributions | |
Lily | -0.147 |
Ben | -0.145 |
Mom | -0.143 |
Anna | -0.141 |
Sam | -0.139 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Mom | +0.635 |
Lily | +0.619 |
mom | +0.584 |
Max | +0.583 |
Ben | +0.579 |
Neg logit contributions | |
'd | -0.426 |
ited | -0.403 |
tted | -0.380 |
contain | -0.374 |
ave | -0.374 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.43e+01 |
Pos logit contributions | |
'd | +0.191 |
eded | +0.108 |
've | +0.095 |
sy | +0.093 |
managed | +0.089 |
Neg logit contributions | |
Lily | -0.568 |
Ben | -0.551 |
Tom | -0.532 |
Max | -0.516 |
Sam | -0.513 |
Token | him |
Token ID | 683 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
'd | +1.166 |
would | +0.992 |
wouldn | +0.950 |
eded | +0.870 |
'll | +0.863 |
Neg logit contributions | |
ados | -0.720 |
Glass | -0.717 |
Anna | -0.690 |
Uncle | -0.680 |
Farmer | -0.665 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Mom | +0.351 |
Ben | +0.350 |
Lily | +0.341 |
Tom | +0.333 |
Uncle | +0.331 |
Neg logit contributions | |
'd | -0.521 |
ave | -0.447 |
eded | -0.411 |
sy | -0.387 |
managed | -0.384 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
avail | +0.051 |
ados | +0.050 |
TV | +0.043 |
broccoli | +0.043 |
groceries | +0.043 |
Neg logit contributions | |
'd | -0.060 |
ave | -0.047 |
'll | -0.046 |
hadn | -0.045 |
would | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
'd | +0.008 |
ave | +0.006 |
eded | +0.006 |
tted | +0.006 |
sy | +0.005 |
Neg logit contributions | |
ados | -0.007 |
Ben | -0.006 |
Lily | -0.006 |
Anna | -0.006 |
avail | -0.006 |
Token | They |
Token ID | 2990 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
'd | +0.006 |
ave | +0.005 |
eded | +0.005 |
tted | +0.005 |
managed | +0.005 |
Neg logit contributions | |
Ben | -0.005 |
Mom | -0.005 |
Lily | -0.005 |
Anna | -0.005 |
Sara | -0.005 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
'd | +0.416 |
ave | +0.340 |
eded | +0.311 |
managed | +0.304 |
succeeded | +0.286 |
Neg logit contributions | |
Lily | -0.469 |
Mom | -0.465 |
Ben | -0.465 |
Tom | -0.448 |
Anna | -0.443 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
'd | +0.499 |
ave | +0.435 |
eded | +0.391 |
managed | +0.377 |
forgot | +0.375 |
Neg logit contributions | |
Ben | -0.304 |
Mom | -0.302 |
Lily | -0.302 |
Tom | -0.288 |
Anna | -0.286 |
Token | but |
Token ID | 475 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
'd | +0.060 |
ave | +0.047 |
managed | +0.046 |
forgot | +0.046 |
eded | +0.042 |
Neg logit contributions | |
Mom | -0.048 |
ados | -0.047 |
Ben | -0.046 |
Lily | -0.045 |
Anna | -0.044 |
Token | he |
Token ID | 339 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
'd | +0.070 |
ave | +0.058 |
forgot | +0.058 |
managed | +0.058 |
eded | +0.055 |
Neg logit contributions | |
ados | -0.025 |
TV | -0.022 |
Mom | -0.021 |
Ben | -0.020 |
Lily | -0.020 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
Mom | +0.598 |
Lily | +0.589 |
Ben | +0.580 |
Tom | +0.560 |
Anna | +0.549 |
Neg logit contributions | |
'd | -0.436 |
aved | -0.381 |
ave | -0.379 |
rated | -0.359 |
tted | -0.356 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.42e+01 |
Pos logit contributions | |
'd | +0.193 |
've | +0.101 |
eded | +0.092 |
'll | +0.083 |
sy | +0.082 |
Neg logit contributions | |
Lily | -0.580 |
Ben | -0.560 |
Tom | -0.551 |
Sam | -0.534 |
Max | -0.530 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.61e+01 |
Pos logit contributions | |
'd | +1.304 |
would | +1.153 |
ave | +1.092 |
cared | +1.064 |
tasted | +1.049 |
Neg logit contributions | |
ados | -0.507 |
Glass | -0.428 |
Farmer | -0.374 |
Uncle | -0.369 |
sofa | -0.366 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Mom | +0.693 |
Ben | +0.682 |
Lily | +0.677 |
Tom | +0.656 |
Anna | +0.643 |
Neg logit contributions | |
'd | -1.035 |
ave | -0.892 |
eded | -0.805 |
managed | -0.774 |
would | -0.773 |
Token | He |
Token ID | 679 |
Feature activation | +8.96e+00 |
Pos logit contributions | |
avail | +0.051 |
ries | +0.050 |
ados | +0.050 |
TV | +0.045 |
Uncle | +0.043 |
Neg logit contributions | |
'd | -0.064 |
ave | -0.059 |
tted | -0.052 |
'll | -0.051 |
managed | -0.049 |
Token | said |
Token ID | 531 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
Lily | +0.337 |
Ben | +0.326 |
Mom | +0.317 |
Tom | +0.310 |
Anna | +0.304 |
Neg logit contributions | |
'd | -0.292 |
rated | -0.242 |
ave | -0.242 |
tted | -0.242 |
aved | -0.237 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
'd | +0.204 |
ave | +0.173 |
managed | +0.158 |
would | +0.153 |
eded | +0.151 |
Neg logit contributions | |
Mom | -0.140 |
Ben | -0.139 |
Uncle | -0.139 |
Lily | -0.135 |
Tom | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
'd | +0.011 |
ave | +0.010 |
tted | +0.009 |
'll | +0.008 |
eded | +0.008 |
Neg logit contributions | |
ados | -0.008 |
Lily | -0.008 |
Ben | -0.007 |
Mom | -0.007 |
TV | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
'd | +0.015 |
ave | +0.013 |
eded | +0.012 |
tted | +0.012 |
sy | +0.011 |
Neg logit contributions | |
ados | -0.015 |
TV | -0.013 |
ries | -0.013 |
Mom | -0.013 |
avail | -0.013 |
Token | Tim |
Token ID | 14967 |
Feature activation | +1.75e+01 |
Pos logit contributions | |
'd | +0.015 |
ave | +0.013 |
eded | +0.012 |
tted | +0.012 |
sy | +0.011 |
Neg logit contributions | |
Mom | -0.013 |
Ben | -0.013 |
ados | -0.013 |
Lily | -0.012 |
Tom | -0.012 |
Token | my |
Token ID | 1820 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
Lily | +0.525 |
Ben | +0.524 |
Tom | +0.508 |
Mom | +0.505 |
Max | +0.495 |
Neg logit contributions | |
'd | -0.676 |
tted | -0.562 |
ave | -0.560 |
eded | -0.532 |
've | -0.530 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
Lily | +0.226 |
Ben | +0.223 |
Mom | +0.223 |
Tom | +0.215 |
Max | +0.213 |
Neg logit contributions | |
'd | -0.196 |
ave | -0.157 |
tted | -0.154 |
aved | -0.153 |
've | -0.148 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.40e+01 |
Pos logit contributions | |
'd | +0.213 |
've | +0.127 |
'll | +0.100 |
eded | +0.098 |
uch | +0.094 |
Neg logit contributions | |
Lily | -0.554 |
Ben | -0.531 |
Tom | -0.518 |
Sam | -0.509 |
Max | -0.509 |
Token | Betsy |
Token ID | 45775 |
Feature activation | +2.58e+01 |
Pos logit contributions | |
'd | +1.221 |
would | +1.064 |
wouldn | +0.992 |
eded | +0.991 |
managed | +0.991 |
Neg logit contributions | |
ados | -0.513 |
Sunny | -0.495 |
Anna | -0.492 |
Glass | -0.474 |
novels | -0.464 |
Token | and |
Token ID | 290 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Lily | +0.782 |
Mom | +0.779 |
Ben | +0.775 |
Tom | +0.753 |
Anna | +0.741 |
Neg logit contributions | |
'd | -0.968 |
ave | -0.814 |
eded | -0.746 |
managed | -0.709 |
sy | -0.705 |
Token | they |
Token ID | 484 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
'd | +0.203 |
ave | +0.177 |
eded | +0.166 |
managed | +0.158 |
tted | +0.155 |
Neg logit contributions | |
Lily | -0.112 |
Mom | -0.111 |
Ben | -0.111 |
Tom | -0.105 |
Anna | -0.102 |
Token | became |
Token ID | 2627 |
Feature activation | -1.54e+01 |
Pos logit contributions | |
Lily | +0.568 |
Mom | +0.566 |
Ben | +0.563 |
Tom | +0.545 |
Max | +0.537 |
Neg logit contributions | |
'd | -0.441 |
ave | -0.358 |
eded | -0.312 |
tted | -0.311 |
rated | -0.290 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
'd | +0.558 |
managed | +0.457 |
ave | +0.455 |
eded | +0.452 |
succeeded | +0.436 |
Neg logit contributions | |
Ben | -0.448 |
Mom | -0.442 |
Tom | -0.435 |
Lily | -0.434 |
Anna | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
'd | +0.011 |
ave | +0.010 |
tted | +0.009 |
'll | +0.009 |
eded | +0.009 |
Neg logit contributions | |
ados | -0.007 |
Lily | -0.007 |
Uncle | -0.007 |
Ben | -0.007 |
Mom | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
'd | +0.018 |
ave | +0.017 |
tted | +0.016 |
eded | +0.015 |
managed | +0.014 |
Neg logit contributions | |
ados | -0.012 |
Mom | -0.012 |
Ben | -0.011 |
Lily | -0.011 |
Uncle | -0.011 |
Token | His |
Token ID | 6653 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
'd | +0.017 |
ave | +0.015 |
eded | +0.014 |
tted | +0.013 |
managed | +0.013 |
Neg logit contributions | |
Mom | -0.012 |
Ben | -0.012 |
Lily | -0.012 |
Tom | -0.012 |
Sam | -0.011 |
Token | friend |
Token ID | 1545 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
Lily | +0.061 |
Ben | +0.060 |
Mom | +0.059 |
Tom | +0.057 |
Anna | +0.056 |
Neg logit contributions | |
'd | -0.108 |
ave | -0.093 |
eded | -0.088 |
managed | -0.083 |
tted | -0.081 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
Lily | +0.367 |
Ben | +0.362 |
Mom | +0.362 |
Tom | +0.353 |
Max | +0.345 |
Neg logit contributions | |
'd | -0.251 |
ave | -0.200 |
eded | -0.179 |
tted | -0.164 |
managed | -0.159 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.40e+01 |
Pos logit contributions | |
'd | +0.179 |
've | +0.098 |
eded | +0.092 |
capt | +0.089 |
uch | +0.081 |
Neg logit contributions | |
Lily | -0.575 |
Ben | -0.555 |
Tom | -0.532 |
Sam | -0.528 |
Max | -0.528 |
Token | him |
Token ID | 683 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
'd | +1.040 |
would | +0.871 |
ave | +0.776 |
eded | +0.776 |
wouldn | +0.740 |
Neg logit contributions | |
Glass | -0.806 |
Water | -0.770 |
Mom | -0.761 |
Uncle | -0.746 |
Nurse | -0.742 |
Token | and |
Token ID | 290 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Mom | +0.398 |
Ben | +0.397 |
Lily | +0.394 |
Tom | +0.380 |
Anna | +0.372 |
Neg logit contributions | |
'd | -0.515 |
ave | -0.437 |
eded | -0.403 |
managed | -0.381 |
sy | -0.371 |
Token | said |
Token ID | 531 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
'd | +0.182 |
ave | +0.156 |
eded | +0.144 |
tted | +0.135 |
managed | +0.134 |
Neg logit contributions | |
Lily | -0.136 |
Ben | -0.134 |
Mom | -0.134 |
Tom | -0.128 |
Max | -0.125 |
Token | that |
Token ID | 326 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
'd | +0.213 |
ave | +0.177 |
managed | +0.165 |
eded | +0.163 |
would | +0.162 |
Neg logit contributions | |
Mom | -0.130 |
Ben | -0.126 |
Uncle | -0.123 |
Lily | -0.123 |
Anna | -0.123 |
Token | it |
Token ID | 340 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
Mom | +0.038 |
Ben | +0.037 |
Lily | +0.037 |
Anna | +0.036 |
Uncle | +0.035 |
Neg logit contributions | |
'd | -0.114 |
ave | -0.094 |
would | -0.093 |
managed | -0.091 |
eded | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Lily | +0.257 |
Mom | +0.254 |
Ben | +0.253 |
Tom | +0.240 |
Anna | +0.234 |
Neg logit contributions | |
'd | -0.461 |
ave | -0.401 |
eded | -0.375 |
managed | -0.358 |
tted | -0.350 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.60e+01 |
Pos logit contributions | |
ados | +0.050 |
ries | +0.047 |
avail | +0.043 |
TV | +0.042 |
olk | +0.040 |
Neg logit contributions | |
'd | -0.052 |
ave | -0.046 |
hadn | -0.041 |
forgot | -0.040 |
missed | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
Lily | +0.979 |
Ben | +0.966 |
Tom | +0.922 |
Mom | +0.908 |
Max | +0.904 |
Neg logit contributions | |
'd | -0.796 |
aved | -0.687 |
tted | -0.681 |
ave | -0.665 |
wn | -0.659 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.91e+01 |
Pos logit contributions | |
'd | +0.225 |
forgot | +0.218 |
missed | +0.203 |
managed | +0.200 |
wouldn | +0.198 |
Neg logit contributions | |
ummy | -0.054 |
ados | -0.046 |
Water | -0.044 |
TV | -0.041 |
lights | -0.032 |
Token | forg |
Token ID | 5784 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
Ben | +1.054 |
Lily | +1.047 |
Tom | +1.028 |
Mom | +1.006 |
the | +0.987 |
Neg logit contributions | |
'd | -0.834 |
wn | -0.740 |
rig | -0.737 |
rated | -0.733 |
tted | -0.719 |
Token | ave |
Token ID | 1015 |
Feature activation | -3.40e+01 |
Pos logit contributions | |
'd | +0.188 |
've | +0.093 |
sy | +0.086 |
eded | +0.085 |
'll | +0.076 |
Neg logit contributions | |
Lily | -0.568 |
Ben | -0.552 |
Tom | -0.541 |
Max | -0.526 |
Sam | -0.522 |
Token | him |
Token ID | 683 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
'd | +1.214 |
would | +1.102 |
ave | +1.019 |
cared | +0.979 |
eded | +0.965 |
Neg logit contributions | |
ados | -0.667 |
Glass | -0.616 |
Water | -0.539 |
Farmer | -0.536 |
Uncle | -0.511 |
Token | and |
Token ID | 290 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Mom | +0.393 |
Lily | +0.391 |
Ben | +0.390 |
Tom | +0.371 |
Anna | +0.365 |
Neg logit contributions | |
'd | -0.529 |
ave | -0.451 |
eded | -0.418 |
managed | -0.394 |
tted | -0.378 |
Token | they |
Token ID | 484 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
'd | +0.151 |
ave | +0.126 |
eded | +0.114 |
tted | +0.108 |
ited | +0.104 |
Neg logit contributions | |
Lily | -0.168 |
Mom | -0.166 |
Ben | -0.166 |
Tom | -0.161 |
Max | -0.157 |
Token | all |
Token ID | 477 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Lily | +0.564 |
Mom | +0.560 |
Ben | +0.558 |
Tom | +0.538 |
Max | +0.523 |
Neg logit contributions | |
'd | -0.431 |
ave | -0.351 |
tted | -0.336 |
rated | -0.315 |
eded | -0.310 |
Token | went |
Token ID | 1816 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
'd | +0.038 |
ave | +0.029 |
eded | +0.026 |
tted | +0.025 |
managed | +0.024 |
Neg logit contributions | |
Lily | -0.059 |
Mom | -0.057 |
Ben | -0.057 |
Tom | -0.056 |
Anna | -0.054 |
Token | bed |
Token ID | 3996 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
Lily | +0.348 |
Ben | +0.323 |
Tom | +0.318 |
Mom | +0.314 |
Sara | +0.314 |
Neg logit contributions | |
'd | -0.784 |
ave | -0.667 |
eded | -0.625 |
sy | -0.603 |
managed | -0.603 |
Token | . |
Token ID | 13 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Lily | +0.367 |
Mom | +0.363 |
Ben | +0.362 |
Tom | +0.343 |
Max | +0.341 |
Neg logit contributions | |
'd | -0.638 |
ave | -0.557 |
eded | -0.508 |
managed | -0.494 |
tted | -0.490 |
Token | He |
Token ID | 679 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
ados | +0.128 |
ries | +0.119 |
ummy | +0.103 |
avail | +0.102 |
strawberries | +0.099 |
Neg logit contributions | |
'd | -0.137 |
ave | -0.127 |
tted | -0.113 |
managed | -0.108 |
missed | -0.107 |
Token | hopes |
Token ID | 7176 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
Ben | +0.374 |
Lily | +0.361 |
Mom | +0.353 |
Anna | +0.352 |
Tom | +0.348 |
Neg logit contributions | |
'd | -0.445 |
ave | -0.392 |
tted | -0.359 |
eded | -0.351 |
sy | -0.347 |
Token | his |
Token ID | 465 |
Feature activation | +1.70e+01 |
Pos logit contributions | |
'd | +0.706 |
ave | +0.597 |
managed | +0.588 |
would | +0.579 |
eded | +0.571 |
Neg logit contributions | |
ados | -0.232 |
Ben | -0.189 |
Lily | -0.187 |
Mom | -0.181 |
Max | -0.178 |
Token | dad |
Token ID | 9955 |
Feature activation | +3.00e+01 |
Pos logit contributions | |
Mom | +0.160 |
Ben | +0.152 |
Lily | +0.152 |
Tom | +0.129 |
Anna | +0.115 |
Neg logit contributions | |
'd | -1.043 |
ave | -0.943 |
eded | -0.903 |
managed | -0.873 |
tted | -0.867 |
Token | will |
Token ID | 481 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
Lily | +1.186 |
Tom | +1.181 |
Ben | +1.175 |
Anna | +1.146 |
the | +1.144 |
Neg logit contributions | |
'd | -0.730 |
ave | -0.699 |
tted | -0.580 |
sy | -0.571 |
succeeded | -0.530 |
Token | not |
Token ID | 407 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
'd | +0.678 |
ave | +0.591 |
eded | +0.519 |
managed | +0.487 |
ited | +0.478 |
Neg logit contributions | |
Lily | -0.700 |
Mom | -0.693 |
Ben | -0.687 |
Tom | -0.665 |
Anna | -0.646 |
Token | see |
Token ID | 766 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
'd | +0.263 |
ave | +0.240 |
eded | +0.218 |
sy | +0.204 |
ited | +0.203 |
Neg logit contributions | |
Lily | -0.243 |
Mom | -0.236 |
Ben | -0.235 |
Tom | -0.227 |
Anna | -0.217 |
Token | them |
Token ID | 606 |
Feature activation | +1.91e+01 |
Pos logit contributions | |
'd | +0.625 |
ave | +0.531 |
would | +0.512 |
managed | +0.504 |
eded | +0.498 |
Neg logit contributions | |
Uncle | -0.239 |
Farmer | -0.235 |
ados | -0.228 |
Daisy | -0.223 |
Mama | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
Lily | +0.445 |
Mom | +0.439 |
Ben | +0.439 |
Tom | +0.416 |
Anna | +0.402 |
Neg logit contributions | |
'd | -0.891 |
ave | -0.783 |
eded | -0.733 |
managed | -0.700 |
tted | -0.688 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
Mom | +0.608 |
Lily | +0.596 |
Ben | +0.580 |
Tom | +0.549 |
Anna | +0.510 |
Neg logit contributions | |
'd | -1.593 |
ave | -1.416 |
eded | -1.345 |
managed | -1.296 |
tted | -1.277 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.07e+01 |
Pos logit contributions | |
ados | +0.088 |
Lily | +0.067 |
Bella | +0.065 |
Ben | +0.064 |
Mom | +0.063 |
Neg logit contributions | |
'd | -0.255 |
ave | -0.226 |
would | -0.205 |
tted | -0.202 |
forgot | -0.198 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
Lily | +1.292 |
Mom | +1.281 |
Ben | +1.267 |
Tom | +1.244 |
Max | +1.229 |
Neg logit contributions | |
'd | -0.807 |
ave | -0.720 |
eded | -0.622 |
tted | -0.619 |
ited | -0.592 |
Token | to |
Token ID | 284 |
Feature activation | -7.35e+00 |
Pos logit contributions | |
'd | +0.714 |
would | +0.564 |
ave | +0.553 |
eded | +0.531 |
packed | +0.528 |
Neg logit contributions | |
Mom | -0.568 |
Ben | -0.565 |
Lily | -0.555 |
Anna | -0.542 |
Tom | -0.521 |
Token | drive |
Token ID | 3708 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
'd | +0.247 |
ave | +0.203 |
eded | +0.185 |
managed | +0.173 |
tted | +0.167 |
Neg logit contributions | |
Lily | -0.266 |
Mom | -0.264 |
Ben | -0.264 |
Tom | -0.255 |
Anna | -0.250 |
Token | his |
Token ID | 465 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
'd | +0.497 |
ave | +0.449 |
eded | +0.420 |
would | +0.404 |
sy | +0.396 |
Neg logit contributions | |
Ben | -0.222 |
Mom | -0.206 |
Lily | -0.204 |
Mama | -0.196 |
Sara | -0.194 |
Token | truck |
Token ID | 7779 |
Feature activation | +1.97e+01 |
Pos logit contributions | |
Ben | +0.468 |
Lily | +0.459 |
Mom | +0.444 |
Tom | +0.439 |
Anna | +0.430 |
Neg logit contributions | |
'd | -0.789 |
ave | -0.684 |
eded | -0.639 |
tted | -0.596 |
managed | -0.591 |
Token | around |
Token ID | 1088 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
Mom | +0.502 |
Lily | +0.494 |
Tom | +0.486 |
Ben | +0.483 |
Max | +0.477 |
Neg logit contributions | |
'd | -0.877 |
ave | -0.757 |
eded | -0.723 |
managed | -0.690 |
ited | -0.688 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
'd | +0.269 |
encountered | +0.226 |
would | +0.222 |
ave | +0.215 |
eded | +0.213 |
Neg logit contributions | |
ados | -0.100 |
Mom | -0.095 |
Sara | -0.091 |
Uncle | -0.090 |
Lily | -0.089 |
Token | ranch |
Token ID | 28752 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
Ben | +0.432 |
Lily | +0.426 |
Mom | +0.422 |
Tom | +0.409 |
Sam | +0.399 |
Neg logit contributions | |
'd | -0.652 |
ave | -0.549 |
eded | -0.522 |
tted | -0.492 |
sy | -0.489 |
Token | . |
Token ID | 13 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
Lily | +0.346 |
Mom | +0.343 |
Ben | +0.342 |
Tom | +0.323 |
Anna | +0.312 |
Neg logit contributions | |
'd | -0.722 |
ave | -0.632 |
eded | -0.594 |
managed | -0.569 |
tted | -0.555 |
Token | young |
Token ID | 1862 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ados | +0.044 |
Ben | +0.039 |
Mom | +0.039 |
Tom | +0.038 |
Leo | +0.037 |
Neg logit contributions | |
'd | -0.054 |
ave | -0.038 |
hadn | -0.038 |
sy | -0.038 |
had | -0.037 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.16e+01 |
Pos logit contributions | |
'd | +0.005 |
would | +0.004 |
packed | +0.004 |
bit | +0.003 |
ave | +0.003 |
Neg logit contributions | |
Sam | -0.004 |
Mom | -0.004 |
Tom | -0.004 |
Ben | -0.004 |
Mia | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
Ben | +0.779 |
Lily | +0.777 |
Mom | +0.776 |
Tom | +0.750 |
Anna | +0.742 |
Neg logit contributions | |
'd | -0.715 |
ave | -0.592 |
eded | -0.535 |
managed | -0.492 |
sy | -0.474 |
Token | Mike |
Token ID | 4995 |
Feature activation | +2.15e+01 |
Pos logit contributions | |
'd | +0.201 |
'll | +0.170 |
would | +0.168 |
sy | +0.147 |
wouldn | +0.141 |
Neg logit contributions | |
ados | -0.094 |
ment | -0.093 |
irens | -0.089 |
yourselves | -0.088 |
ries | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
Lily | +0.543 |
Mom | +0.534 |
Ben | +0.534 |
Tom | +0.509 |
Anna | +0.488 |
Neg logit contributions | |
'd | -0.953 |
ave | -0.834 |
eded | -0.780 |
managed | -0.750 |
tted | -0.741 |
Token | Mike |
Token ID | 4995 |
Feature activation | +2.15e+01 |
Pos logit contributions | |
Ben | +0.089 |
Lily | +0.088 |
Mom | +0.086 |
Max | +0.083 |
Anna | +0.081 |
Neg logit contributions | |
'd | -0.229 |
ave | -0.192 |
eded | -0.178 |
tted | -0.177 |
managed | -0.176 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.06e+01 |
Pos logit contributions | |
Lily | +0.900 |
Mom | +0.876 |
Ben | +0.866 |
Tom | +0.850 |
Tim | +0.830 |
Neg logit contributions | |
'd | -0.583 |
ave | -0.493 |
eded | -0.423 |
tted | -0.413 |
managed | -0.407 |
Token | to |
Token ID | 284 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
'd | +0.696 |
ave | +0.541 |
would | +0.519 |
eded | +0.506 |
managed | +0.483 |
Neg logit contributions | |
Lily | -0.639 |
Mom | -0.634 |
Ben | -0.634 |
Anna | -0.625 |
Tom | -0.613 |
Token | explore |
Token ID | 7301 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
'd | +0.254 |
ave | +0.197 |
eded | +0.185 |
managed | +0.170 |
tted | +0.163 |
Neg logit contributions | |
Lily | -0.295 |
Ben | -0.292 |
Mom | -0.292 |
Tom | -0.284 |
Anna | -0.282 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
'd | +0.389 |
would | +0.321 |
eded | +0.320 |
ave | +0.307 |
sy | +0.297 |
Neg logit contributions | |
Mom | -0.184 |
Ben | -0.183 |
Lily | -0.176 |
Tom | -0.175 |
Anna | -0.172 |
Token | big |
Token ID | 1263 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Lily | +0.413 |
Mom | +0.410 |
Ben | +0.410 |
Tom | +0.390 |
Anna | +0.380 |
Neg logit contributions | |
'd | -0.638 |
ave | -0.550 |
eded | -0.512 |
managed | -0.487 |
tted | -0.474 |
Token | was |
Token ID | 373 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
Ben | +1.188 |
Lily | +1.151 |
Tom | +1.125 |
Mom | +1.106 |
Anna | +1.076 |
Neg logit contributions | |
'd | -0.989 |
aved | -0.825 |
tted | -0.805 |
wn | -0.791 |
ave | -0.791 |
Token | sad |
Token ID | 6507 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
'd | +0.613 |
ave | +0.516 |
eded | +0.473 |
tted | +0.439 |
managed | +0.437 |
Neg logit contributions | |
Lily | -0.469 |
Mom | -0.459 |
Ben | -0.457 |
Tom | -0.443 |
Anna | -0.433 |
Token | . |
Token ID | 13 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
'd | +0.356 |
ave | +0.306 |
eded | +0.276 |
forgot | +0.268 |
managed | +0.266 |
Neg logit contributions | |
Mom | -0.249 |
Lily | -0.249 |
Ben | -0.247 |
Tom | -0.239 |
Anna | -0.237 |
Token | He |
Token ID | 679 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
ados | +0.090 |
ries | +0.088 |
Farmer | +0.088 |
Uncle | +0.084 |
Lily | +0.082 |
Neg logit contributions | |
'd | -0.172 |
ave | -0.171 |
forgot | -0.145 |
missed | -0.137 |
managed | -0.134 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
Lily | +0.463 |
Ben | +0.459 |
Mom | +0.441 |
Tom | +0.438 |
Max | +0.432 |
Neg logit contributions | |
'd | -0.322 |
tted | -0.308 |
ave | -0.267 |
aved | -0.264 |
sy | -0.260 |
Token | his |
Token ID | 465 |
Feature activation | +1.71e+01 |
Pos logit contributions | |
'd | +0.475 |
would | +0.425 |
ave | +0.416 |
eded | +0.386 |
managed | +0.378 |
Neg logit contributions | |
ados | -0.188 |
avail | -0.153 |
Cathy | -0.141 |
ummy | -0.138 |
yourselves | -0.133 |
Token | dad |
Token ID | 9955 |
Feature activation | +3.01e+01 |
Pos logit contributions | |
Ben | +0.144 |
Lily | +0.144 |
Mom | +0.125 |
Tom | +0.118 |
Max | +0.115 |
Neg logit contributions | |
'd | -1.034 |
ave | -0.930 |
eded | -0.887 |
managed | -0.859 |
forgot | -0.848 |
Token | to |
Token ID | 284 |
Feature activation | -8.25e+00 |
Pos logit contributions | |
Mom | +0.814 |
Lily | +0.813 |
Ben | +0.807 |
Tom | +0.768 |
Anna | +0.752 |
Neg logit contributions | |
'd | -1.273 |
ave | -1.084 |
eded | -1.004 |
managed | -0.962 |
forgot | -0.924 |
Token | let |
Token ID | 1309 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
'd | +0.288 |
ave | +0.243 |
eded | +0.219 |
managed | +0.205 |
tted | +0.201 |
Neg logit contributions | |
Mom | -0.294 |
Lily | -0.293 |
Ben | -0.292 |
Tom | -0.283 |
Anna | -0.274 |
Token | him |
Token ID | 683 |
Feature activation | +1.59e+01 |
Pos logit contributions | |
'd | +0.677 |
ave | +0.568 |
would | +0.565 |
managed | +0.537 |
eded | +0.535 |
Neg logit contributions | |
ados | -0.299 |
Mom | -0.275 |
Lily | -0.256 |
Uncle | -0.254 |
Anna | -0.252 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
Lily | +0.536 |
Mom | +0.535 |
Ben | +0.529 |
Tom | +0.517 |
Sam | +0.501 |
Neg logit contributions | |
'd | -0.597 |
ave | -0.494 |
eded | -0.455 |
managed | -0.426 |
sy | -0.414 |
Token | her |
Token ID | 607 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
'd | +0.527 |
eded | +0.431 |
ave | +0.431 |
managed | +0.424 |
would | +0.415 |
Neg logit contributions | |
ados | -0.128 |
Lily | -0.120 |
Ben | -0.111 |
Anna | -0.104 |
Max | -0.100 |
Token | heart |
Token ID | 2612 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Lily | +0.327 |
Ben | +0.316 |
Tom | +0.297 |
Anna | +0.288 |
Mom | +0.280 |
Neg logit contributions | |
'd | -0.909 |
ave | -0.783 |
eded | -0.752 |
managed | -0.720 |
forgot | -0.710 |
Token | . |
Token ID | 13 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
'd | +0.071 |
ave | +0.062 |
eded | +0.058 |
managed | +0.056 |
tted | +0.055 |
Neg logit contributions | |
Mom | -0.033 |
Lily | -0.033 |
Ben | -0.032 |
Tom | -0.030 |
Anna | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
ados | +0.068 |
Ben | +0.059 |
avail | +0.057 |
ries | +0.056 |
his | +0.056 |
Neg logit contributions | |
'd | -0.126 |
ave | -0.110 |
'll | -0.101 |
tted | -0.097 |
've | -0.095 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
Mom | +0.444 |
Ben | +0.425 |
Lily | +0.422 |
Anna | +0.406 |
Tom | +0.402 |
Neg logit contributions | |
'd | -0.336 |
ave | -0.324 |
tted | -0.323 |
rated | -0.287 |
aved | -0.281 |
Token | she |
Token ID | 673 |
Feature activation | +1.80e+01 |
Pos logit contributions | |
'd | +0.740 |
managed | +0.600 |
would | +0.592 |
ave | +0.586 |
eded | +0.585 |
Neg logit contributions | |
Ben | -0.272 |
Lily | -0.268 |
ados | -0.267 |
Mom | -0.254 |
Tom | -0.246 |
Token | would |
Token ID | 561 |
Feature activation | -2.09e+01 |
Pos logit contributions | |
Mom | +0.672 |
Lily | +0.669 |
Max | +0.651 |
Tom | +0.636 |
Ben | +0.630 |
Neg logit contributions | |
ave | -0.409 |
tted | -0.390 |
ited | -0.384 |
aved | -0.351 |
rig | -0.344 |
Token | have |
Token ID | 423 |
Feature activation | -1.62e+01 |
Pos logit contributions | |
'd | +0.609 |
ave | +0.583 |
eded | +0.477 |
tted | +0.450 |
ited | +0.444 |
Neg logit contributions | |
Mom | -0.828 |
Ben | -0.818 |
Lily | -0.816 |
Tom | -0.792 |
Max | -0.764 |
Token | lots |
Token ID | 6041 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
'd | +0.693 |
ave | +0.598 |
eded | +0.557 |
managed | +0.529 |
tted | +0.518 |
Neg logit contributions | |
Lily | -0.443 |
Mom | -0.439 |
Ben | -0.439 |
Tom | -0.418 |
Anna | -0.407 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
'd | +0.336 |
ave | +0.287 |
eded | +0.272 |
managed | +0.259 |
tted | +0.254 |
Neg logit contributions | |
Lily | -0.202 |
Mom | -0.196 |
Ben | -0.196 |
Tom | -0.188 |
Anna | -0.183 |
Token | memories |
Token ID | 9846 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
'd | +0.575 |
ave | +0.498 |
eded | +0.457 |
managed | +0.436 |
tted | +0.431 |
Neg logit contributions | |
Lily | -0.394 |
Mom | -0.390 |
Ben | -0.390 |
Tom | -0.373 |
Anna | -0.363 |
Token | cookies |
Token ID | 14746 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
Ben | +0.123 |
Lily | +0.121 |
Mom | +0.119 |
Tom | +0.117 |
Anna | +0.112 |
Neg logit contributions | |
'd | -0.248 |
ave | -0.210 |
eded | -0.200 |
managed | -0.191 |
sy | -0.187 |
Token | were |
Token ID | 547 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
Lily | +0.439 |
Mom | +0.433 |
Ben | +0.425 |
Tom | +0.420 |
Anna | +0.409 |
Neg logit contributions | |
'd | -0.318 |
ave | -0.284 |
eded | -0.251 |
ited | -0.217 |
tted | -0.217 |
Token | covered |
Token ID | 5017 |
Feature activation | -1.38e+01 |
Pos logit contributions | |
'd | +0.704 |
ave | +0.598 |
eded | +0.554 |
managed | +0.524 |
tted | +0.509 |
Neg logit contributions | |
Lily | -0.542 |
Mom | -0.538 |
Ben | -0.537 |
Tom | -0.515 |
Anna | -0.503 |
Token | in |
Token ID | 287 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
'd | +0.449 |
ave | +0.351 |
eded | +0.330 |
sy | +0.323 |
managed | +0.316 |
Neg logit contributions | |
Ben | -0.483 |
Mom | -0.475 |
Lily | -0.470 |
Tom | -0.454 |
Uncle | -0.453 |
Token | rainbow |
Token ID | 27223 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
'd | +0.495 |
eded | +0.395 |
ave | +0.393 |
managed | +0.383 |
sy | +0.369 |
Neg logit contributions | |
Ben | -0.290 |
Lily | -0.281 |
Mom | -0.275 |
Tom | -0.266 |
Max | -0.266 |
Token | sprink |
Token ID | 27562 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Ben | +0.086 |
Mom | +0.086 |
Lily | +0.086 |
Tom | +0.082 |
Anna | +0.079 |
Neg logit contributions | |
'd | -0.127 |
ave | -0.108 |
eded | -0.100 |
managed | -0.096 |
sy | -0.094 |
Token | les |
Token ID | 829 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
'd | +0.047 |
ave | +0.039 |
eded | +0.037 |
managed | +0.034 |
tted | +0.034 |
Neg logit contributions | |
Lily | -0.043 |
Ben | -0.043 |
Mom | -0.042 |
Tom | -0.041 |
Anna | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
Lily | +0.049 |
Mom | +0.049 |
Ben | +0.049 |
Tom | +0.046 |
Anna | +0.045 |
Neg logit contributions | |
'd | -0.082 |
ave | -0.071 |
eded | -0.066 |
managed | -0.063 |
tted | -0.062 |
Token | they |
Token ID | 484 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
'd | +0.171 |
ave | +0.145 |
eded | +0.136 |
managed | +0.132 |
forgot | +0.127 |
Neg logit contributions | |
Mom | -0.101 |
Ben | -0.101 |
Lily | -0.101 |
Tom | -0.095 |
Max | -0.093 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.44e+01 |
Pos logit contributions | |
Mom | +0.592 |
Lily | +0.592 |
Ben | +0.574 |
Tom | +0.561 |
Anna | +0.552 |
Neg logit contributions | |
'd | -0.403 |
ave | -0.358 |
eded | -0.314 |
tted | -0.313 |
ited | -0.274 |
Token | delicious |
Token ID | 12625 |
Feature activation | -7.82e+00 |
Pos logit contributions | |
'd | +0.555 |
ave | +0.479 |
eded | +0.442 |
tted | +0.416 |
managed | +0.408 |
Neg logit contributions | |
Lily | -0.469 |
Mom | -0.461 |
Ben | -0.448 |
Tom | -0.433 |
Anna | -0.427 |
Token | see |
Token ID | 766 |
Feature activation | -1.40e+01 |
Pos logit contributions | |
Ben | +0.306 |
Lily | +0.305 |
Tom | +0.300 |
Mom | +0.283 |
Max | +0.281 |
Neg logit contributions | |
'd | -0.313 |
ave | -0.282 |
rated | -0.247 |
be | -0.246 |
ited | -0.246 |
Token | that |
Token ID | 326 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
'd | +0.552 |
ave | +0.489 |
missed | +0.485 |
would | +0.473 |
forgot | +0.458 |
Neg logit contributions | |
ados | -0.260 |
avail | -0.217 |
ummy | -0.211 |
Farmer | -0.201 |
Uncle | -0.196 |
Token | they |
Token ID | 484 |
Feature activation | +1.72e+01 |
Pos logit contributions | |
ados | +0.083 |
ummy | +0.068 |
Uncle | +0.067 |
Farmer | +0.065 |
Mama | +0.064 |
Neg logit contributions | |
'd | -0.229 |
forgot | -0.192 |
would | -0.191 |
succeeded | -0.190 |
managed | -0.188 |
Token | have |
Token ID | 423 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
Lily | +0.491 |
Ben | +0.485 |
the | +0.475 |
Tom | +0.473 |
Max | +0.454 |
Neg logit contributions | |
'd | -0.647 |
ave | -0.646 |
sy | -0.562 |
rated | -0.546 |
ited | -0.540 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
'd | +0.569 |
ave | +0.481 |
eded | +0.445 |
managed | +0.416 |
tted | +0.410 |
Neg logit contributions | |
Lily | -0.456 |
Ben | -0.453 |
Mom | -0.450 |
Tom | -0.436 |
Anna | -0.421 |
Token | . |
Token ID | 13 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
Lily | +0.276 |
Ben | +0.275 |
Tom | +0.266 |
Mom | +0.264 |
Max | +0.247 |
Neg logit contributions | |
'd | -0.657 |
ave | -0.605 |
eded | -0.559 |
sy | -0.545 |
tted | -0.540 |
Token | They |
Token ID | 1119 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
ados | +0.142 |
ries | +0.132 |
avail | +0.127 |
her | +0.124 |
Uncle | +0.120 |
Neg logit contributions | |
'd | -0.156 |
ave | -0.140 |
tted | -0.125 |
'll | -0.118 |
missed | -0.115 |
Token | see |
Token ID | 766 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
Ben | +0.311 |
Lily | +0.305 |
Tom | +0.301 |
Mom | +0.300 |
Sam | +0.283 |
Neg logit contributions | |
'd | -0.319 |
ave | -0.306 |
sy | -0.254 |
eded | -0.253 |
tted | -0.246 |
Token | that |
Token ID | 326 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
'd | +0.606 |
ave | +0.526 |
would | +0.508 |
eded | +0.490 |
forgot | +0.485 |
Neg logit contributions | |
ados | -0.240 |
Mom | -0.201 |
Uncle | -0.201 |
avail | -0.199 |
Lily | -0.197 |
Token | they |
Token ID | 484 |
Feature activation | +1.73e+01 |
Pos logit contributions | |
ados | +0.083 |
Mom | +0.073 |
Uncle | +0.073 |
Mama | +0.071 |
Ben | +0.070 |
Neg logit contributions | |
'd | -0.240 |
would | -0.197 |
forgot | -0.196 |
ave | -0.195 |
managed | -0.194 |
Token | have |
Token ID | 423 |
Feature activation | -1.45e+01 |
Pos logit contributions | |
Lily | +0.519 |
Ben | +0.512 |
Tom | +0.502 |
the | +0.502 |
Max | +0.485 |
Neg logit contributions | |
ave | -0.634 |
'd | -0.629 |
sy | -0.544 |
rated | -0.522 |
ited | -0.516 |
Token | He |
Token ID | 679 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
ados | +0.007 |
avail | +0.007 |
ries | +0.006 |
things | +0.006 |
accidents | +0.006 |
Neg logit contributions | |
'd | -0.012 |
've | -0.010 |
'll | -0.010 |
ave | -0.010 |
tted | -0.009 |
Token | is |
Token ID | 318 |
Feature activation | -1.74e+01 |
Pos logit contributions | |
Ben | +0.284 |
Lily | +0.268 |
Tom | +0.265 |
Mom | +0.264 |
Anna | +0.261 |
Neg logit contributions | |
'd | -0.214 |
ave | -0.209 |
tted | -0.183 |
ited | -0.181 |
eded | -0.179 |
Token | very |
Token ID | 845 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
'd | +0.676 |
ave | +0.573 |
eded | +0.529 |
managed | +0.500 |
tted | +0.485 |
Neg logit contributions | |
Lily | -0.545 |
Mom | -0.541 |
Ben | -0.540 |
Tom | -0.518 |
Anna | -0.507 |
Token | proud |
Token ID | 6613 |
Feature activation | -1.69e+01 |
Pos logit contributions | |
'd | +0.539 |
ave | +0.464 |
eded | +0.428 |
managed | +0.396 |
tted | +0.384 |
Neg logit contributions | |
Lily | -0.425 |
Mom | -0.424 |
Ben | -0.419 |
Tom | -0.403 |
Anna | -0.394 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
'd | +0.581 |
ave | +0.483 |
eded | +0.415 |
managed | +0.404 |
would | +0.398 |
Neg logit contributions | |
Lily | -0.547 |
Ben | -0.546 |
Mom | -0.538 |
Tom | -0.524 |
Max | -0.523 |
Token | his |
Token ID | 465 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
'd | +0.729 |
eded | +0.592 |
managed | +0.591 |
would | +0.579 |
hadn | +0.570 |
Neg logit contributions | |
Uncle | -0.241 |
ados | -0.230 |
Mama | -0.220 |
Ben | -0.220 |
Mother | -0.212 |
Token | boat |
Token ID | 8848 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
Mom | +0.349 |
Lily | +0.344 |
Ben | +0.342 |
Tom | +0.323 |
Anna | +0.312 |
Neg logit contributions | |
'd | -0.610 |
ave | -0.537 |
eded | -0.496 |
managed | -0.477 |
tted | -0.465 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Lily | +0.340 |
Ben | +0.337 |
Mom | +0.336 |
Tom | +0.320 |
Max | +0.310 |
Neg logit contributions | |
'd | -0.702 |
ave | -0.622 |
eded | -0.581 |
managed | -0.556 |
tted | -0.547 |
Token | He |
Token ID | 679 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
ados | +0.037 |
ries | +0.033 |
avail | +0.032 |
her | +0.031 |
TV | +0.030 |
Neg logit contributions | |
'd | -0.045 |
ave | -0.036 |
've | -0.034 |
'll | -0.034 |
tted | -0.033 |
Token | shows |
Token ID | 2523 |
Feature activation | -2.07e+01 |
Pos logit contributions | |
Ben | +0.293 |
Lily | +0.277 |
Tom | +0.267 |
Mom | +0.267 |
Anna | +0.265 |
Neg logit contributions | |
'd | -0.269 |
ave | -0.258 |
tted | -0.233 |
rated | -0.228 |
eded | -0.228 |
Token | it |
Token ID | 340 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
'd | +0.936 |
ave | +0.859 |
would | +0.770 |
managed | +0.760 |
eded | +0.753 |
Neg logit contributions | |
Farmer | -0.306 |
ados | -0.295 |
Uncle | -0.278 |
Ben | -0.272 |
Mom | -0.262 |
Token | she |
Token ID | 673 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
'd | +0.315 |
done | +0.264 |
succeeded | +0.261 |
eded | +0.258 |
uch | +0.257 |
Neg logit contributions | |
Uncle | -0.182 |
Farmer | -0.174 |
Mom | -0.172 |
Lily | -0.171 |
Mama | -0.170 |
Token | is |
Token ID | 318 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
Ben | +0.651 |
Tom | +0.637 |
Lily | +0.636 |
Anna | +0.600 |
Mom | +0.585 |
Neg logit contributions | |
'd | -0.655 |
sy | -0.540 |
ave | -0.515 |
tted | -0.506 |
eded | -0.504 |
Token | done |
Token ID | 1760 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
'd | +0.596 |
ave | +0.512 |
eded | +0.480 |
managed | +0.462 |
forgot | +0.446 |
Neg logit contributions | |
Ben | -0.370 |
Mom | -0.369 |
Lily | -0.366 |
Tom | -0.347 |
Anna | -0.339 |
Token | ." |
Token ID | 526 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
'd | +0.804 |
ave | +0.692 |
eded | +0.640 |
managed | +0.612 |
succeeded | +0.587 |
Neg logit contributions | |
Ben | -0.521 |
Mom | -0.517 |
Lily | -0.511 |
Tom | -0.491 |
Sam | -0.483 |
Token |
|
Token ID | 198 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ados | +0.053 |
avail | +0.047 |
ries | +0.047 |
Farmer | +0.047 |
lava | +0.046 |
Neg logit contributions | |
'd | -0.035 |
'm | -0.033 |
ave | -0.031 |
'll | -0.027 |
could | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ados | +0.061 |
Uncle | +0.051 |
TV | +0.049 |
Farmer | +0.048 |
Lee | +0.048 |
Neg logit contributions | |
'd | -0.062 |
ave | -0.053 |
eded | -0.050 |
tted | -0.049 |
forgot | -0.046 |
Token | The |
Token ID | 464 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
Mom | +0.060 |
Ben | +0.059 |
Uncle | +0.058 |
ados | +0.057 |
Tom | +0.057 |
Neg logit contributions | |
'd | -0.067 |
ave | -0.057 |
eded | -0.052 |
managed | -0.050 |
forgot | -0.050 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.87e+01 |
Pos logit contributions | |
Lily | +0.104 |
Ben | +0.104 |
Mom | +0.102 |
Tom | +0.098 |
Anna | +0.095 |
Neg logit contributions | |
'd | -0.228 |
ave | -0.199 |
eded | -0.185 |
managed | -0.178 |
tted | -0.174 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
Ben | +0.597 |
Lily | +0.585 |
Mom | +0.573 |
Tom | +0.568 |
Anna | +0.563 |
Neg logit contributions | |
'd | -0.751 |
ave | -0.644 |
eded | -0.604 |
tted | -0.598 |
sy | -0.591 |
Token | at |
Token ID | 379 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
'd | +0.542 |
ave | +0.462 |
eded | +0.425 |
managed | +0.403 |
tted | +0.390 |
Neg logit contributions | |
Lily | -0.429 |
Mom | -0.427 |
Ben | -0.426 |
Tom | -0.408 |
Anna | -0.399 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.84e+01 |
Pos logit contributions | |
'd | +0.434 |
forgot | +0.393 |
would | +0.388 |
had | +0.387 |
missed | +0.385 |
Neg logit contributions | |
ados | -0.186 |
Farmer | -0.162 |
Uncle | -0.156 |
beef | -0.137 |
steak | -0.132 |
Token | ller |
Token ID | 6051 |
Feature activation | +1.88e+01 |
Pos logit contributions | |
'd | +0.240 |
ave | +0.207 |
eded | +0.192 |
managed | +0.181 |
forgot | +0.176 |
Neg logit contributions | |
Ben | -0.158 |
Mom | -0.156 |
Lily | -0.156 |
Tom | -0.147 |
Anna | -0.147 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
Lily | +0.686 |
Ben | +0.683 |
Mom | +0.674 |
Tom | +0.653 |
Anna | +0.639 |
Neg logit contributions | |
'd | -0.592 |
ave | -0.512 |
tted | -0.497 |
eded | -0.462 |
rated | -0.432 |
Token | up |
Token ID | 510 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
'd | +0.498 |
ave | +0.426 |
eded | +0.396 |
tted | +0.376 |
managed | +0.371 |
Neg logit contributions | |
Lily | -0.385 |
Mom | -0.378 |
Ben | -0.373 |
Tom | -0.359 |
Max | -0.350 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Lily | +0.012 |
Ben | +0.012 |
Mom | +0.012 |
Tom | +0.011 |
Anna | +0.011 |
Neg logit contributions | |
'd | -0.015 |
ave | -0.012 |
eded | -0.011 |
managed | -0.011 |
tted | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
'd | +0.055 |
ave | +0.044 |
eded | +0.039 |
managed | +0.036 |
tted | +0.034 |
Neg logit contributions | |
Lily | -0.072 |
Mom | -0.072 |
Ben | -0.072 |
Tom | -0.070 |
Anna | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
'd | +0.107 |
ave | +0.087 |
eded | +0.082 |
managed | +0.080 |
would | +0.080 |
Neg logit contributions | |
Ben | -0.068 |
Mom | -0.067 |
Lily | -0.066 |
Tom | -0.063 |
Sam | -0.062 |
Token | " |
Token ID | 366 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
Lily | +0.031 |
Ben | +0.031 |
Mom | +0.030 |
Tom | +0.029 |
Anna | +0.028 |
Neg logit contributions | |
'd | -0.081 |
ave | -0.066 |
eded | -0.064 |
managed | -0.063 |
would | -0.061 |
Token | Welcome |
Token ID | 14618 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
Lily | +0.149 |
Mom | +0.147 |
Ben | +0.147 |
Tom | +0.142 |
Anna | +0.139 |
Neg logit contributions | |
'd | -0.186 |
ave | -0.158 |
eded | -0.148 |
managed | -0.140 |
tted | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
'd | +0.235 |
ave | +0.191 |
eded | +0.177 |
'll | +0.169 |
managed | +0.168 |
Neg logit contributions | |
Mom | -0.175 |
Ben | -0.173 |
Lily | -0.172 |
Tom | -0.164 |
Max | -0.160 |
Token | little |
Token ID | 1310 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Ben | +0.036 |
Lily | +0.034 |
Mom | +0.034 |
Tom | +0.033 |
ados | +0.033 |
Neg logit contributions | |
'd | -0.078 |
ave | -0.061 |
eded | -0.060 |
would | -0.058 |
'll | -0.058 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +2.23e+01 |
Pos logit contributions | |
Mom | +0.107 |
Lily | +0.102 |
Ben | +0.101 |
Tom | +0.100 |
Anna | +0.099 |
Neg logit contributions | |
'd | -0.183 |
ave | -0.148 |
eded | -0.143 |
would | -0.137 |
'll | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
'd | +0.352 |
ave | +0.309 |
eded | +0.267 |
managed | +0.265 |
sy | +0.259 |
Neg logit contributions | |
Ben | -0.278 |
Mom | -0.272 |
Lily | -0.269 |
ados | -0.264 |
Tom | -0.264 |
Token | " |
Token ID | 366 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
Mom | +0.030 |
Ben | +0.030 |
Lily | +0.030 |
Tom | +0.027 |
Anna | +0.027 |
Neg logit contributions | |
'd | -0.083 |
ave | -0.070 |
eded | -0.067 |
managed | -0.066 |
sy | -0.063 |
Token | What |
Token ID | 2061 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Lily | +0.149 |
Mom | +0.148 |
Ben | +0.148 |
Tom | +0.141 |
Anna | +0.139 |
Neg logit contributions | |
'd | -0.191 |
ave | -0.163 |
eded | -0.148 |
managed | -0.142 |
tted | -0.137 |
Token | are |
Token ID | 389 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
Ben | +0.012 |
Mom | +0.012 |
Lily | +0.012 |
Tom | +0.012 |
Max | +0.011 |
Neg logit contributions | |
'd | -0.011 |
ave | -0.010 |
eded | -0.009 |
tted | -0.008 |
ited | -0.008 |
Token | you |
Token ID | 345 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
'd | +0.586 |
would | +0.455 |
eded | +0.447 |
ave | +0.446 |
managed | +0.435 |
Neg logit contributions | |
Lily | -0.360 |
Anna | -0.356 |
Ben | -0.348 |
Mom | -0.346 |
Sara | -0.336 |
Token | doing |
Token ID | 1804 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
Ben | +0.483 |
Mom | +0.479 |
Lily | +0.479 |
Tom | +0.462 |
Max | +0.450 |
Neg logit contributions | |
'd | -0.515 |
ave | -0.443 |
eded | -0.400 |
tted | -0.372 |
managed | -0.370 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
'd | +0.580 |
ave | +0.458 |
eded | +0.449 |
managed | +0.431 |
sy | +0.420 |
Neg logit contributions | |
Lily | -0.434 |
Ben | -0.421 |
Mom | -0.419 |
Sara | -0.411 |
Anna | -0.404 |
Token | |
Token ID | 220 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
ados | +0.043 |
Ben | +0.041 |
Mom | +0.039 |
Sara | +0.037 |
Lily | +0.036 |
Neg logit contributions | |
'd | -0.113 |
ave | -0.102 |
managed | -0.092 |
eded | -0.091 |
would | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ados | +0.088 |
Lily | +0.079 |
Ben | +0.076 |
Mom | +0.075 |
Anna | +0.074 |
Neg logit contributions | |
'd | -0.101 |
ave | -0.086 |
tted | -0.084 |
'll | -0.082 |
eded | -0.076 |
Token | The |
Token ID | 464 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
ados | +0.073 |
Ben | +0.070 |
Lily | +0.067 |
Mom | +0.067 |
Sara | +0.063 |
Neg logit contributions | |
'd | -0.110 |
ave | -0.099 |
eded | -0.090 |
tted | -0.089 |
managed | -0.086 |
Token | fire |
Token ID | 2046 |
Feature activation | +1.66e+01 |
Pos logit contributions | |
Ben | +0.087 |
Lily | +0.086 |
Mom | +0.082 |
Tom | +0.078 |
Anna | +0.075 |
Neg logit contributions | |
'd | -0.308 |
ave | -0.273 |
eded | -0.260 |
managed | -0.248 |
tted | -0.245 |
Token | What |
Token ID | 2061 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Lily | +0.131 |
Mom | +0.130 |
Ben | +0.130 |
Tom | +0.124 |
Anna | +0.122 |
Neg logit contributions | |
'd | -0.150 |
ave | -0.126 |
eded | -0.116 |
managed | -0.110 |
tted | -0.106 |
Token | 's |
Token ID | 338 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
'd | +0.017 |
ave | +0.015 |
eded | +0.014 |
ited | +0.013 |
tted | +0.013 |
Neg logit contributions | |
Ben | -0.019 |
Lily | -0.018 |
Tom | -0.018 |
Mom | -0.018 |
Sam | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
'd | +0.209 |
ave | +0.168 |
eded | +0.167 |
managed | +0.157 |
sy | +0.151 |
Neg logit contributions | |
Mom | -0.155 |
Lily | -0.154 |
Ben | -0.153 |
Tom | -0.147 |
Anna | -0.146 |
Token | ? |
Token ID | 30 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
Lily | +0.113 |
Mom | +0.111 |
Ben | +0.111 |
Tom | +0.108 |
Anna | +0.104 |
Neg logit contributions | |
'd | -0.176 |
ave | -0.147 |
eded | -0.138 |
managed | -0.132 |
sy | -0.130 |
Token | It |
Token ID | 632 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
Lily | +0.089 |
Mom | +0.088 |
Ben | +0.088 |
Tom | +0.085 |
Anna | +0.082 |
Neg logit contributions | |
'd | -0.147 |
ave | -0.125 |
eded | -0.113 |
managed | -0.110 |
tted | -0.110 |
Token | 's |
Token ID | 338 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
Lily | +0.279 |
Ben | +0.272 |
Max | +0.262 |
Mom | +0.260 |
Anna | +0.259 |
Neg logit contributions | |
'd | -0.272 |
ave | -0.256 |
tted | -0.235 |
eded | -0.227 |
ited | -0.218 |
Token | all |
Token ID | 477 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
'd | +0.226 |
ave | +0.187 |
eded | +0.179 |
managed | +0.172 |
sy | +0.166 |
Neg logit contributions | |
Lily | -0.148 |
Mom | -0.147 |
Ben | -0.147 |
Tom | -0.141 |
Anna | -0.137 |
Token | lump |
Token ID | 23844 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
Lily | +0.016 |
Ben | +0.015 |
Mom | +0.015 |
Tom | +0.015 |
Anna | +0.014 |
Neg logit contributions | |
'd | -0.026 |
ave | -0.023 |
eded | -0.021 |
tted | -0.020 |
managed | -0.020 |
Token | y |
Token ID | 88 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
Lily | +0.033 |
Mom | +0.032 |
Ben | +0.032 |
Tom | +0.031 |
Anna | +0.031 |
Neg logit contributions | |
'd | -0.027 |
ave | -0.022 |
eded | -0.020 |
managed | -0.019 |
tted | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Lily | +0.136 |
Mom | +0.136 |
Ben | +0.134 |
Tom | +0.126 |
Anna | +0.124 |
Neg logit contributions | |
'd | -0.223 |
ave | -0.194 |
eded | -0.181 |
managed | -0.171 |
tted | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Mom | +0.048 |
ados | +0.047 |
Uncle | +0.046 |
avail | +0.046 |
grandma | +0.045 |
Neg logit contributions | |
'd | -0.088 |
ave | -0.080 |
managed | -0.072 |
eded | -0.072 |
tted | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
Lily | +0.096 |
Mom | +0.096 |
Ben | +0.094 |
Tom | +0.089 |
Anna | +0.085 |
Neg logit contributions | |
'd | -0.241 |
ave | -0.214 |
eded | -0.204 |
managed | -0.196 |
tted | -0.192 |
Token | He |
Token ID | 679 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
ados | +0.122 |
Max | +0.104 |
Uncle | +0.101 |
ries | +0.101 |
grandma | +0.100 |
Neg logit contributions | |
'd | -0.181 |
ave | -0.152 |
would | -0.132 |
tted | -0.131 |
'll | -0.130 |
Token | plays |
Token ID | 5341 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
Ben | +0.437 |
Lily | +0.425 |
Mom | +0.407 |
Anna | +0.407 |
his | +0.406 |
Neg logit contributions | |
'd | -0.344 |
ave | -0.336 |
eded | -0.297 |
ited | -0.295 |
tted | -0.294 |
Token | with |
Token ID | 351 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
'd | +0.659 |
ave | +0.549 |
eded | +0.514 |
managed | +0.494 |
would | +0.494 |
Neg logit contributions | |
Mom | -0.409 |
Ben | -0.396 |
Uncle | -0.385 |
Lily | -0.381 |
Tom | -0.377 |
Token | them |
Token ID | 606 |
Feature activation | +1.93e+01 |
Pos logit contributions | |
'd | +0.477 |
would | +0.405 |
ave | +0.397 |
collected | +0.374 |
gathered | +0.368 |
Neg logit contributions | |
Uncle | -0.216 |
Farmer | -0.212 |
Mama | -0.189 |
Lee | -0.182 |
Mom | -0.181 |
Token | every |
Token ID | 790 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
Lily | +0.519 |
Mom | +0.517 |
Ben | +0.514 |
Tom | +0.491 |
Anna | +0.476 |
Neg logit contributions | |
'd | -0.827 |
ave | -0.706 |
eded | -0.658 |
managed | -0.627 |
tted | -0.605 |
Token | day |
Token ID | 1110 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
'd | +0.281 |
ave | +0.247 |
eded | +0.230 |
managed | +0.219 |
tted | +0.215 |
Neg logit contributions | |
Lily | -0.175 |
Mom | -0.174 |
Ben | -0.172 |
Tom | -0.163 |
Anna | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
Lily | +0.033 |
Mom | +0.031 |
Ben | +0.031 |
Sara | +0.030 |
Tom | +0.030 |
Neg logit contributions | |
'd | -0.044 |
ave | -0.037 |
eded | -0.032 |
managed | -0.032 |
would | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
ados | +0.125 |
Max | +0.104 |
ries | +0.104 |
Uncle | +0.101 |
grandma | +0.098 |
Neg logit contributions | |
'd | -0.188 |
ave | -0.155 |
would | -0.141 |
'll | -0.139 |
tted | -0.132 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.07e+01 |
Pos logit contributions | |
Ben | +0.430 |
Lily | +0.413 |
Anna | +0.401 |
Mom | +0.393 |
Tom | +0.390 |
Neg logit contributions | |
'd | -0.373 |
ave | -0.365 |
eded | -0.327 |
tted | -0.326 |
ited | -0.322 |
Token | them |
Token ID | 606 |
Feature activation | +1.94e+01 |
Pos logit contributions | |
'd | +0.940 |
ave | +0.813 |
managed | +0.745 |
eded | +0.741 |
succeeded | +0.740 |
Neg logit contributions | |
Mom | -0.422 |
Uncle | -0.392 |
Ben | -0.392 |
Lily | -0.377 |
Mama | -0.376 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Ben | +0.045 |
Lily | +0.045 |
Mom | +0.043 |
ados | +0.042 |
Tom | +0.042 |
Neg logit contributions | |
'd | -0.082 |
ave | -0.069 |
eded | -0.067 |
tted | -0.066 |
managed | -0.063 |
Token | The |
Token ID | 464 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
Lily | +0.052 |
Ben | +0.051 |
Mom | +0.051 |
Tom | +0.049 |
Anna | +0.047 |
Neg logit contributions | |
'd | -0.082 |
ave | -0.070 |
eded | -0.066 |
managed | -0.063 |
tted | -0.061 |
Token | end |
Token ID | 886 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
Lily | +0.122 |
Ben | +0.121 |
Mom | +0.117 |
Tom | +0.115 |
Anna | +0.112 |
Neg logit contributions | |
'd | -0.213 |
ave | -0.181 |
eded | -0.172 |
managed | -0.163 |
tted | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
'd | +0.232 |
ave | +0.199 |
eded | +0.189 |
managed | +0.179 |
tted | +0.175 |
Neg logit contributions | |
Lily | -0.118 |
Ben | -0.117 |
Mom | -0.115 |
Tom | -0.110 |
Anna | -0.106 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
ados | +0.110 |
Lily | +0.105 |
Ben | +0.103 |
Anna | +0.096 |
Tom | +0.096 |
Neg logit contributions | |
'd | -0.165 |
ave | -0.128 |
've | -0.126 |
'll | -0.125 |
eded | -0.125 |
Token | Once |
Token ID | 7454 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
Mom | +0.101 |
Lily | +0.097 |
Ben | +0.097 |
Uncle | +0.095 |
Tom | +0.092 |
Neg logit contributions | |
'd | -0.175 |
ave | -0.147 |
tted | -0.136 |
eded | -0.136 |
'll | -0.131 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
'd | +0.137 |
ave | +0.089 |
would | +0.088 |
forgot | +0.082 |
managed | +0.077 |
Neg logit contributions | |
ados | -0.212 |
Ben | -0.204 |
Lily | -0.201 |
Farmer | -0.200 |
Mom | -0.198 |
Token | a |
Token ID | 257 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
'd | +0.123 |
ave | +0.106 |
eded | +0.101 |
managed | +0.097 |
tted | +0.094 |
Neg logit contributions | |
Ben | -0.047 |
Mom | -0.047 |
Lily | -0.047 |
Tom | -0.043 |
Sam | -0.042 |
Token | time |
Token ID | 640 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
Lily | +0.127 |
Mom | +0.127 |
Ben | +0.125 |
Tom | +0.122 |
Anna | +0.120 |
Neg logit contributions | |
'd | -0.208 |
ave | -0.189 |
eded | -0.171 |
managed | -0.169 |
tted | -0.167 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
'd | +0.228 |
ave | +0.175 |
managed | +0.166 |
eded | +0.164 |
would | +0.163 |
Neg logit contributions | |
Ben | -0.165 |
Mom | -0.163 |
Lily | -0.161 |
ados | -0.158 |
Uncle | -0.158 |
Token | there |
Token ID | 612 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
Ben | +0.024 |
Mom | +0.024 |
Lily | +0.024 |
Tom | +0.023 |
Anna | +0.022 |
Neg logit contributions | |
'd | -0.048 |
ave | -0.041 |
eded | -0.038 |
managed | -0.037 |
tted | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
ados | +0.114 |
Lily | +0.098 |
Ben | +0.097 |
Uncle | +0.095 |
grandma | +0.094 |
Neg logit contributions | |
'd | -0.211 |
ave | -0.174 |
would | -0.158 |
tted | -0.157 |
've | -0.152 |
Token | was |
Token ID | 373 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
Lily | +0.519 |
Ben | +0.496 |
Mom | +0.493 |
Tom | +0.480 |
Max | +0.476 |
Neg logit contributions | |
'd | -0.324 |
ave | -0.289 |
eded | -0.255 |
ited | -0.249 |
tted | -0.248 |
Token | jumping |
Token ID | 14284 |
Feature activation | -7.72e+00 |
Pos logit contributions | |
'd | +0.549 |
ave | +0.470 |
eded | +0.435 |
managed | +0.409 |
tted | +0.399 |
Neg logit contributions | |
Lily | -0.434 |
Mom | -0.431 |
Ben | -0.429 |
Tom | -0.411 |
Anna | -0.402 |
Token | around |
Token ID | 1088 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
'd | +0.305 |
ave | +0.260 |
eded | +0.241 |
managed | +0.228 |
tted | +0.221 |
Neg logit contributions | |
Lily | -0.237 |
Ben | -0.235 |
Mom | -0.234 |
Tom | -0.224 |
Anna | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
'd | +0.227 |
ave | +0.174 |
eded | +0.167 |
would | +0.167 |
managed | +0.160 |
Neg logit contributions | |
Lily | -0.187 |
Mom | -0.185 |
Ben | -0.182 |
Sara | -0.178 |
Tom | -0.175 |
Token | waving |
Token ID | 25849 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
Lily | +0.063 |
Mom | +0.063 |
Ben | +0.063 |
Tom | +0.060 |
Anna | +0.059 |
Neg logit contributions | |
'd | -0.078 |
ave | -0.066 |
eded | -0.061 |
managed | -0.058 |
tted | -0.055 |
Token | his |
Token ID | 465 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
'd | +0.352 |
ave | +0.322 |
managed | +0.281 |
would | +0.279 |
eded | +0.277 |
Neg logit contributions | |
Lily | -0.129 |
Max | -0.119 |
Anna | -0.118 |
Mom | -0.118 |
Ben | -0.117 |
Token | hand |
Token ID | 1021 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Lily | +0.444 |
Mom | +0.439 |
Ben | +0.439 |
Tom | +0.417 |
Anna | +0.405 |
Neg logit contributions | |
'd | -0.805 |
ave | -0.700 |
eded | -0.654 |
managed | -0.624 |
tted | -0.610 |
Token | in |
Token ID | 287 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
Mom | +0.022 |
Lily | +0.022 |
Ben | +0.022 |
Tom | +0.021 |
Max | +0.020 |
Neg logit contributions | |
'd | -0.043 |
ave | -0.037 |
eded | -0.036 |
managed | -0.034 |
tted | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
'd | +0.414 |
ave | +0.336 |
eded | +0.335 |
managed | +0.333 |
ited | +0.332 |
Neg logit contributions | |
ados | -0.149 |
Lily | -0.133 |
Ben | -0.131 |
Mom | -0.124 |
Tom | -0.123 |
Token | air |
Token ID | 1633 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Lily | +0.341 |
Ben | +0.339 |
Mom | +0.329 |
Tom | +0.327 |
Anna | +0.312 |
Neg logit contributions | |
'd | -0.708 |
ave | -0.626 |
eded | -0.571 |
tted | -0.550 |
sy | -0.545 |
Token | my |
Token ID | 1820 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
Lily | +0.677 |
Ben | +0.663 |
Mom | +0.655 |
Tom | +0.642 |
Max | +0.615 |
Neg logit contributions | |
'd | -0.966 |
ave | -0.838 |
eded | -0.779 |
tted | -0.760 |
managed | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
Lily | +0.090 |
Mom | +0.089 |
Ben | +0.087 |
Tom | +0.084 |
Max | +0.081 |
Neg logit contributions | |
'd | -0.250 |
ave | -0.223 |
eded | -0.209 |
tted | -0.208 |
managed | -0.202 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.39e+01 |
Pos logit contributions | |
Ben | +0.012 |
Anna | +0.012 |
ados | +0.012 |
her | +0.012 |
avail | +0.011 |
Neg logit contributions | |
'd | -0.035 |
'll | -0.028 |
've | -0.027 |
hadn | -0.027 |
ave | -0.027 |
Token | my |
Token ID | 1820 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
Lily | +0.655 |
Mom | +0.629 |
Ben | +0.619 |
Tom | +0.613 |
Max | +0.602 |
Neg logit contributions | |
'd | -0.985 |
ave | -0.874 |
tted | -0.848 |
eded | -0.817 |
managed | -0.777 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.43e+01 |
Pos logit contributions | |
Mom | +0.215 |
Lily | +0.215 |
Ben | +0.209 |
Max | +0.209 |
Tom | +0.207 |
Neg logit contributions | |
'd | -0.141 |
ave | -0.120 |
tted | -0.117 |
eded | -0.109 |
ited | -0.104 |
Token | going |
Token ID | 1016 |
Feature activation | -2.27e+01 |
Pos logit contributions | |
'd | +0.744 |
would | +0.569 |
ave | +0.556 |
eded | +0.523 |
managed | +0.515 |
Neg logit contributions | |
Ben | -0.774 |
Lily | -0.757 |
Anna | -0.756 |
Mom | -0.742 |
Sara | -0.726 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
'd | +0.900 |
ave | +0.762 |
eded | +0.708 |
managed | +0.671 |
tted | +0.653 |
Neg logit contributions | |
Lily | -0.678 |
Ben | -0.676 |
Mom | -0.674 |
Tom | -0.644 |
Anna | -0.633 |
Token | his |
Token ID | 465 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
'd | +0.508 |
've | +0.412 |
would | +0.404 |
succeeded | +0.404 |
managed | +0.400 |
Neg logit contributions | |
ados | -0.194 |
Mom | -0.182 |
Lily | -0.175 |
Ben | -0.168 |
Anna | -0.163 |
Token | classroom |
Token ID | 15806 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
Lily | +0.384 |
Ben | +0.381 |
Tom | +0.362 |
Anna | +0.354 |
Sam | +0.350 |
Neg logit contributions | |
'd | -0.557 |
ave | -0.447 |
eded | -0.442 |
would | -0.414 |
succeeded | -0.409 |
Token | because |
Token ID | 780 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Lily | +0.148 |
Mom | +0.144 |
Ben | +0.141 |
Tom | +0.139 |
Anna | +0.132 |
Neg logit contributions | |
'd | -0.295 |
ave | -0.258 |
eded | -0.250 |
managed | -0.235 |
tted | -0.231 |
Token | he |
Token ID | 339 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
'd | +0.081 |
would | +0.068 |
managed | +0.063 |
ave | +0.062 |
packed | +0.061 |
Neg logit contributions | |
ados | -0.034 |
Ben | -0.034 |
Anna | -0.031 |
Sara | -0.030 |
Leo | -0.030 |
Token | your |
Token ID | 534 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
'd | +1.045 |
ave | +0.874 |
eded | +0.854 |
managed | +0.847 |
forgot | +0.837 |
Neg logit contributions | |
ados | -0.421 |
Mom | -0.367 |
Lily | -0.346 |
Ben | -0.332 |
Uncle | -0.307 |
Token | new |
Token ID | 649 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Lily | +0.312 |
Ben | +0.304 |
Mom | +0.288 |
Tom | +0.285 |
Max | +0.279 |
Neg logit contributions | |
'd | -0.560 |
ave | -0.473 |
eded | -0.444 |
'll | -0.421 |
managed | -0.416 |
Token | alarm |
Token ID | 10436 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Lily | +0.078 |
Ben | +0.078 |
Mom | +0.074 |
Tom | +0.073 |
Max | +0.071 |
Neg logit contributions | |
'd | -0.124 |
ave | -0.105 |
eded | -0.097 |
managed | -0.092 |
'll | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Lily | +0.072 |
Mom | +0.071 |
Ben | +0.071 |
Tom | +0.067 |
Anna | +0.065 |
Neg logit contributions | |
'd | -0.149 |
ave | -0.131 |
eded | -0.123 |
managed | -0.118 |
tted | -0.115 |
Token | I |
Token ID | 314 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
ados | +0.068 |
Lily | +0.063 |
Ben | +0.062 |
Mom | +0.062 |
Uncle | +0.059 |
Neg logit contributions | |
'd | -0.120 |
ave | -0.102 |
've | -0.090 |
'll | -0.088 |
tted | -0.088 |
Token | can |
Token ID | 460 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
Lily | +0.207 |
Ben | +0.199 |
Tom | +0.193 |
Anna | +0.192 |
Sara | +0.186 |
Neg logit contributions | |
'd | -0.173 |
ave | -0.157 |
rated | -0.150 |
eded | -0.139 |
ounded | -0.134 |
Token | make |
Token ID | 787 |
Feature activation | -2.06e+01 |
Pos logit contributions | |
'd | +0.674 |
ave | +0.566 |
eded | +0.513 |
managed | +0.483 |
tted | +0.464 |
Neg logit contributions | |
Mom | -0.710 |
Lily | -0.710 |
Ben | -0.704 |
Tom | -0.681 |
Anna | -0.667 |
Token | any |
Token ID | 597 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
'd | +0.782 |
be | +0.665 |
ave | +0.658 |
'll | +0.650 |
eded | +0.629 |
Neg logit contributions | |
ados | -0.391 |
Lily | -0.363 |
Farmer | -0.352 |
Uncle | -0.350 |
Lee | -0.343 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Ben | +0.057 |
Lily | +0.056 |
Mom | +0.055 |
Tom | +0.053 |
Anna | +0.051 |
Neg logit contributions | |
'd | -0.098 |
ave | -0.084 |
eded | -0.079 |
managed | -0.075 |
tted | -0.073 |
Token | you |
Token ID | 345 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
'd | +0.108 |
ave | +0.092 |
eded | +0.085 |
managed | +0.081 |
forgot | +0.079 |
Neg logit contributions | |
Mom | -0.071 |
Lily | -0.071 |
Ben | -0.070 |
Tom | -0.067 |
Max | -0.065 |
Token | want |
Token ID | 765 |
Feature activation | -2.74e+01 |
Pos logit contributions | |
Lily | +0.405 |
Ben | +0.404 |
Tom | +0.391 |
Mom | +0.391 |
Max | +0.377 |
Neg logit contributions | |
'd | -0.419 |
ave | -0.378 |
eded | -0.340 |
tted | -0.327 |
managed | -0.321 |
Token | it |
Token ID | 340 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Lily | +0.181 |
Mom | +0.178 |
Ben | +0.178 |
Tom | +0.167 |
Sam | +0.166 |
Neg logit contributions | |
'd | -0.255 |
ave | -0.238 |
eded | -0.210 |
tted | -0.194 |
ited | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Lily | +0.367 |
Ben | +0.357 |
Mom | +0.355 |
Tom | +0.338 |
Anna | +0.330 |
Neg logit contributions | |
'd | -0.408 |
ave | -0.364 |
eded | -0.340 |
tted | -0.317 |
sy | -0.309 |
Token | They |
Token ID | 1119 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
'd | +0.048 |
ave | +0.040 |
'll | +0.037 |
've | +0.037 |
hadn | +0.036 |
Neg logit contributions | |
ados | -0.023 |
Ben | -0.021 |
Uncle | -0.021 |
Mom | -0.020 |
Lily | -0.020 |
Token | realized |
Token ID | 6939 |
Feature activation | -1.72e+01 |
Pos logit contributions | |
Ben | +0.141 |
Lily | +0.138 |
Mom | +0.138 |
Tom | +0.136 |
Anna | +0.130 |
Neg logit contributions | |
'd | -0.098 |
ave | -0.087 |
eded | -0.075 |
tted | -0.074 |
sy | -0.070 |
Token | they |
Token ID | 484 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
'd | +0.673 |
would | +0.547 |
managed | +0.546 |
wouldn | +0.543 |
eded | +0.534 |
Neg logit contributions | |
ados | -0.359 |
Ben | -0.353 |
Mom | -0.344 |
Anna | -0.338 |
Lily | -0.325 |
Token | were |
Token ID | 547 |
Feature activation | -2.01e+01 |
Pos logit contributions | |
Lily | +0.439 |
Mom | +0.430 |
the | +0.414 |
Ben | +0.411 |
Tom | +0.411 |
Neg logit contributions | |
ave | -0.312 |
'd | -0.303 |
rig | -0.301 |
sc | -0.299 |
tted | -0.294 |
Token | being |
Token ID | 852 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
'd | +0.745 |
ave | +0.622 |
eded | +0.577 |
managed | +0.550 |
succeeded | +0.524 |
Neg logit contributions | |
Lily | -0.647 |
Mom | -0.646 |
Ben | -0.643 |
Tom | -0.618 |
Anna | -0.606 |
Token | silly |
Token ID | 14397 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
'd | +0.357 |
ave | +0.297 |
eded | +0.273 |
managed | +0.255 |
tted | +0.247 |
Neg logit contributions | |
Lily | -0.341 |
Mom | -0.338 |
Ben | -0.338 |
Tom | -0.325 |
Anna | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
'd | +0.310 |
ave | +0.269 |
eded | +0.253 |
managed | +0.240 |
tted | +0.236 |
Neg logit contributions | |
Lily | -0.184 |
Ben | -0.182 |
Mom | -0.182 |
Tom | -0.173 |
Anna | -0.168 |
Token | They |
Token ID | 1119 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
ados | +0.018 |
avail | +0.017 |
ries | +0.016 |
honey | +0.015 |
TV | +0.015 |
Neg logit contributions | |
'd | -0.020 |
ave | -0.017 |
hadn | -0.015 |
'll | -0.015 |
tted | -0.015 |
Token | did |
Token ID | 750 |
Feature activation | -2.48e+01 |
Pos logit contributions | |
Lily | +0.202 |
Mom | +0.201 |
Ben | +0.201 |
Tom | +0.195 |
Sam | +0.188 |
Neg logit contributions | |
'd | -0.134 |
ave | -0.117 |
tted | -0.107 |
eded | -0.102 |
rated | -0.100 |
Token | play |
Token ID | 711 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
'd | +0.332 |
ave | +0.269 |
eded | +0.245 |
managed | +0.229 |
tted | +0.219 |
Neg logit contributions | |
Lily | -0.389 |
Ben | -0.387 |
Mom | -0.386 |
Tom | -0.373 |
Anna | -0.368 |
Token | so |
Token ID | 523 |
Feature activation | -8.56e+00 |
Pos logit contributions | |
'd | +0.476 |
ave | +0.396 |
eded | +0.375 |
managed | +0.361 |
tted | +0.357 |
Neg logit contributions | |
Ben | -0.380 |
Mom | -0.379 |
Lily | -0.362 |
Tom | -0.357 |
Uncle | -0.356 |
Token | badly |
Token ID | 11234 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
'd | +0.223 |
ave | +0.172 |
eded | +0.165 |
managed | +0.153 |
forgot | +0.142 |
Neg logit contributions | |
Ben | -0.343 |
Lily | -0.331 |
Mom | -0.327 |
Anna | -0.325 |
ados | -0.320 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
'd | +0.059 |
eded | +0.047 |
ave | +0.047 |
managed | +0.045 |
would | +0.044 |
Neg logit contributions | |
Mom | -0.042 |
Ben | -0.040 |
Lily | -0.039 |
Anna | -0.038 |
Tom | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
Ben | +0.063 |
Lily | +0.062 |
Anna | +0.062 |
Sara | +0.060 |
Tom | +0.057 |
Neg logit contributions | |
'd | -0.106 |
ave | -0.092 |
eded | -0.083 |
managed | -0.082 |
'll | -0.081 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.21e+01 |
Pos logit contributions | |
Lily | +0.386 |
Mom | +0.370 |
Ben | +0.370 |
Tom | +0.359 |
Anna | +0.355 |
Neg logit contributions | |
'd | -0.274 |
ave | -0.231 |
tted | -0.226 |
've | -0.204 |
eded | -0.203 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
'd | +0.738 |
ave | +0.577 |
managed | +0.545 |
eded | +0.540 |
would | +0.539 |
Neg logit contributions | |
Ben | -0.688 |
Lily | -0.671 |
ados | -0.667 |
Anna | -0.655 |
Mom | -0.654 |
Token | throw |
Token ID | 3714 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
'd | +0.319 |
ave | +0.256 |
eded | +0.234 |
managed | +0.219 |
tted | +0.210 |
Neg logit contributions | |
Lily | -0.380 |
Ben | -0.380 |
Mom | -0.378 |
Tom | -0.365 |
Anna | -0.361 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
'd | +0.677 |
ave | +0.610 |
eded | +0.587 |
managed | +0.581 |
ched | +0.559 |
Neg logit contributions | |
Uncle | -0.234 |
Ben | -0.234 |
Mom | -0.229 |
Anna | -0.220 |
Mother | -0.215 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Mom | +0.286 |
Lily | +0.283 |
Ben | +0.276 |
Tom | +0.261 |
Max | +0.252 |
Neg logit contributions | |
'd | -0.620 |
ave | -0.550 |
eded | -0.518 |
managed | -0.496 |
tted | -0.478 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Mom | +0.298 |
Ben | +0.297 |
Lily | +0.296 |
Tom | +0.282 |
Anna | +0.280 |
Neg logit contributions | |
'd | -0.395 |
ave | -0.336 |
eded | -0.308 |
managed | -0.300 |
tted | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ados | +0.055 |
Lily | +0.051 |
Ben | +0.050 |
Mom | +0.048 |
Max | +0.048 |
Neg logit contributions | |
'd | -0.086 |
ave | -0.072 |
eded | -0.069 |
tted | -0.065 |
would | -0.064 |
Token | M |
Token ID | 44 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Lily | +0.058 |
Ben | +0.057 |
Mom | +0.057 |
Tom | +0.054 |
Anna | +0.053 |
Neg logit contributions | |
'd | -0.091 |
ave | -0.079 |
eded | -0.073 |
managed | -0.070 |
tted | -0.068 |
Token | ia |
Token ID | 544 |
Feature activation | +2.07e+01 |
Pos logit contributions | |
Lily | +0.089 |
Mom | +0.087 |
Ben | +0.086 |
Max | +0.084 |
Tom | +0.081 |
Neg logit contributions | |
'd | -0.146 |
ave | -0.127 |
eded | -0.117 |
managed | -0.111 |
tted | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Ben | +0.461 |
Tom | +0.437 |
Lily | +0.435 |
Anna | +0.421 |
Mom | +0.402 |
Neg logit contributions | |
'd | -0.953 |
tted | -0.847 |
ave | -0.846 |
aved | -0.830 |
rated | -0.825 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.16e+01 |
Pos logit contributions | |
'd | +0.107 |
forgot | +0.094 |
ave | +0.094 |
ate | +0.090 |
missed | +0.090 |
Neg logit contributions | |
Kim | -0.027 |
Farmer | -0.022 |
Sue | -0.022 |
Liz | -0.022 |
Mom | -0.021 |
Token | made |
Token ID | 925 |
Feature activation | -2.37e+01 |
Pos logit contributions | |
Ben | +1.231 |
Tom | +1.187 |
Lily | +1.149 |
Mom | +1.128 |
the | +1.120 |
Neg logit contributions | |
'd | -0.862 |
ave | -0.771 |
tted | -0.761 |
wn | -0.758 |
rated | -0.743 |
Token | a |
Token ID | 257 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
'd | +0.859 |
ave | +0.770 |
eded | +0.730 |
succeeded | +0.712 |
managed | +0.687 |
Neg logit contributions | |
ados | -0.495 |
Mom | -0.486 |
Farmer | -0.486 |
Uncle | -0.485 |
Dad | -0.466 |
Token | new |
Token ID | 649 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Lily | +0.128 |
Ben | +0.127 |
Mom | +0.127 |
Tom | +0.121 |
Anna | +0.117 |
Neg logit contributions | |
'd | -0.222 |
ave | -0.190 |
eded | -0.179 |
managed | -0.170 |
tted | -0.166 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
Ben | +0.133 |
Lily | +0.133 |
Mom | +0.131 |
Tom | +0.127 |
Anna | +0.124 |
Neg logit contributions | |
'd | -0.181 |
ave | -0.153 |
eded | -0.143 |
managed | -0.134 |
sy | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
Mom | +0.284 |
Lily | +0.276 |
Ben | +0.272 |
Tom | +0.258 |
Max | +0.256 |
Neg logit contributions | |
'd | -0.484 |
ave | -0.417 |
eded | -0.383 |
managed | -0.369 |
forgot | -0.358 |
Token | They |
Token ID | 1119 |
Feature activation | +8.58e+00 |
Pos logit contributions | |
ados | +0.114 |
ries | +0.105 |
Farmer | +0.104 |
Uncle | +0.099 |
Daddy | +0.097 |
Neg logit contributions | |
'd | -0.152 |
ave | -0.134 |
tted | -0.120 |
missed | -0.113 |
'll | -0.113 |