Token | man |
Token ID | 582 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
This | +0.369 |
Novel | +0.367 |
These | +0.364 |
Today | +0.327 |
ses | +0.326 |
Neg logit contributions | |
nowhere | -0.505 |
aming | -0.464 |
pr | -0.458 |
we | -0.443 |
amed | -0.437 |
Token | , |
Token ID | 11 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
This | +0.010 |
These | +0.010 |
Novel | +0.009 |
Today | +0.009 |
acts | +0.009 |
Neg logit contributions | |
nowhere | -0.011 |
aming | -0.010 |
pr | -0.010 |
amed | -0.009 |
we | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
This | +0.397 |
Novel | +0.374 |
These | +0.374 |
They | +0.356 |
The | +0.347 |
Neg logit contributions | |
nowhere | -0.391 |
pr | -0.370 |
aming | -0.363 |
amed | -0.354 |
dd | -0.347 |
Token | he |
Token ID | 339 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
nowhere | +0.112 |
aming | +0.105 |
pr | +0.103 |
we | +0.100 |
amed | +0.098 |
Neg logit contributions | |
This | -0.109 |
These | -0.104 |
Novel | -0.100 |
The | -0.093 |
Today | -0.093 |
Token | was |
Token ID | 373 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
nowhere | +0.038 |
aming | +0.037 |
pr | +0.037 |
we | +0.036 |
amed | +0.035 |
Neg logit contributions | |
This | -0.038 |
Novel | -0.036 |
acts | -0.036 |
These | -0.035 |
leave | -0.035 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.178 |
pr | +0.169 |
ths | +0.165 |
THE | +0.164 |
P | +0.162 |
Neg logit contributions | |
This | -0.182 |
The | -0.168 |
try | -0.163 |
ses | -0.161 |
leave | -0.160 |
Token | in |
Token ID | 287 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
nowhere | +1.444 |
aming | +1.426 |
amed | +1.380 |
dd | +1.364 |
ths | +1.337 |
Neg logit contributions | |
This | -0.980 |
Novel | -0.898 |
These | -0.859 |
acts | -0.832 |
hy | -0.819 |
Token | sight |
Token ID | 6504 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
nowhere | +0.489 |
aming | +0.420 |
pr | +0.418 |
amed | +0.399 |
we | +0.397 |
Neg logit contributions | |
These | -0.469 |
This | -0.467 |
Novel | -0.456 |
ses | -0.430 |
Today | -0.421 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nowhere | +0.263 |
aming | +0.226 |
pr | +0.223 |
amed | +0.218 |
we | +0.212 |
Neg logit contributions | |
These | -0.188 |
This | -0.187 |
Novel | -0.181 |
Today | -0.166 |
ses | -0.164 |
Token | She |
Token ID | 1375 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
ses | +0.031 |
Novel | +0.029 |
These | +0.029 |
acts | +0.027 |
This | +0.025 |
Neg logit contributions | |
nowhere | -0.089 |
aming | -0.076 |
pr | -0.076 |
amed | -0.076 |
we | -0.073 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
acts | +0.515 |
This | +0.499 |
Novel | +0.499 |
act | +0.485 |
leave | +0.482 |
Neg logit contributions | |
pr | -0.577 |
aming | -0.570 |
nowhere | -0.552 |
THE | -0.543 |
we | -0.536 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
This | +0.022 |
These | +0.021 |
Novel | +0.021 |
They | +0.021 |
thank | +0.021 |
Neg logit contributions | |
nowhere | -0.031 |
pr | -0.029 |
aming | -0.028 |
ths | -0.028 |
we | -0.027 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
nowhere | +0.100 |
we | +0.096 |
pr | +0.090 |
aming | +0.087 |
ths | +0.084 |
Neg logit contributions | |
This | -0.134 |
These | -0.128 |
Novel | -0.125 |
thank | -0.121 |
Today | -0.121 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nowhere | +1.128 |
aming | +1.025 |
pr | +1.011 |
amed | +0.992 |
we | +0.978 |
Neg logit contributions | |
This | -0.677 |
These | -0.651 |
Novel | -0.628 |
Today | -0.588 |
ses | -0.583 |
Token | he |
Token ID | 339 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
pr | +0.105 |
nowhere | +0.103 |
aming | +0.099 |
we | +0.094 |
amed | +0.093 |
Neg logit contributions | |
This | -0.112 |
These | -0.109 |
Novel | -0.104 |
They | -0.102 |
thank | -0.101 |
Token | was |
Token ID | 373 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
pr | +0.043 |
aming | +0.040 |
nowhere | +0.038 |
amed | +0.038 |
we | +0.038 |
Neg logit contributions | |
ses | -0.034 |
acts | -0.034 |
Novel | -0.033 |
thank | -0.033 |
This | -0.033 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.193 |
pr | +0.178 |
P | +0.174 |
dd | +0.169 |
ths | +0.167 |
Neg logit contributions | |
This | -0.177 |
leave | -0.173 |
The | -0.170 |
thank | -0.167 |
Novel | -0.166 |
Token | to |
Token ID | 284 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
nowhere | +1.468 |
aming | +1.437 |
amed | +1.433 |
ths | +1.403 |
dd | +1.383 |
Neg logit contributions | |
This | -0.892 |
Novel | -0.810 |
These | -0.770 |
offer | -0.741 |
try | -0.737 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.025 |
ses | +0.023 |
This | +0.023 |
Novel | +0.021 |
Show | +0.020 |
Neg logit contributions | |
nowhere | -0.045 |
aming | -0.037 |
pr | -0.037 |
soon | -0.036 |
THE | -0.035 |
Token | found |
Token ID | 1043 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
This | +0.393 |
Novel | +0.385 |
The | +0.375 |
attitude | +0.365 |
leave | +0.359 |
Neg logit contributions | |
pr | -0.323 |
we | -0.316 |
ths | -0.315 |
nowhere | -0.301 |
THE | -0.279 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nowhere | +0.339 |
pr | +0.307 |
aming | +0.306 |
amed | +0.298 |
ths | +0.285 |
Neg logit contributions | |
This | -0.198 |
These | -0.190 |
Novel | -0.190 |
acts | -0.171 |
They | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
These | +0.053 |
Novel | +0.052 |
This | +0.051 |
ses | +0.050 |
acts | +0.048 |
Neg logit contributions | |
nowhere | -0.069 |
aming | -0.057 |
pr | -0.056 |
amed | -0.055 |
we | -0.054 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
nowhere | +0.077 |
aming | +0.068 |
pr | +0.067 |
we | +0.066 |
amed | +0.061 |
Neg logit contributions | |
This | -0.158 |
These | -0.154 |
Novel | -0.154 |
Today | -0.146 |
ses | -0.146 |
Token | , |
Token ID | 11 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
nowhere | +1.161 |
aming | +1.100 |
amed | +1.071 |
pr | +1.066 |
ths | +1.031 |
Neg logit contributions | |
This | -0.619 |
Novel | -0.594 |
These | -0.589 |
Today | -0.543 |
thank | -0.516 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
This | +0.222 |
Novel | +0.212 |
But | +0.208 |
These | +0.194 |
The | +0.188 |
Neg logit contributions | |
pr | -0.555 |
aming | -0.537 |
amed | -0.534 |
P | -0.527 |
dd | -0.524 |
Token | it |
Token ID | 340 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
aming | +0.107 |
pr | +0.106 |
nowhere | +0.106 |
amed | +0.101 |
we | +0.099 |
Neg logit contributions | |
This | -0.108 |
These | -0.104 |
Novel | -0.104 |
ses | -0.096 |
But | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
pr | +0.395 |
aming | +0.393 |
nowhere | +0.388 |
amed | +0.366 |
dd | +0.357 |
Neg logit contributions | |
Novel | -0.389 |
This | -0.384 |
ses | -0.368 |
opens | -0.358 |
These | -0.355 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.122 |
pr | +0.114 |
aming | +0.110 |
dd | +0.109 |
amed | +0.107 |
Neg logit contributions | |
Novel | -0.248 |
This | -0.245 |
ses | -0.243 |
One | -0.231 |
Today | -0.231 |
Token | to |
Token ID | 284 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
aming | +1.393 |
nowhere | +1.372 |
amed | +1.362 |
dd | +1.346 |
pr | +1.327 |
Neg logit contributions | |
This | -0.989 |
Novel | -0.971 |
These | -0.862 |
ses | -0.857 |
The | -0.834 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.026 |
ses | +0.025 |
This | +0.023 |
Show | +0.022 |
Today | +0.021 |
Neg logit contributions | |
nowhere | -0.043 |
aming | -0.037 |
pr | -0.036 |
soon | -0.035 |
amed | -0.034 |
Token | found |
Token ID | 1043 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
Novel | +0.401 |
This | +0.392 |
The | +0.363 |
ses | +0.356 |
attitude | +0.355 |
Neg logit contributions | |
pr | -0.335 |
ths | -0.332 |
nowhere | -0.316 |
we | -0.316 |
dd | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nowhere | +0.344 |
pr | +0.323 |
aming | +0.321 |
amed | +0.314 |
ths | +0.311 |
Neg logit contributions | |
This | -0.180 |
Novel | -0.179 |
These | -0.168 |
acts | -0.153 |
ness | -0.144 |
Token | |
Token ID | 220 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
These | +0.058 |
Novel | +0.056 |
This | +0.056 |
ses | +0.055 |
acts | +0.052 |
Neg logit contributions | |
nowhere | -0.065 |
aming | -0.053 |
pr | -0.052 |
amed | -0.051 |
we | -0.050 |
Token | searched |
Token ID | 16499 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
Novel | +0.491 |
This | +0.485 |
acts | +0.480 |
They | +0.468 |
ses | +0.461 |
Neg logit contributions | |
nowhere | -0.509 |
pr | -0.500 |
aming | -0.476 |
we | -0.472 |
amed | -0.450 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
nowhere | +0.403 |
pr | +0.394 |
we | +0.393 |
aming | +0.387 |
amed | +0.365 |
Neg logit contributions | |
Novel | -0.386 |
This | -0.376 |
Today | -0.363 |
They | -0.363 |
These | -0.357 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nowhere | +1.195 |
aming | +1.146 |
pr | +1.131 |
amed | +1.123 |
we | +1.082 |
Neg logit contributions | |
This | -0.582 |
These | -0.537 |
Novel | -0.523 |
Today | -0.482 |
But | -0.479 |
Token | it |
Token ID | 340 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
pr | +0.105 |
aming | +0.102 |
nowhere | +0.101 |
amed | +0.098 |
we | +0.094 |
Neg logit contributions | |
This | -0.119 |
These | -0.113 |
But | -0.108 |
Novel | -0.107 |
Today | -0.104 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
nowhere | +0.395 |
pr | +0.391 |
aming | +0.388 |
amed | +0.364 |
we | +0.355 |
Neg logit contributions | |
This | -0.405 |
Novel | -0.384 |
But | -0.381 |
These | -0.366 |
They | -0.357 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.160 |
pr | +0.144 |
amed | +0.137 |
aming | +0.135 |
dd | +0.134 |
Neg logit contributions | |
Novel | -0.219 |
This | -0.218 |
Today | -0.209 |
One | -0.209 |
ses | -0.206 |
Token | to |
Token ID | 284 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
nowhere | +1.456 |
aming | +1.431 |
amed | +1.414 |
pr | +1.354 |
dd | +1.341 |
Neg logit contributions | |
This | -0.997 |
Novel | -0.914 |
These | -0.882 |
They | -0.820 |
ses | -0.805 |
Token | be |
Token ID | 307 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
These | +0.024 |
ses | +0.022 |
This | +0.022 |
Novel | +0.020 |
Show | +0.019 |
Neg logit contributions | |
nowhere | -0.044 |
aming | -0.037 |
pr | -0.037 |
soon | -0.035 |
ep | -0.035 |
Token | found |
Token ID | 1043 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
This | +0.394 |
Novel | +0.394 |
The | +0.369 |
attitude | +0.367 |
ses | +0.360 |
Neg logit contributions | |
pr | -0.332 |
nowhere | -0.313 |
ths | -0.311 |
we | -0.309 |
aming | -0.288 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nowhere | +0.341 |
pr | +0.310 |
aming | +0.309 |
amed | +0.302 |
we | +0.290 |
Neg logit contributions | |
This | -0.195 |
Novel | -0.188 |
These | -0.186 |
acts | -0.163 |
Today | -0.157 |
Token | He |
Token ID | 679 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
Novel | +0.031 |
These | +0.030 |
acts | +0.029 |
ses | +0.029 |
This | +0.027 |
Neg logit contributions | |
nowhere | -0.090 |
aming | -0.076 |
pr | -0.074 |
amed | -0.074 |
we | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
nowhere | +0.328 |
aming | +0.293 |
pr | +0.287 |
amed | +0.279 |
lling | +0.276 |
Neg logit contributions | |
This | -0.219 |
These | -0.210 |
Today | -0.195 |
Novel | -0.192 |
They | -0.187 |
Token | Then |
Token ID | 6423 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
nowhere | +0.224 |
pr | +0.166 |
aming | +0.165 |
we | +0.160 |
amed | +0.159 |
Neg logit contributions | |
This | -0.320 |
These | -0.320 |
Novel | -0.303 |
Today | -0.298 |
They | -0.285 |
Token | , |
Token ID | 11 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
nowhere | +0.490 |
aming | +0.429 |
pr | +0.425 |
amed | +0.414 |
we | +0.411 |
Neg logit contributions | |
This | -0.260 |
These | -0.260 |
Novel | -0.247 |
Today | -0.228 |
ses | -0.225 |
Token | out |
Token ID | 503 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
This | +0.347 |
Today | +0.324 |
These | +0.323 |
But | +0.314 |
They | +0.311 |
Neg logit contributions | |
nowhere | -0.450 |
aming | -0.391 |
amed | -0.385 |
ep | -0.379 |
we | -0.369 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
nowhere | +0.293 |
pr | +0.249 |
aming | +0.241 |
amed | +0.230 |
we | +0.228 |
Neg logit contributions | |
These | -0.272 |
Novel | -0.266 |
This | -0.265 |
ses | -0.253 |
Today | -0.239 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.046 |
aming | +0.043 |
pr | +0.043 |
amed | +0.043 |
nowhere | +0.042 |
Neg logit contributions | |
This | -0.064 |
Novel | -0.063 |
These | -0.061 |
ses | -0.060 |
Today | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
nowhere | +1.788 |
aming | +1.596 |
pr | +1.557 |
amed | +1.548 |
we | +1.518 |
Neg logit contributions | |
This | -0.794 |
These | -0.773 |
Novel | -0.768 |
ses | -0.683 |
Today | -0.673 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
This | +0.347 |
These | +0.323 |
Novel | +0.323 |
They | +0.319 |
Today | +0.316 |
Neg logit contributions | |
nowhere | -0.444 |
aming | -0.396 |
amed | -0.389 |
pr | -0.379 |
ep | -0.378 |
Token | small |
Token ID | 1402 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
nowhere | +0.079 |
aming | +0.069 |
pr | +0.068 |
we | +0.066 |
amed | +0.066 |
Neg logit contributions | |
These | -0.065 |
This | -0.064 |
Novel | -0.063 |
ses | -0.059 |
Today | -0.058 |
Token | voice |
Token ID | 3809 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
These | +0.167 |
This | +0.162 |
Novel | +0.154 |
ses | +0.144 |
Show | +0.138 |
Neg logit contributions | |
nowhere | -0.195 |
aming | -0.153 |
pr | -0.153 |
in | -0.147 |
there | -0.144 |
Token | said |
Token ID | 531 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
This | +0.078 |
These | +0.077 |
Novel | +0.077 |
ses | +0.071 |
acts | +0.071 |
Neg logit contributions | |
nowhere | -0.070 |
aming | -0.059 |
amed | -0.056 |
pr | -0.056 |
we | -0.054 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
nowhere | +0.101 |
we | +0.093 |
pr | +0.090 |
aming | +0.090 |
amed | +0.085 |
Neg logit contributions | |
This | -0.130 |
These | -0.124 |
Novel | -0.124 |
Today | -0.118 |
They | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +1.130 |
aming | +1.007 |
pr | +0.991 |
amed | +0.974 |
we | +0.950 |
Neg logit contributions | |
This | -0.685 |
These | -0.673 |
Novel | -0.651 |
Today | -0.600 |
ses | -0.597 |
Token | but |
Token ID | 475 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
This | +0.284 |
These | +0.266 |
Novel | +0.262 |
They | +0.250 |
But | +0.244 |
Neg logit contributions | |
nowhere | -0.500 |
pr | -0.494 |
aming | -0.470 |
amed | -0.461 |
P | -0.457 |
Token | he |
Token ID | 339 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
nowhere | +0.116 |
aming | +0.112 |
pr | +0.112 |
we | +0.110 |
amed | +0.107 |
Neg logit contributions | |
This | -0.102 |
These | -0.097 |
They | -0.090 |
Novel | -0.090 |
But | -0.090 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
pr | +0.041 |
aming | +0.040 |
amed | +0.038 |
we | +0.038 |
nowhere | +0.038 |
Neg logit contributions | |
ses | -0.034 |
This | -0.033 |
acts | -0.033 |
Novel | -0.033 |
try | -0.032 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.125 |
pr | +0.108 |
P | +0.104 |
dd | +0.103 |
ths | +0.099 |
Neg logit contributions | |
This | -0.228 |
The | -0.221 |
brain | -0.220 |
need | -0.217 |
He | -0.216 |
Token | in |
Token ID | 287 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
aming | +1.485 |
amed | +1.482 |
nowhere | +1.453 |
dd | +1.448 |
ths | +1.420 |
Neg logit contributions | |
This | -0.868 |
Novel | -0.793 |
The | -0.712 |
opens | -0.709 |
try | -0.700 |
Token | sight |
Token ID | 6504 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
nowhere | +0.489 |
aming | +0.422 |
pr | +0.420 |
amed | +0.401 |
we | +0.400 |
Neg logit contributions | |
These | -0.471 |
This | -0.470 |
Novel | -0.458 |
ses | -0.432 |
Today | -0.423 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nowhere | +0.274 |
aming | +0.239 |
pr | +0.237 |
amed | +0.231 |
we | +0.225 |
Neg logit contributions | |
This | -0.176 |
These | -0.175 |
Novel | -0.168 |
Today | -0.154 |
ses | -0.151 |
Token | He |
Token ID | 679 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
These | +0.042 |
Novel | +0.041 |
This | +0.041 |
ses | +0.038 |
acts | +0.036 |
Neg logit contributions | |
nowhere | -0.078 |
aming | -0.067 |
pr | -0.066 |
amed | -0.065 |
we | -0.064 |
Token | seemed |
Token ID | 3947 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
acts | +0.451 |
This | +0.427 |
opens | +0.426 |
One | +0.422 |
act | +0.421 |
Neg logit contributions | |
pr | -0.509 |
aming | -0.508 |
nowhere | -0.485 |
we | -0.482 |
THE | -0.475 |
Token | for |
Token ID | 329 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
nowhere | +0.502 |
aming | +0.478 |
pr | +0.474 |
amed | +0.468 |
we | +0.448 |
Neg logit contributions | |
This | -0.381 |
These | -0.364 |
Novel | -0.363 |
Today | -0.344 |
ses | -0.333 |
Token | it |
Token ID | 340 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
Novel | +0.031 |
This | +0.031 |
These | +0.031 |
ses | +0.028 |
thank | +0.028 |
Neg logit contributions | |
nowhere | -0.037 |
aming | -0.033 |
pr | -0.033 |
amed | -0.033 |
we | -0.031 |
Token | but |
Token ID | 475 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
aming | +0.500 |
nowhere | +0.494 |
pr | +0.484 |
we | +0.480 |
amed | +0.479 |
Neg logit contributions | |
This | -0.291 |
Novel | -0.270 |
These | -0.261 |
ses | -0.259 |
Today | -0.247 |
Token | it |
Token ID | 340 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
pr | +0.118 |
aming | +0.117 |
ep | +0.113 |
P | +0.111 |
amed | +0.111 |
Neg logit contributions | |
This | -0.092 |
But | -0.088 |
The | -0.085 |
It | -0.083 |
These | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
aming | +0.417 |
nowhere | +0.405 |
pr | +0.402 |
year | +0.391 |
amed | +0.389 |
Neg logit contributions | |
This | -0.335 |
ses | -0.330 |
Novel | -0.328 |
But | -0.312 |
squeeze | -0.311 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.133 |
dd | +0.114 |
in | +0.112 |
pr | +0.109 |
aming | +0.109 |
Neg logit contributions | |
Novel | -0.233 |
ses | -0.232 |
This | -0.230 |
One | -0.225 |
Today | -0.221 |
Token | to |
Token ID | 284 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
nowhere | +1.426 |
aming | +1.416 |
amed | +1.391 |
dd | +1.353 |
pr | +1.306 |
Neg logit contributions | |
This | -0.978 |
Novel | -0.927 |
These | -0.851 |
ses | -0.824 |
They | -0.787 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.025 |
This | +0.023 |
ses | +0.023 |
Show | +0.021 |
Novel | +0.021 |
Neg logit contributions | |
nowhere | -0.044 |
aming | -0.038 |
pr | -0.038 |
we | -0.036 |
amed | -0.035 |
Token | seen |
Token ID | 1775 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
Novel | +0.376 |
This | +0.365 |
The | +0.346 |
ses | +0.341 |
attitude | +0.340 |
Neg logit contributions | |
ths | -0.316 |
nowhere | -0.315 |
pr | -0.314 |
we | -0.305 |
THE | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nowhere | +0.573 |
amed | +0.551 |
dd | +0.540 |
pr | +0.537 |
aming | +0.534 |
Neg logit contributions | |
This | -0.262 |
Novel | -0.258 |
These | -0.231 |
Today | -0.215 |
ness | -0.212 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
These | +0.041 |
Novel | +0.040 |
This | +0.040 |
ses | +0.039 |
acts | +0.037 |
Neg logit contributions | |
nowhere | -0.078 |
aming | -0.067 |
pr | -0.066 |
amed | -0.065 |
we | -0.064 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
nowhere | +0.005 |
aming | +0.005 |
pr | +0.005 |
amed | +0.005 |
we | +0.005 |
Neg logit contributions | |
This | -0.004 |
These | -0.004 |
Novel | -0.004 |
They | -0.004 |
ses | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +1.224 |
amed | +1.178 |
aming | +1.170 |
pr | +1.150 |
ths | +1.091 |
Neg logit contributions | |
This | -0.546 |
These | -0.517 |
Novel | -0.502 |
Today | -0.465 |
But | -0.431 |
Token | but |
Token ID | 475 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
This | +0.191 |
But | +0.189 |
Novel | +0.186 |
They | +0.175 |
ses | +0.174 |
Neg logit contributions | |
pr | -0.579 |
aming | -0.547 |
amed | -0.542 |
P | -0.542 |
in | -0.541 |
Token | he |
Token ID | 339 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
aming | +0.152 |
pr | +0.150 |
we | +0.146 |
if | +0.146 |
nowhere | +0.143 |
Neg logit contributions | |
This | -0.067 |
These | -0.060 |
Novel | -0.059 |
But | -0.057 |
They | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
pr | +0.046 |
aming | +0.046 |
amed | +0.042 |
THE | +0.041 |
if | +0.041 |
Neg logit contributions | |
But | -0.030 |
ses | -0.030 |
He | -0.029 |
The | -0.028 |
Novel | -0.027 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.193 |
P | +0.182 |
dd | +0.176 |
ths | +0.175 |
pr | +0.172 |
Neg logit contributions | |
ses | -0.158 |
Novel | -0.154 |
The | -0.152 |
cry | -0.147 |
slam | -0.147 |
Token | to |
Token ID | 284 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
nowhere | +1.428 |
aming | +1.369 |
amed | +1.327 |
dd | +1.264 |
pr | +1.252 |
Neg logit contributions | |
This | -1.024 |
Novel | -0.996 |
These | -0.927 |
ses | -0.894 |
They | -0.868 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.025 |
ses | +0.023 |
This | +0.023 |
Show | +0.021 |
Novel | +0.021 |
Neg logit contributions | |
nowhere | -0.044 |
pr | -0.037 |
aming | -0.036 |
soon | -0.035 |
we | -0.035 |
Token | found |
Token ID | 1043 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Novel | +0.378 |
This | +0.363 |
The | +0.352 |
ses | +0.343 |
try | +0.339 |
Neg logit contributions | |
ths | -0.322 |
pr | -0.320 |
we | -0.318 |
THE | -0.315 |
nowhere | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nowhere | +0.334 |
aming | +0.299 |
pr | +0.297 |
amed | +0.287 |
we | +0.278 |
Neg logit contributions | |
This | -0.208 |
These | -0.203 |
Novel | -0.202 |
ses | -0.179 |
acts | -0.178 |
Token | She |
Token ID | 1375 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
acts | +0.041 |
Novel | +0.038 |
These | +0.038 |
offer | +0.036 |
ses | +0.035 |
Neg logit contributions | |
nowhere | -0.081 |
amed | -0.065 |
aming | -0.063 |
sudden | -0.062 |
B | -0.061 |
Token | long |
Token ID | 890 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
nowhere | +0.086 |
aming | +0.084 |
amed | +0.083 |
pr | +0.082 |
we | +0.080 |
Neg logit contributions | |
These | -0.052 |
This | -0.051 |
Novel | -0.048 |
ses | -0.047 |
Today | -0.046 |
Token | time |
Token ID | 640 |
Feature activation | +7.77e+00 |
Pos logit contributions | |
These | +0.369 |
This | +0.369 |
Novel | +0.363 |
Today | +0.341 |
ses | +0.340 |
Neg logit contributions | |
nowhere | -0.364 |
pr | -0.329 |
aming | -0.325 |
we | -0.318 |
amed | -0.312 |
Token | but |
Token ID | 475 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
nowhere | +0.569 |
pr | +0.521 |
aming | +0.510 |
amed | +0.501 |
we | +0.490 |
Neg logit contributions | |
This | -0.323 |
These | -0.322 |
Novel | -0.304 |
Today | -0.286 |
ses | -0.285 |
Token | it |
Token ID | 340 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
pr | +0.107 |
aming | +0.106 |
nowhere | +0.102 |
P | +0.102 |
amed | +0.100 |
Neg logit contributions | |
This | -0.112 |
These | -0.108 |
ses | -0.104 |
But | -0.101 |
They | -0.100 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
nowhere | +0.407 |
aming | +0.395 |
pr | +0.379 |
ppa | +0.361 |
amed | +0.360 |
Neg logit contributions | |
ses | -0.357 |
This | -0.355 |
acts | -0.352 |
Novel | -0.343 |
But | -0.339 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.175 |
P | +0.161 |
in | +0.156 |
dd | +0.153 |
pr | +0.153 |
Neg logit contributions | |
This | -0.193 |
ses | -0.192 |
Novel | -0.190 |
One | -0.188 |
Today | -0.187 |
Token | to |
Token ID | 284 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
nowhere | +1.475 |
aming | +1.446 |
amed | +1.422 |
dd | +1.379 |
pr | +1.347 |
Neg logit contributions | |
This | -0.954 |
Novel | -0.864 |
These | -0.827 |
acts | -0.802 |
ses | -0.789 |
Token | be |
Token ID | 307 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
These | +0.023 |
This | +0.021 |
Novel | +0.020 |
ses | +0.020 |
Today | +0.018 |
Neg logit contributions | |
nowhere | -0.047 |
pr | -0.040 |
aming | -0.040 |
we | -0.038 |
amed | -0.037 |
Token | found |
Token ID | 1043 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
This | +0.393 |
Novel | +0.389 |
ses | +0.374 |
acts | +0.371 |
The | +0.367 |
Neg logit contributions | |
pr | -0.314 |
nowhere | -0.314 |
we | -0.300 |
ths | -0.299 |
THE | -0.286 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nowhere | +0.337 |
pr | +0.301 |
aming | +0.299 |
amed | +0.292 |
ths | +0.282 |
Neg logit contributions | |
This | -0.199 |
These | -0.193 |
Novel | -0.193 |
acts | -0.173 |
ses | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
These | +0.052 |
This | +0.052 |
Novel | +0.050 |
ses | +0.047 |
Today | +0.046 |
Neg logit contributions | |
nowhere | -0.071 |
aming | -0.061 |
pr | -0.060 |
amed | -0.058 |
we | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
nowhere | +0.127 |
pr | +0.115 |
aming | +0.114 |
amed | +0.108 |
we | +0.106 |
Neg logit contributions | |
This | -0.112 |
These | -0.110 |
Novel | -0.105 |
ses | -0.104 |
They | -0.099 |
Token | truck |
Token ID | 7779 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
nowhere | +0.086 |
aming | +0.075 |
pr | +0.074 |
amed | +0.072 |
we | +0.071 |
Neg logit contributions | |
These | -0.059 |
This | -0.058 |
Novel | -0.056 |
ses | -0.054 |
Today | -0.052 |
Token | came |
Token ID | 1625 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
These | +0.053 |
This | +0.053 |
Novel | +0.051 |
ses | +0.049 |
Today | +0.047 |
Neg logit contributions | |
nowhere | -0.050 |
aming | -0.042 |
pr | -0.041 |
amed | -0.039 |
we | -0.038 |
Token | out |
Token ID | 503 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
nowhere | +0.215 |
pr | +0.173 |
aming | +0.170 |
dd | +0.166 |
ths | +0.166 |
Neg logit contributions | |
This | -0.205 |
Novel | -0.197 |
These | -0.192 |
They | -0.192 |
Today | -0.186 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
nowhere | +0.284 |
aming | +0.237 |
pr | +0.234 |
amed | +0.226 |
we | +0.222 |
Neg logit contributions | |
These | -0.278 |
This | -0.278 |
Novel | -0.269 |
Today | -0.252 |
ses | -0.251 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
nowhere | +0.060 |
pr | +0.060 |
aming | +0.058 |
we | +0.058 |
amed | +0.057 |
Neg logit contributions | |
This | -0.051 |
Novel | -0.050 |
These | -0.048 |
ses | -0.047 |
Today | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nowhere | +1.619 |
amed | +1.463 |
aming | +1.460 |
pr | +1.418 |
dd | +1.404 |
Neg logit contributions | |
This | -0.917 |
These | -0.855 |
Novel | -0.854 |
acts | -0.771 |
Today | -0.766 |
Token | It |
Token ID | 632 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
Novel | +0.032 |
These | +0.032 |
ses | +0.028 |
acts | +0.027 |
This | +0.027 |
Neg logit contributions | |
nowhere | -0.091 |
aming | -0.076 |
amed | -0.075 |
pr | -0.074 |
sudden | -0.072 |
Token | was |
Token ID | 373 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
This | +0.396 |
They | +0.388 |
He | +0.371 |
The | +0.367 |
shout | +0.363 |
Neg logit contributions | |
nowhere | -0.407 |
pr | -0.386 |
aming | -0.386 |
we | -0.375 |
if | -0.373 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
nowhere | +0.177 |
we | +0.175 |
pr | +0.170 |
in | +0.166 |
P | +0.166 |
Neg logit contributions | |
This | -0.192 |
ses | -0.186 |
Novel | -0.181 |
These | -0.179 |
They | -0.174 |
Token | fuel |
Token ID | 5252 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
These | +0.092 |
This | +0.088 |
ses | +0.087 |
Novel | +0.086 |
Today | +0.080 |
Neg logit contributions | |
nowhere | -0.167 |
pr | -0.151 |
aming | -0.147 |
we | -0.143 |
amed | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
nowhere | +0.499 |
aming | +0.440 |
pr | +0.437 |
amed | +0.423 |
we | +0.416 |
Neg logit contributions | |
This | -0.406 |
These | -0.402 |
Novel | -0.391 |
Today | -0.368 |
ses | -0.361 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
This | +0.335 |
But | +0.309 |
Novel | +0.306 |
These | +0.303 |
They | +0.300 |
Neg logit contributions | |
pr | -0.439 |
nowhere | -0.438 |
aming | -0.408 |
in | -0.406 |
P | -0.401 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
nowhere | +0.116 |
aming | +0.115 |
we | +0.113 |
pr | +0.113 |
amed | +0.110 |
Neg logit contributions | |
This | -0.093 |
But | -0.084 |
The | -0.083 |
These | -0.083 |
It | -0.080 |
Token | keys |
Token ID | 8251 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
These | +0.098 |
This | +0.095 |
Novel | +0.093 |
ses | +0.088 |
Today | +0.084 |
Neg logit contributions | |
nowhere | -0.166 |
pr | -0.148 |
aming | -0.145 |
we | -0.140 |
amed | -0.139 |
Token | were |
Token ID | 547 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
These | +0.009 |
This | +0.009 |
Novel | +0.009 |
ses | +0.008 |
acts | +0.008 |
Neg logit contributions | |
nowhere | -0.008 |
aming | -0.007 |
pr | -0.007 |
amed | -0.007 |
we | -0.006 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.038 |
P | +0.036 |
dd | +0.036 |
pr | +0.035 |
aming | +0.035 |
Neg logit contributions | |
ses | -0.048 |
Novel | -0.047 |
This | -0.046 |
hy | -0.046 |
attitude | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
nowhere | +1.401 |
aming | +1.293 |
amed | +1.275 |
dd | +1.226 |
pr | +1.219 |
Neg logit contributions | |
This | -1.072 |
These | -1.000 |
Novel | -0.998 |
acts | -0.913 |
ses | -0.907 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.023 |
This | +0.022 |
ses | +0.021 |
Novel | +0.020 |
Show | +0.019 |
Neg logit contributions | |
nowhere | -0.045 |
pr | -0.039 |
aming | -0.038 |
we | -0.036 |
amed | -0.036 |
Token | seen |
Token ID | 1775 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
Novel | +0.417 |
This | +0.406 |
ses | +0.402 |
attitude | +0.389 |
opens | +0.382 |
Neg logit contributions | |
nowhere | -0.289 |
we | -0.285 |
pr | -0.281 |
THE | -0.274 |
ths | -0.271 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nowhere | +0.546 |
pr | +0.495 |
amed | +0.489 |
aming | +0.483 |
dd | +0.475 |
Neg logit contributions | |
This | -0.324 |
Novel | -0.312 |
These | -0.307 |
Today | -0.277 |
ness | -0.274 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
Novel | +0.031 |
These | +0.031 |
ses | +0.028 |
This | +0.028 |
acts | +0.027 |
Neg logit contributions | |
nowhere | -0.090 |
aming | -0.077 |
pr | -0.076 |
amed | -0.075 |
we | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
nowhere | +0.107 |
we | +0.100 |
aming | +0.096 |
pr | +0.095 |
amed | +0.091 |
Neg logit contributions | |
This | -0.122 |
Novel | -0.119 |
These | -0.116 |
They | -0.113 |
thank | -0.112 |
Token | but |
Token ID | 475 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
This | +0.306 |
Novel | +0.296 |
These | +0.291 |
They | +0.280 |
ses | +0.276 |
Neg logit contributions | |
nowhere | -0.484 |
pr | -0.464 |
aming | -0.449 |
in | -0.432 |
amed | -0.432 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
pr | +0.111 |
nowhere | +0.109 |
aming | +0.108 |
amed | +0.102 |
we | +0.102 |
Neg logit contributions | |
This | -0.103 |
These | -0.101 |
They | -0.095 |
ses | -0.095 |
Novel | -0.092 |
Token | monster |
Token ID | 9234 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
These | +0.110 |
This | +0.108 |
Novel | +0.105 |
ses | +0.100 |
Today | +0.096 |
Neg logit contributions | |
nowhere | -0.154 |
aming | -0.133 |
pr | -0.133 |
amed | -0.127 |
we | -0.126 |
Token | was |
Token ID | 373 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
nowhere | +0.137 |
aming | +0.131 |
pr | +0.127 |
amed | +0.126 |
THE | +0.120 |
Neg logit contributions | |
Novel | -0.142 |
acts | -0.142 |
This | -0.141 |
ses | -0.139 |
These | -0.138 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.133 |
P | +0.122 |
pr | +0.116 |
ths | +0.110 |
dd | +0.108 |
Neg logit contributions | |
ses | -0.225 |
This | -0.212 |
The | -0.210 |
Novel | -0.209 |
thank | -0.206 |
Token | to |
Token ID | 284 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
aming | +1.480 |
amed | +1.474 |
nowhere | +1.457 |
ths | +1.424 |
dd | +1.415 |
Neg logit contributions | |
This | -0.886 |
Novel | -0.817 |
These | -0.725 |
The | -0.723 |
ses | -0.716 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.025 |
This | +0.023 |
ses | +0.023 |
Novel | +0.021 |
Show | +0.020 |
Neg logit contributions | |
nowhere | -0.044 |
pr | -0.037 |
aming | -0.036 |
soon | -0.034 |
THE | -0.034 |
Token | found |
Token ID | 1043 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
This | +0.361 |
Novel | +0.360 |
The | +0.345 |
opens | +0.326 |
acts | +0.325 |
Neg logit contributions | |
ths | -0.335 |
pr | -0.330 |
we | -0.325 |
THE | -0.305 |
nowhere | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nowhere | +0.345 |
pr | +0.312 |
aming | +0.311 |
amed | +0.303 |
ths | +0.294 |
Neg logit contributions | |
This | -0.192 |
Novel | -0.184 |
These | -0.182 |
acts | -0.167 |
ses | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
Novel | +0.032 |
These | +0.030 |
ses | +0.030 |
This | +0.028 |
hy | +0.026 |
Neg logit contributions | |
nowhere | -0.088 |
aming | -0.076 |
amed | -0.076 |
pr | -0.074 |
we | -0.072 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
nowhere | +0.261 |
aming | +0.183 |
pr | +0.180 |
amed | +0.176 |
ths | +0.174 |
Neg logit contributions | |
These | -0.295 |
This | -0.286 |
Novel | -0.276 |
Today | -0.251 |
Show | -0.250 |
Token | , |
Token ID | 11 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
nowhere | +0.654 |
pr | +0.565 |
aming | +0.561 |
amed | +0.535 |
we | +0.531 |
Neg logit contributions | |
These | -0.380 |
This | -0.370 |
Novel | -0.362 |
ses | -0.352 |
Today | -0.327 |
Token | from |
Token ID | 422 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
This | +0.332 |
These | +0.330 |
Novel | +0.314 |
They | +0.287 |
Today | +0.278 |
Neg logit contributions | |
nowhere | -0.486 |
aming | -0.442 |
amed | -0.425 |
pr | -0.415 |
we | -0.402 |
Token | out |
Token ID | 503 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
nowhere | +0.109 |
pr | +0.105 |
we | +0.104 |
if | +0.103 |
aming | +0.103 |
Neg logit contributions | |
ses | -0.129 |
This | -0.128 |
Novel | -0.125 |
These | -0.121 |
The | -0.117 |
Token | of |
Token ID | 286 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
nowhere | +0.259 |
pr | +0.212 |
aming | +0.211 |
amed | +0.198 |
we | +0.196 |
Neg logit contributions | |
These | -0.304 |
This | -0.300 |
Novel | -0.299 |
ses | -0.286 |
Today | -0.276 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.022 |
pr | +0.021 |
if | +0.019 |
aming | +0.019 |
ll | +0.018 |
Neg logit contributions | |
This | -0.086 |
Novel | -0.084 |
These | -0.081 |
ses | -0.081 |
The | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +1.723 |
aming | +1.512 |
pr | +1.495 |
amed | +1.455 |
we | +1.437 |
Neg logit contributions | |
These | -0.869 |
This | -0.868 |
Novel | -0.842 |
ses | -0.766 |
acts | -0.737 |
Token | magic |
Token ID | 5536 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
This | +0.350 |
These | +0.344 |
Novel | +0.333 |
They | +0.309 |
The | +0.301 |
Neg logit contributions | |
nowhere | -0.455 |
aming | -0.417 |
pr | -0.403 |
amed | -0.400 |
ep | -0.378 |
Token | happened |
Token ID | 3022 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
These | +0.133 |
This | +0.131 |
Novel | +0.129 |
ses | +0.123 |
Today | +0.118 |
Neg logit contributions | |
nowhere | -0.139 |
aming | -0.116 |
pr | -0.116 |
amed | -0.110 |
we | -0.108 |
Token | ! |
Token ID | 0 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
nowhere | +0.114 |
aming | +0.101 |
pr | +0.100 |
amed | +0.098 |
ths | +0.095 |
Neg logit contributions | |
This | -0.067 |
These | -0.062 |
Novel | -0.061 |
Today | -0.057 |
ses | -0.055 |
Token | Out |
Token ID | 3806 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ses | +0.038 |
Novel | +0.036 |
These | +0.036 |
acts | +0.035 |
This | +0.034 |
Neg logit contributions | |
nowhere | -0.076 |
aming | -0.064 |
pr | -0.064 |
amed | -0.062 |
we | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
we | +0.192 |
P | +0.190 |
nowhere | +0.182 |
pr | +0.180 |
dd | +0.174 |
Neg logit contributions | |
This | -0.175 |
ses | -0.172 |
cry | -0.165 |
scream | -0.164 |
Novel | -0.164 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
nowhere | +0.627 |
pr | +0.527 |
aming | +0.523 |
we | +0.510 |
amed | +0.494 |
Neg logit contributions | |
These | -0.586 |
This | -0.585 |
Novel | -0.571 |
ses | -0.545 |
Today | -0.529 |
Token | that |
Token ID | 326 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
These | +0.156 |
This | +0.151 |
Novel | +0.149 |
ses | +0.143 |
Today | +0.138 |
Neg logit contributions | |
nowhere | -0.151 |
aming | -0.123 |
pr | -0.123 |
we | -0.117 |
amed | -0.116 |
Token | he |
Token ID | 339 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
nowhere | +0.192 |
aming | +0.182 |
pr | +0.181 |
amed | +0.177 |
we | +0.167 |
Neg logit contributions | |
This | -0.147 |
These | -0.141 |
Novel | -0.139 |
Today | -0.127 |
They | -0.127 |
Token | had |
Token ID | 550 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
nowhere | +0.041 |
pr | +0.037 |
aming | +0.037 |
we | +0.035 |
amed | +0.034 |
Neg logit contributions | |
Novel | -0.039 |
This | -0.037 |
ses | -0.036 |
They | -0.035 |
thank | -0.035 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
aming | +0.247 |
nowhere | +0.242 |
pr | +0.241 |
we | +0.235 |
amed | +0.224 |
Neg logit contributions | |
This | -0.285 |
These | -0.266 |
Novel | -0.266 |
ses | -0.261 |
thank | -0.254 |
Token | to |
Token ID | 284 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
nowhere | +1.417 |
aming | +1.297 |
dd | +1.262 |
pr | +1.260 |
ths | +1.221 |
Neg logit contributions | |
This | -1.082 |
Novel | -1.035 |
These | -1.021 |
ses | -0.957 |
acts | -0.952 |
Token | go |
Token ID | 467 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
These | +0.028 |
This | +0.025 |
ses | +0.025 |
Today | +0.022 |
Show | +0.021 |
Neg logit contributions | |
nowhere | -0.043 |
pr | -0.037 |
soon | -0.036 |
aming | -0.036 |
there | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
This | +0.368 |
These | +0.359 |
Novel | +0.359 |
Today | +0.337 |
They | +0.325 |
Neg logit contributions | |
nowhere | -0.337 |
aming | -0.290 |
pr | -0.281 |
amed | -0.275 |
we | -0.267 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
These | +0.059 |
Novel | +0.058 |
This | +0.057 |
ses | +0.057 |
acts | +0.054 |
Neg logit contributions | |
nowhere | -0.063 |
aming | -0.050 |
pr | -0.049 |
amed | -0.048 |
we | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
nowhere | +0.325 |
aming | +0.293 |
pr | +0.293 |
amed | +0.278 |
ths | +0.271 |
Neg logit contributions | |
This | -0.224 |
These | -0.213 |
Novel | -0.203 |
Today | -0.192 |
They | -0.190 |
Token | so |
Token ID | 523 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
we | +0.192 |
P | +0.190 |
nowhere | +0.182 |
pr | +0.180 |
dd | +0.174 |
Neg logit contributions | |
This | -0.175 |
ses | -0.172 |
cry | -0.165 |
scream | -0.164 |
Novel | -0.164 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
nowhere | +0.627 |
pr | +0.527 |
aming | +0.523 |
we | +0.510 |
amed | +0.494 |
Neg logit contributions | |
These | -0.586 |
This | -0.585 |
Novel | -0.571 |
ses | -0.545 |
Today | -0.529 |
Token | that |
Token ID | 326 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
These | +0.156 |
This | +0.151 |
Novel | +0.149 |
ses | +0.143 |
Today | +0.138 |
Neg logit contributions | |
nowhere | -0.151 |
aming | -0.123 |
pr | -0.123 |
we | -0.117 |
amed | -0.116 |
Token | he |
Token ID | 339 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
nowhere | +0.192 |
aming | +0.182 |
pr | +0.181 |
amed | +0.177 |
we | +0.167 |
Neg logit contributions | |
This | -0.147 |
These | -0.141 |
Novel | -0.139 |
Today | -0.127 |
They | -0.127 |
Token | had |
Token ID | 550 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
nowhere | +0.041 |
pr | +0.037 |
aming | +0.037 |
we | +0.035 |
amed | +0.034 |
Neg logit contributions | |
Novel | -0.039 |
This | -0.037 |
ses | -0.036 |
They | -0.035 |
thank | -0.035 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
aming | +0.247 |
nowhere | +0.242 |
pr | +0.241 |
we | +0.235 |
amed | +0.224 |
Neg logit contributions | |
This | -0.285 |
These | -0.266 |
Novel | -0.266 |
ses | -0.261 |
thank | -0.254 |
Token | to |
Token ID | 284 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
nowhere | +1.417 |
aming | +1.297 |
dd | +1.262 |
pr | +1.260 |
ths | +1.221 |
Neg logit contributions | |
This | -1.082 |
Novel | -1.035 |
These | -1.021 |
ses | -0.957 |
acts | -0.952 |
Token | go |
Token ID | 467 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
These | +0.028 |
This | +0.025 |
ses | +0.025 |
Today | +0.022 |
Show | +0.021 |
Neg logit contributions | |
nowhere | -0.043 |
pr | -0.037 |
soon | -0.036 |
aming | -0.036 |
there | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
This | +0.368 |
These | +0.359 |
Novel | +0.359 |
Today | +0.337 |
They | +0.325 |
Neg logit contributions | |
nowhere | -0.337 |
aming | -0.290 |
pr | -0.281 |
amed | -0.275 |
we | -0.267 |
Token |
|
Token ID | 198 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
These | +0.059 |
Novel | +0.058 |
This | +0.057 |
ses | +0.057 |
acts | +0.054 |
Neg logit contributions | |
nowhere | -0.063 |
aming | -0.050 |
pr | -0.049 |
amed | -0.048 |
we | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
nowhere | +0.325 |
aming | +0.293 |
pr | +0.293 |
amed | +0.278 |
ths | +0.271 |
Neg logit contributions | |
This | -0.224 |
These | -0.213 |
Novel | -0.203 |
Today | -0.192 |
They | -0.190 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
This | +0.286 |
These | +0.265 |
The | +0.250 |
But | +0.248 |
thank | +0.246 |
Neg logit contributions | |
aming | -0.500 |
amed | -0.490 |
pr | -0.482 |
nowhere | -0.475 |
in | -0.468 |
Token | 's |
Token ID | 338 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
This | +0.014 |
Novel | +0.013 |
These | +0.013 |
ses | +0.013 |
They | +0.012 |
Neg logit contributions | |
nowhere | -0.014 |
pr | -0.013 |
aming | -0.012 |
we | -0.012 |
amed | -0.012 |
Token | favorite |
Token ID | 4004 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Novel | +0.156 |
This | +0.153 |
These | +0.151 |
ses | +0.150 |
attitude | +0.141 |
Neg logit contributions | |
nowhere | -0.272 |
pr | -0.260 |
aming | -0.256 |
we | -0.247 |
amed | -0.245 |
Token | doll |
Token ID | 3654 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
These | +0.188 |
This | +0.185 |
Novel | +0.181 |
ses | +0.170 |
Today | +0.165 |
Neg logit contributions | |
nowhere | -0.258 |
aming | -0.222 |
pr | -0.220 |
amed | -0.211 |
we | -0.210 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
These | +0.162 |
This | +0.159 |
Novel | +0.158 |
ses | +0.151 |
Today | +0.149 |
Neg logit contributions | |
nowhere | -0.097 |
pr | -0.073 |
aming | -0.073 |
we | -0.068 |
amed | -0.068 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
P | +0.160 |
aming | +0.159 |
we | +0.158 |
pr | +0.157 |
dd | +0.154 |
Neg logit contributions | |
This | -0.200 |
Novel | -0.187 |
ses | -0.185 |
These | -0.181 |
hy | -0.179 |
Token | to |
Token ID | 284 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
nowhere | +1.404 |
aming | +1.337 |
amed | +1.305 |
pr | +1.264 |
dd | +1.256 |
Neg logit contributions | |
This | -1.089 |
Novel | -1.012 |
These | -1.006 |
ses | -0.918 |
Today | -0.888 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.025 |
ses | +0.024 |
This | +0.023 |
Novel | +0.021 |
Show | +0.021 |
Neg logit contributions | |
nowhere | -0.043 |
pr | -0.037 |
aming | -0.036 |
soon | -0.036 |
we | -0.034 |
Token | found |
Token ID | 1043 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
This | +0.430 |
Novel | +0.419 |
These | +0.400 |
ses | +0.390 |
attitude | +0.388 |
Neg logit contributions | |
nowhere | -0.320 |
pr | -0.301 |
we | -0.292 |
THE | -0.287 |
aming | -0.282 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nowhere | +0.315 |
aming | +0.280 |
pr | +0.279 |
amed | +0.270 |
dd | +0.261 |
Neg logit contributions | |
This | -0.224 |
Novel | -0.219 |
These | -0.218 |
acts | -0.195 |
ses | -0.194 |
Token | She |
Token ID | 1375 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
acts | +0.029 |
ses | +0.027 |
Novel | +0.027 |
offer | +0.026 |
These | +0.025 |
Neg logit contributions | |
nowhere | -0.091 |
aming | -0.074 |
amed | -0.073 |
we | -0.071 |
pr | -0.071 |
Token | home |
Token ID | 1363 |
Feature activation | +8.32e+00 |
Pos logit contributions | |
nowhere | +0.285 |
aming | +0.241 |
pr | +0.238 |
amed | +0.228 |
we | +0.226 |
Neg logit contributions | |
These | -0.260 |
This | -0.259 |
Novel | -0.252 |
ses | -0.238 |
Today | -0.233 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +0.620 |
aming | +0.534 |
pr | +0.530 |
amed | +0.509 |
we | +0.509 |
Neg logit contributions | |
These | -0.364 |
This | -0.354 |
Novel | -0.348 |
ses | -0.332 |
Today | -0.312 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
This | +0.260 |
These | +0.258 |
Novel | +0.241 |
ses | +0.226 |
They | +0.223 |
Neg logit contributions | |
nowhere | -0.552 |
aming | -0.507 |
pr | -0.486 |
amed | -0.481 |
we | -0.466 |
Token | wallet |
Token ID | 13008 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
These | +0.104 |
This | +0.101 |
Novel | +0.100 |
ses | +0.096 |
Today | +0.091 |
Neg logit contributions | |
nowhere | -0.150 |
pr | -0.142 |
aming | -0.134 |
we | -0.134 |
amed | -0.131 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
pr | +0.051 |
nowhere | +0.049 |
aming | +0.049 |
we | +0.048 |
Mill | +0.048 |
Neg logit contributions | |
hy | -0.044 |
Novel | -0.043 |
opens | -0.042 |
This | -0.042 |
ses | -0.042 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.182 |
P | +0.149 |
in | +0.148 |
if | +0.140 |
dd | +0.140 |
Neg logit contributions | |
leave | -0.192 |
thank | -0.184 |
hy | -0.181 |
ses | -0.180 |
Novel | -0.179 |
Token | to |
Token ID | 284 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
nowhere | +1.431 |
aming | +1.422 |
amed | +1.410 |
dd | +1.355 |
pr | +1.342 |
Neg logit contributions | |
This | -0.936 |
Novel | -0.883 |
These | -0.809 |
acts | -0.787 |
ses | -0.787 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.024 |
ses | +0.022 |
This | +0.022 |
Novel | +0.020 |
Show | +0.020 |
Neg logit contributions | |
nowhere | -0.045 |
pr | -0.038 |
aming | -0.037 |
soon | -0.036 |
we | -0.035 |
Token | seen |
Token ID | 1775 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
This | +0.405 |
Novel | +0.399 |
attitude | +0.375 |
ses | +0.374 |
The | +0.371 |
Neg logit contributions | |
pr | -0.314 |
nowhere | -0.306 |
we | -0.306 |
ths | -0.299 |
THE | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nowhere | +0.534 |
amed | +0.497 |
pr | +0.492 |
aming | +0.488 |
P | +0.474 |
Neg logit contributions | |
This | -0.324 |
Novel | -0.315 |
These | -0.304 |
Today | -0.273 |
ness | -0.273 |
Token | Mia |
Token ID | 32189 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
Novel | +0.037 |
These | +0.037 |
acts | +0.033 |
ses | +0.033 |
This | +0.033 |
Neg logit contributions | |
nowhere | -0.083 |
aming | -0.068 |
pr | -0.067 |
amed | -0.067 |
we | -0.065 |
Token | it |
Token ID | 340 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
These | +0.034 |
This | +0.034 |
Novel | +0.033 |
ses | +0.031 |
acts | +0.030 |
Neg logit contributions | |
nowhere | -0.037 |
pr | -0.032 |
aming | -0.032 |
amed | -0.030 |
we | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +0.430 |
aming | +0.429 |
we | +0.422 |
dd | +0.418 |
pr | +0.414 |
Neg logit contributions | |
This | -0.335 |
Novel | -0.324 |
They | -0.314 |
ses | -0.307 |
One | -0.302 |
Token | but |
Token ID | 475 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
This | +0.224 |
But | +0.217 |
They | +0.208 |
ses | +0.198 |
Novel | +0.198 |
Neg logit contributions | |
pr | -0.560 |
in | -0.551 |
P | -0.532 |
dd | -0.528 |
aming | -0.525 |
Token | it |
Token ID | 340 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
aming | +0.140 |
pr | +0.135 |
if | +0.134 |
we | +0.133 |
in | +0.132 |
Neg logit contributions | |
This | -0.081 |
But | -0.074 |
These | -0.073 |
They | -0.072 |
The | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
nowhere | +0.418 |
aming | +0.398 |
pr | +0.392 |
year | +0.360 |
amed | +0.359 |
Neg logit contributions | |
This | -0.366 |
ses | -0.352 |
They | -0.350 |
Novel | -0.345 |
But | -0.342 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
we | +0.143 |
in | +0.119 |
pr | +0.118 |
amed | +0.113 |
aming | +0.112 |
Neg logit contributions | |
ses | -0.233 |
One | -0.231 |
Novel | -0.228 |
This | -0.225 |
Today | -0.222 |
Token | to |
Token ID | 284 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
nowhere | +1.430 |
aming | +1.425 |
amed | +1.398 |
pr | +1.338 |
dd | +1.330 |
Neg logit contributions | |
This | -0.977 |
Novel | -0.909 |
These | -0.850 |
ses | -0.836 |
They | -0.813 |
Token | be |
Token ID | 307 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
These | +0.024 |
This | +0.022 |
ses | +0.021 |
Novel | +0.020 |
Today | +0.019 |
Neg logit contributions | |
nowhere | -0.045 |
aming | -0.039 |
pr | -0.038 |
we | -0.037 |
amed | -0.036 |
Token | seen |
Token ID | 1775 |
Feature activation | +7.64e+00 |
Pos logit contributions | |
Novel | +0.394 |
This | +0.389 |
ses | +0.375 |
The | +0.368 |
acts | +0.360 |
Neg logit contributions | |
pr | -0.325 |
ths | -0.315 |
nowhere | -0.312 |
we | -0.308 |
THE | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
nowhere | +0.540 |
amed | +0.525 |
pr | +0.520 |
aming | +0.513 |
ths | +0.505 |
Neg logit contributions | |
This | -0.294 |
Novel | -0.287 |
These | -0.262 |
ness | -0.243 |
The | -0.238 |
Token | Tim |
Token ID | 5045 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
These | +0.038 |
This | +0.038 |
Novel | +0.036 |
ses | +0.033 |
Today | +0.032 |
Neg logit contributions | |
nowhere | -0.083 |
aming | -0.073 |
pr | -0.073 |
amed | -0.070 |
we | -0.070 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
nowhere | +0.068 |
pr | +0.063 |
aming | +0.061 |
we | +0.056 |
amed | +0.055 |
Neg logit contributions | |
This | -0.062 |
Novel | -0.061 |
acts | -0.060 |
These | -0.059 |
The | -0.059 |
Token | so |
Token ID | 523 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
we | +0.209 |
P | +0.188 |
pr | +0.188 |
J | +0.184 |
ths | +0.177 |
Neg logit contributions | |
This | -0.169 |
The | -0.160 |
leave | -0.159 |
cry | -0.156 |
thank | -0.153 |
Token | scared |
Token ID | 12008 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
nowhere | +0.675 |
pr | +0.594 |
we | +0.589 |
aming | +0.581 |
amed | +0.548 |
Neg logit contributions | |
This | -0.522 |
These | -0.515 |
Novel | -0.493 |
ses | -0.474 |
Today | -0.451 |
Token | and |
Token ID | 290 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
nowhere | +0.030 |
pr | +0.026 |
aming | +0.026 |
amed | +0.025 |
we | +0.024 |
Neg logit contributions | |
This | -0.028 |
These | -0.028 |
Novel | -0.027 |
ses | -0.025 |
Today | -0.025 |
Token | had |
Token ID | 550 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
nowhere | +0.111 |
pr | +0.103 |
aming | +0.101 |
we | +0.095 |
amed | +0.093 |
Neg logit contributions | |
This | -0.127 |
Novel | -0.123 |
These | -0.121 |
ses | -0.118 |
thank | -0.115 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
nowhere | +0.270 |
aming | +0.246 |
pr | +0.242 |
we | +0.234 |
amed | +0.229 |
Neg logit contributions | |
This | -0.287 |
These | -0.280 |
Novel | -0.271 |
ses | -0.261 |
acts | -0.251 |
Token | to |
Token ID | 284 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
nowhere | +1.399 |
aming | +1.236 |
pr | +1.187 |
amed | +1.155 |
we | +1.149 |
Neg logit contributions | |
This | -1.169 |
These | -1.119 |
Novel | -1.116 |
ses | -1.029 |
acts | -1.019 |
Token | go |
Token ID | 467 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
These | +0.026 |
This | +0.023 |
ses | +0.023 |
Novel | +0.020 |
acts | +0.020 |
Neg logit contributions | |
nowhere | -0.043 |
pr | -0.037 |
aming | -0.037 |
soon | -0.036 |
THE | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
This | +0.360 |
These | +0.357 |
Novel | +0.351 |
Today | +0.325 |
ses | +0.324 |
Neg logit contributions | |
nowhere | -0.350 |
aming | -0.297 |
pr | -0.294 |
amed | -0.281 |
we | -0.275 |
Token | She |
Token ID | 1375 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
Novel | +0.045 |
These | +0.045 |
ses | +0.044 |
acts | +0.043 |
This | +0.042 |
Neg logit contributions | |
nowhere | -0.075 |
aming | -0.061 |
amed | -0.059 |
we | -0.059 |
pr | -0.058 |
Token | cried |
Token ID | 16896 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
Novel | +0.551 |
acts | +0.546 |
ses | +0.539 |
They | +0.537 |
This | +0.537 |
Neg logit contributions | |
pr | -0.576 |
nowhere | -0.572 |
aming | -0.562 |
we | -0.529 |
amed | -0.502 |
Token | ugly |
Token ID | 13400 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
nowhere | +0.141 |
aming | +0.126 |
we | +0.124 |
pr | +0.123 |
amed | +0.120 |
Neg logit contributions | |
This | -0.099 |
These | -0.096 |
Novel | -0.093 |
ses | -0.090 |
Today | -0.087 |
Token | cat |
Token ID | 3797 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
These | +0.385 |
This | +0.361 |
Novel | +0.353 |
ses | +0.317 |
Today | +0.311 |
Neg logit contributions | |
nowhere | -0.484 |
aming | -0.377 |
pr | -0.370 |
in | -0.364 |
dd | -0.355 |
Token | came |
Token ID | 1625 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
These | +0.212 |
This | +0.212 |
Novel | +0.207 |
ses | +0.198 |
Today | +0.191 |
Neg logit contributions | |
nowhere | -0.181 |
aming | -0.152 |
pr | -0.149 |
amed | -0.143 |
we | -0.138 |
Token | out |
Token ID | 503 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
nowhere | +0.222 |
aming | +0.185 |
pr | +0.182 |
amed | +0.175 |
we | +0.171 |
Neg logit contributions | |
This | -0.210 |
These | -0.205 |
Novel | -0.202 |
Today | -0.190 |
ses | -0.189 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nowhere | +0.300 |
aming | +0.254 |
pr | +0.250 |
amed | +0.244 |
we | +0.238 |
Neg logit contributions | |
This | -0.262 |
These | -0.261 |
Novel | -0.253 |
Today | -0.236 |
ses | -0.233 |
Token | nowhere |
Token ID | 12062 |
Feature activation | +2.20e+01 |
Pos logit contributions | |
nowhere | +0.058 |
pr | +0.058 |
aming | +0.056 |
we | +0.055 |
amed | +0.055 |
Neg logit contributions | |
This | -0.054 |
Novel | -0.053 |
These | -0.051 |
ses | -0.049 |
Today | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
nowhere | +1.627 |
aming | +1.486 |
amed | +1.465 |
pr | +1.451 |
dd | +1.390 |
Neg logit contributions | |
This | -0.932 |
These | -0.891 |
Novel | -0.888 |
acts | -0.786 |
Today | -0.785 |
Token | The |
Token ID | 383 |
Feature activation | -1.56e+01 |
Pos logit contributions | |
ses | +0.038 |
acts | +0.036 |
affect | +0.034 |
icks | +0.034 |
offer | +0.033 |
Neg logit contributions | |
nowhere | -0.078 |
there | -0.060 |
B | -0.057 |
sudden | -0.057 |
aming | -0.056 |
Token | cat |
Token ID | 3797 |
Feature activation | -3.36e+00 |
Pos logit contributions | |
These | +0.706 |
This | +0.694 |
Novel | +0.676 |
ses | +0.635 |
Today | +0.610 |
Neg logit contributions | |
nowhere | -1.148 |
aming | -0.998 |
pr | -0.994 |
amed | -0.954 |
we | -0.949 |
Token | stretched |
Token ID | 19110 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
This | +0.180 |
Novel | +0.175 |
These | +0.172 |
ses | +0.164 |
acts | +0.164 |
Neg logit contributions | |
nowhere | -0.185 |
aming | -0.177 |
pr | -0.173 |
amed | -0.165 |
we | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +0.100 |
aming | +0.085 |
pr | +0.085 |
we | +0.082 |
amed | +0.079 |
Neg logit contributions | |
This | -0.093 |
These | -0.091 |
Novel | -0.091 |
ses | -0.085 |
Today | -0.084 |
Token | These |
Token ID | 2312 |
Feature activation | -2.17e+01 |
Pos logit contributions | |
These | +0.132 |
Novel | +0.131 |
ses | +0.129 |
This | +0.124 |
acts | +0.119 |
Neg logit contributions | |
nowhere | -0.325 |
aming | -0.278 |
pr | -0.276 |
we | -0.269 |
amed | -0.268 |
Token | are |
Token ID | 389 |
Feature activation | -1.23e+01 |
Pos logit contributions | |
Novel | +0.966 |
This | +0.960 |
These | +0.945 |
ses | +0.893 |
Today | +0.887 |
Neg logit contributions | |
nowhere | -1.576 |
pr | -1.311 |
aming | -1.305 |
we | -1.296 |
in | -1.286 |
Token | not |
Token ID | 407 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
These | +0.725 |
This | +0.720 |
Novel | +0.690 |
ses | +0.666 |
They | +0.643 |
Neg logit contributions | |
nowhere | -0.717 |
aming | -0.617 |
pr | -0.601 |
amed | -0.578 |
we | -0.558 |
Token | candy |
Token ID | 18550 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
nowhere | +0.078 |
aming | +0.065 |
pr | +0.064 |
amed | +0.061 |
we | +0.061 |
Neg logit contributions | |
These | -0.076 |
This | -0.075 |
Novel | -0.074 |
ses | -0.070 |
Today | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
These | +0.174 |
This | +0.169 |
ses | +0.169 |
Novel | +0.169 |
Today | +0.166 |
Neg logit contributions | |
nowhere | -0.201 |
we | -0.163 |
in | -0.163 |
pr | -0.160 |
aming | -0.159 |
Token | These |
Token ID | 2312 |
Feature activation | -2.07e+01 |
Pos logit contributions | |
ses | +0.073 |
acts | +0.064 |
ness | +0.064 |
attitude | +0.063 |
Novel | +0.061 |
Neg logit contributions | |
nowhere | -0.177 |
aming | -0.151 |
we | -0.150 |
pr | -0.149 |
there | -0.149 |
Token | are |
Token ID | 389 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
This | +0.827 |
ses | +0.825 |
Novel | +0.819 |
These | +0.816 |
Today | +0.784 |
Neg logit contributions | |
nowhere | -1.549 |
aming | -1.299 |
pr | -1.292 |
we | -1.290 |
in | -1.288 |
Token | pills |
Token ID | 19521 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
These | +0.675 |
This | +0.670 |
Novel | +0.648 |
ses | +0.626 |
acts | +0.592 |
Neg logit contributions | |
nowhere | -0.687 |
aming | -0.595 |
pr | -0.584 |
amed | -0.563 |
we | -0.544 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
These | +0.272 |
This | +0.268 |
Novel | +0.263 |
ses | +0.252 |
Today | +0.245 |
Neg logit contributions | |
nowhere | -0.312 |
aming | -0.262 |
pr | -0.258 |
we | -0.247 |
amed | -0.247 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ses | +0.061 |
Novel | +0.053 |
attitude | +0.052 |
ness | +0.052 |
acts | +0.051 |
Neg logit contributions | |
nowhere | -0.153 |
we | -0.135 |
aming | -0.134 |
pr | -0.132 |
B | -0.132 |
Token | my |
Token ID | 1820 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
nowhere | +0.059 |
aming | +0.049 |
pr | +0.048 |
amed | +0.046 |
we | +0.045 |
Neg logit contributions | |
These | -0.061 |
This | -0.060 |
Novel | -0.059 |
ses | -0.056 |
Today | -0.055 |
Token | special |
Token ID | 2041 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
These | +0.024 |
This | +0.023 |
Novel | +0.023 |
ses | +0.021 |
Today | +0.021 |
Neg logit contributions | |
nowhere | -0.031 |
pr | -0.028 |
aming | -0.028 |
amed | -0.027 |
we | -0.026 |
Token | family |
Token ID | 1641 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
These | +0.131 |
This | +0.129 |
Novel | +0.126 |
ses | +0.119 |
Today | +0.115 |
Neg logit contributions | |
nowhere | -0.162 |
aming | -0.136 |
pr | -0.136 |
amed | -0.129 |
we | -0.128 |
Token | of |
Token ID | 286 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
nowhere | +0.290 |
pr | +0.258 |
aming | +0.254 |
amed | +0.251 |
we | +0.240 |
Neg logit contributions | |
This | -0.228 |
These | -0.226 |
Novel | -0.212 |
Today | -0.198 |
They | -0.198 |
Token | ducks |
Token ID | 39694 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
These | +0.012 |
This | +0.012 |
Novel | +0.011 |
They | +0.011 |
ses | +0.011 |
Neg logit contributions | |
nowhere | -0.011 |
pr | -0.010 |
aming | -0.010 |
amed | -0.010 |
we | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
This | +0.067 |
These | +0.067 |
They | +0.064 |
Novel | +0.062 |
Today | +0.058 |
Neg logit contributions | |
nowhere | -0.114 |
aming | -0.102 |
pr | -0.102 |
ths | -0.100 |
amed | -0.099 |
Token | These |
Token ID | 2312 |
Feature activation | -2.05e+01 |
Pos logit contributions | |
ses | +0.051 |
Novel | +0.044 |
These | +0.041 |
acts | +0.041 |
This | +0.037 |
Neg logit contributions | |
nowhere | -0.189 |
aming | -0.160 |
pr | -0.155 |
THE | -0.155 |
there | -0.154 |
Token | ducks |
Token ID | 39694 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
These | +1.059 |
This | +1.028 |
Novel | +1.008 |
ses | +0.956 |
acts | +0.935 |
Neg logit contributions | |
nowhere | -1.385 |
pr | -1.181 |
aming | -1.178 |
amed | -1.123 |
we | -1.103 |
Token | loved |
Token ID | 6151 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
These | +0.081 |
This | +0.080 |
Novel | +0.078 |
acts | +0.073 |
ses | +0.073 |
Neg logit contributions | |
nowhere | -0.084 |
aming | -0.072 |
pr | -0.071 |
amed | -0.067 |
we | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
This | +0.002 |
These | +0.002 |
Novel | +0.002 |
ses | +0.002 |
acts | +0.002 |
Neg logit contributions | |
nowhere | -0.003 |
aming | -0.002 |
pr | -0.002 |
amed | -0.002 |
we | -0.002 |
Token | share |
Token ID | 2648 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
These | +0.064 |
ses | +0.061 |
This | +0.059 |
Novel | +0.056 |
Today | +0.053 |
Neg logit contributions | |
nowhere | -0.093 |
pr | -0.085 |
soon | -0.083 |
ep | -0.082 |
aming | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
This | +0.607 |
These | +0.603 |
Novel | +0.593 |
ses | +0.534 |
acts | +0.532 |
Neg logit contributions | |
nowhere | -0.672 |
aming | -0.579 |
pr | -0.565 |
amed | -0.551 |
we | -0.534 |
Token | This |
Token ID | 770 |
Feature activation | -1.79e+01 |
Pos logit contributions | |
ses | +0.088 |
acts | +0.082 |
attitude | +0.081 |
affect | +0.075 |
ness | +0.074 |
Neg logit contributions | |
nowhere | -0.125 |
there | -0.113 |
year | -0.108 |
we | -0.107 |
THE | -0.106 |
Token | is |
Token ID | 318 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
These | +0.784 |
ses | +0.767 |
Novel | +0.762 |
This | +0.757 |
Today | +0.671 |
Neg logit contributions | |
nowhere | -1.285 |
pr | -1.099 |
aming | -1.092 |
amed | -1.063 |
we | -1.059 |
Token | your |
Token ID | 534 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
This | +0.528 |
These | +0.512 |
Novel | +0.502 |
ses | +0.472 |
They | +0.462 |
Neg logit contributions | |
nowhere | -0.606 |
aming | -0.545 |
pr | -0.528 |
amed | -0.513 |
we | -0.512 |
Token | teacher |
Token ID | 4701 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
These | +0.345 |
This | +0.333 |
Novel | +0.326 |
ses | +0.303 |
Today | +0.293 |
Neg logit contributions | |
nowhere | -0.477 |
pr | -0.392 |
aming | -0.392 |
we | -0.381 |
amed | -0.378 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
These | +0.192 |
This | +0.188 |
Novel | +0.185 |
ses | +0.176 |
Today | +0.169 |
Neg logit contributions | |
nowhere | -0.245 |
aming | -0.208 |
pr | -0.207 |
we | -0.197 |
amed | -0.197 |
Token | These |
Token ID | 2312 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
ses | +0.076 |
attitude | +0.065 |
acts | +0.063 |
ness | +0.061 |
backs | +0.057 |
Neg logit contributions | |
nowhere | -0.118 |
pr | -0.106 |
we | -0.105 |
year | -0.105 |
there | -0.104 |
Token | are |
Token ID | 389 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
ses | +1.022 |
This | +1.017 |
These | +1.014 |
Novel | +1.000 |
Today | +0.930 |
Neg logit contributions | |
nowhere | -1.300 |
pr | -1.115 |
aming | -1.105 |
we | -1.071 |
amed | -1.056 |
Token | your |
Token ID | 534 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
These | +0.629 |
This | +0.625 |
Novel | +0.605 |
ses | +0.568 |
Today | +0.547 |
Neg logit contributions | |
nowhere | -0.701 |
aming | -0.601 |
pr | -0.587 |
amed | -0.564 |
we | -0.553 |
Token | classmates |
Token ID | 28999 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
These | +0.347 |
This | +0.340 |
Novel | +0.332 |
ses | +0.313 |
Today | +0.305 |
Neg logit contributions | |
nowhere | -0.445 |
pr | -0.366 |
aming | -0.364 |
we | -0.358 |
amed | -0.351 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
nowhere | +0.089 |
aming | +0.077 |
pr | +0.077 |
amed | +0.074 |
we | +0.073 |
Neg logit contributions | |
These | -0.060 |
This | -0.060 |
Novel | -0.058 |
ses | -0.053 |
Today | -0.052 |
Token | They |
Token ID | 1119 |
Feature activation | -1.14e+01 |
Pos logit contributions | |
ses | +0.063 |
attitude | +0.054 |
acts | +0.052 |
ness | +0.052 |
Novel | +0.048 |
Neg logit contributions | |
nowhere | -0.114 |
we | -0.103 |
pr | -0.103 |
aming | -0.101 |
B | -0.101 |
Token |
|
Token ID | 198 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
nowhere | +0.223 |
pr | +0.190 |
aming | +0.189 |
amed | +0.180 |
we | +0.177 |
Neg logit contributions | |
These | -0.199 |
This | -0.198 |
Novel | -0.192 |
Today | -0.178 |
ses | -0.177 |
Token | " |
Token ID | 1 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
nowhere | +0.196 |
pr | +0.160 |
aming | +0.154 |
we | +0.148 |
amed | +0.148 |
Neg logit contributions | |
These | -0.236 |
This | -0.233 |
Novel | -0.224 |
Today | -0.211 |
They | -0.210 |
Token | Y |
Token ID | 56 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
nowhere | +0.001 |
pr | +0.001 |
aming | +0.001 |
amed | +0.001 |
exactly | +0.001 |
Neg logit contributions | |
These | -0.002 |
This | -0.001 |
Novel | -0.001 |
ses | -0.001 |
They | -0.001 |
Token | uck |
Token ID | 1347 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Novel | +0.276 |
ses | +0.267 |
These | +0.266 |
This | +0.261 |
acts | +0.258 |
Neg logit contributions | |
nowhere | -0.153 |
pr | -0.149 |
aming | -0.146 |
amed | -0.134 |
in | -0.129 |
Token | ! |
Token ID | 0 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
These | +0.070 |
This | +0.069 |
Novel | +0.067 |
ses | +0.064 |
Today | +0.061 |
Neg logit contributions | |
nowhere | -0.106 |
aming | -0.092 |
pr | -0.091 |
amed | -0.087 |
we | -0.087 |
Token | These |
Token ID | 2312 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
Novel | +0.058 |
offer | +0.055 |
attitude | +0.054 |
acts | +0.054 |
hy | +0.053 |
Neg logit contributions | |
nowhere | -0.130 |
we | -0.114 |
there | -0.113 |
aming | -0.108 |
in | -0.108 |
Token | past |
Token ID | 1613 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Novel | +0.788 |
This | +0.771 |
These | +0.761 |
Today | +0.746 |
ses | +0.694 |
Neg logit contributions | |
nowhere | -1.575 |
aming | -1.395 |
pr | -1.357 |
in | -1.355 |
we | -1.354 |
Token | ries |
Token ID | 1678 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
Novel | +0.223 |
These | +0.223 |
This | +0.221 |
ses | +0.215 |
Today | +0.214 |
Neg logit contributions | |
nowhere | -0.198 |
aming | -0.165 |
we | -0.164 |
pr | -0.161 |
in | -0.157 |
Token | are |
Token ID | 389 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
nowhere | +0.380 |
aming | +0.335 |
pr | +0.334 |
we | +0.322 |
amed | +0.317 |
Neg logit contributions | |
These | -0.168 |
Novel | -0.163 |
This | -0.162 |
ses | -0.150 |
Today | -0.147 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
These | +0.613 |
This | +0.611 |
Novel | +0.587 |
ses | +0.570 |
Today | +0.528 |
Neg logit contributions | |
nowhere | -0.692 |
aming | -0.600 |
pr | -0.590 |
amed | -0.569 |
we | -0.562 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
These | +0.190 |
This | +0.187 |
Novel | +0.183 |
ses | +0.173 |
Today | +0.168 |
Neg logit contributions | |
nowhere | -0.233 |
aming | -0.199 |
pr | -0.196 |
we | -0.189 |
amed | -0.187 |
Token | said |
Token ID | 531 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
nowhere | +0.094 |
pr | +0.080 |
aming | +0.079 |
we | +0.078 |
amed | +0.077 |
Neg logit contributions | |
These | -0.045 |
This | -0.043 |
Novel | -0.042 |
ses | -0.040 |
Today | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
nowhere | +0.282 |
pr | +0.243 |
we | +0.228 |
aming | +0.228 |
in | +0.225 |
Neg logit contributions | |
These | -0.199 |
Novel | -0.191 |
This | -0.190 |
ses | -0.188 |
Today | -0.179 |
Token | " |
Token ID | 366 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
This | +0.296 |
These | +0.292 |
Novel | +0.273 |
Today | +0.242 |
They | +0.242 |
Neg logit contributions | |
nowhere | -0.638 |
aming | -0.581 |
pr | -0.567 |
amed | -0.555 |
we | -0.530 |
Token | No |
Token ID | 2949 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
This | +0.131 |
These | +0.127 |
Novel | +0.119 |
But | +0.118 |
Today | +0.115 |
Neg logit contributions | |
nowhere | -0.150 |
pr | -0.128 |
aming | -0.128 |
amed | -0.124 |
bled | -0.117 |
Token | ! |
Token ID | 0 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
These | +0.210 |
Novel | +0.204 |
ses | +0.203 |
This | +0.203 |
Today | +0.179 |
Neg logit contributions | |
nowhere | -0.250 |
pr | -0.205 |
ths | -0.201 |
there | -0.196 |
sudden | -0.196 |
Token | These |
Token ID | 2312 |
Feature activation | -2.03e+01 |
Pos logit contributions | |
offer | +0.065 |
acts | +0.065 |
ses | +0.065 |
Novel | +0.065 |
attitude | +0.062 |
Neg logit contributions | |
nowhere | -0.108 |
we | -0.089 |
there | -0.089 |
in | -0.089 |
it | -0.086 |
Token | are |
Token ID | 389 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
Novel | +0.765 |
This | +0.763 |
These | +0.748 |
ses | +0.736 |
Today | +0.732 |
Neg logit contributions | |
nowhere | -1.574 |
in | -1.366 |
pr | -1.351 |
aming | -1.345 |
we | -1.314 |
Token | mine |
Token ID | 6164 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
These | +0.545 |
This | +0.543 |
Novel | +0.523 |
ses | +0.497 |
Today | +0.466 |
Neg logit contributions | |
nowhere | -0.771 |
aming | -0.681 |
pr | -0.670 |
amed | -0.649 |
we | -0.641 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
These | +0.010 |
This | +0.009 |
Novel | +0.009 |
ses | +0.009 |
Today | +0.009 |
Neg logit contributions | |
nowhere | -0.012 |
pr | -0.010 |
aming | -0.010 |
we | -0.010 |
amed | -0.010 |
Token | His |
Token ID | 2399 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
These | +0.158 |
This | +0.158 |
Novel | +0.150 |
ses | +0.139 |
Today | +0.137 |
Neg logit contributions | |
nowhere | -0.262 |
aming | -0.229 |
pr | -0.229 |
amed | -0.218 |
we | -0.216 |
Token | sister |
Token ID | 6621 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
These | +0.545 |
This | +0.545 |
Novel | +0.536 |
ses | +0.530 |
Today | +0.493 |
Neg logit contributions | |
nowhere | -0.894 |
aming | -0.809 |
pr | -0.802 |
amed | -0.759 |
we | -0.758 |
Token | other |
Token ID | 584 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
This | +0.560 |
These | +0.558 |
Novel | +0.551 |
ses | +0.504 |
acts | +0.501 |
Neg logit contributions | |
nowhere | -0.659 |
aming | -0.573 |
pr | -0.566 |
amed | -0.548 |
we | -0.523 |
Token | people |
Token ID | 661 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
nowhere | +0.014 |
aming | +0.012 |
pr | +0.012 |
amed | +0.011 |
we | +0.011 |
Neg logit contributions | |
These | -0.013 |
This | -0.012 |
Novel | -0.012 |
ses | -0.012 |
Today | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
nowhere | +0.097 |
aming | +0.082 |
pr | +0.082 |
amed | +0.078 |
we | +0.077 |
Neg logit contributions | |
These | -0.087 |
This | -0.086 |
Novel | -0.084 |
ses | -0.079 |
Today | -0.077 |
Token | things |
Token ID | 1243 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
These | +0.207 |
This | +0.204 |
Novel | +0.199 |
ses | +0.186 |
Today | +0.179 |
Neg logit contributions | |
nowhere | -0.328 |
aming | -0.284 |
pr | -0.282 |
amed | -0.271 |
we | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
nowhere | +0.174 |
aming | +0.148 |
pr | +0.147 |
amed | +0.140 |
we | +0.139 |
Neg logit contributions | |
These | -0.145 |
This | -0.143 |
Novel | -0.140 |
ses | -0.132 |
Today | -0.128 |
Token | These |
Token ID | 2312 |
Feature activation | -2.02e+01 |
Pos logit contributions | |
ses | +0.058 |
Novel | +0.052 |
acts | +0.051 |
attitude | +0.050 |
These | +0.049 |
Neg logit contributions | |
nowhere | -0.132 |
aming | -0.114 |
THE | -0.109 |
pr | -0.109 |
B | -0.108 |
Token | balls |
Token ID | 11333 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
This | +0.784 |
These | +0.774 |
Novel | +0.741 |
ses | +0.725 |
Today | +0.687 |
Neg logit contributions | |
nowhere | -1.581 |
pr | -1.361 |
aming | -1.360 |
we | -1.321 |
in | -1.304 |
Token | are |
Token ID | 389 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
These | +0.023 |
This | +0.022 |
Novel | +0.021 |
ses | +0.020 |
Today | +0.019 |
Neg logit contributions | |
nowhere | -0.074 |
aming | -0.065 |
pr | -0.065 |
amed | -0.063 |
we | -0.063 |
Token | not |
Token ID | 407 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
These | +0.642 |
This | +0.641 |
Novel | +0.636 |
ses | +0.607 |
Today | +0.573 |
Neg logit contributions | |
nowhere | -0.652 |
aming | -0.558 |
pr | -0.547 |
we | -0.532 |
amed | -0.524 |
Token | toys |
Token ID | 14958 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
nowhere | +0.130 |
pr | +0.107 |
aming | +0.107 |
amed | +0.101 |
we | +0.099 |
Neg logit contributions | |
These | -0.130 |
This | -0.127 |
Novel | -0.124 |
ses | -0.119 |
Today | -0.117 |
Token | , |
Token ID | 11 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
nowhere | +0.210 |
aming | +0.166 |
pr | +0.165 |
there | +0.163 |
in | +0.161 |
Neg logit contributions | |
These | -0.181 |
ses | -0.179 |
This | -0.177 |
Novel | -0.172 |
Today | -0.170 |
Token | , |
Token ID | 11 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
nowhere | +0.243 |
aming | +0.208 |
pr | +0.206 |
amed | +0.197 |
we | +0.196 |
Neg logit contributions | |
These | -0.183 |
This | -0.181 |
Novel | -0.176 |
ses | -0.166 |
Today | -0.161 |
Token | " |
Token ID | 366 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
This | +0.292 |
These | +0.288 |
Novel | +0.273 |
ses | +0.255 |
Today | +0.244 |
Neg logit contributions | |
nowhere | -0.610 |
aming | -0.547 |
pr | -0.542 |
amed | -0.525 |
we | -0.514 |
Token | Go |
Token ID | 5247 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
This | +0.124 |
These | +0.123 |
Novel | +0.112 |
Today | +0.109 |
But | +0.109 |
Neg logit contributions | |
nowhere | -0.123 |
amed | -0.102 |
pr | -0.101 |
exactly | -0.101 |
aming | -0.100 |
Token | away |
Token ID | 1497 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
This | +0.090 |
These | +0.088 |
Novel | +0.086 |
ses | +0.081 |
Today | +0.081 |
Neg logit contributions | |
nowhere | -0.071 |
aming | -0.058 |
pr | -0.056 |
we | -0.054 |
amed | -0.053 |
Token | ! |
Token ID | 0 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
nowhere | +0.353 |
pr | +0.298 |
aming | +0.296 |
amed | +0.274 |
we | +0.272 |
Neg logit contributions | |
These | -0.361 |
This | -0.343 |
Novel | -0.337 |
ses | -0.335 |
acts | -0.321 |
Token | These |
Token ID | 2312 |
Feature activation | -2.01e+01 |
Pos logit contributions | |
Novel | +0.051 |
ses | +0.049 |
acts | +0.047 |
attitude | +0.045 |
offer | +0.045 |
Neg logit contributions | |
nowhere | -0.121 |
we | -0.101 |
aming | -0.099 |
pr | -0.097 |
pped | -0.097 |
Token | are |
Token ID | 389 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
These | +1.040 |
This | +1.033 |
Novel | +1.005 |
ses | +0.966 |
Today | +0.941 |
Neg logit contributions | |
nowhere | -1.326 |
aming | -1.118 |
pr | -1.116 |
we | -1.071 |
amed | -1.050 |
Token | my |
Token ID | 616 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
This | +0.514 |
These | +0.499 |
ses | +0.468 |
Novel | +0.466 |
Dogs | +0.433 |
Neg logit contributions | |
nowhere | -0.743 |
aming | -0.704 |
pr | -0.684 |
amed | -0.675 |
we | -0.644 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
These | +0.341 |
This | +0.336 |
Novel | +0.329 |
ses | +0.314 |
Today | +0.303 |
Neg logit contributions | |
nowhere | -0.389 |
aming | -0.331 |
pr | -0.328 |
amed | -0.313 |
we | -0.309 |
Token | ." |
Token ID | 526 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
nowhere | +0.067 |
aming | +0.056 |
pr | +0.056 |
amed | +0.053 |
we | +0.053 |
Neg logit contributions | |
These | -0.059 |
This | -0.058 |
Novel | -0.057 |
ses | -0.054 |
Today | -0.052 |
Token | But |
Token ID | 887 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
These | +0.190 |
Novel | +0.185 |
ses | +0.179 |
This | +0.179 |
acts | +0.172 |
Neg logit contributions | |
nowhere | -0.286 |
aming | -0.239 |
pr | -0.234 |
we | -0.232 |
amed | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
nowhere | +0.288 |
pr | +0.251 |
aming | +0.248 |
amed | +0.234 |
we | +0.232 |
Neg logit contributions | |
This | -0.217 |
These | -0.216 |
Novel | -0.200 |
They | -0.192 |
Today | -0.191 |
Token | " |
Token ID | 1 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
nowhere | +0.234 |
pr | +0.188 |
aming | +0.180 |
we | +0.176 |
amed | +0.170 |
Neg logit contributions | |
These | -0.271 |
This | -0.265 |
Novel | -0.252 |
They | -0.239 |
Today | -0.237 |
Token | Go |
Token ID | 5247 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
nowhere | +0.033 |
pr | +0.029 |
exactly | +0.029 |
aming | +0.028 |
amed | +0.028 |
Neg logit contributions | |
These | -0.026 |
This | -0.025 |
Novel | -0.024 |
They | -0.024 |
acts | -0.023 |
Token | away |
Token ID | 1497 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
This | +0.075 |
These | +0.074 |
Novel | +0.071 |
Today | +0.067 |
ses | +0.067 |
Neg logit contributions | |
nowhere | -0.059 |
aming | -0.048 |
pr | -0.046 |
we | -0.044 |
amed | -0.044 |
Token | ! |
Token ID | 0 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
nowhere | +0.400 |
there | +0.341 |
pr | +0.339 |
in | +0.339 |
aming | +0.336 |
Neg logit contributions | |
These | -0.330 |
This | -0.317 |
ses | -0.316 |
Novel | -0.299 |
acts | -0.288 |
Token | These |
Token ID | 2312 |
Feature activation | -2.00e+01 |
Pos logit contributions | |
ses | +0.051 |
Novel | +0.050 |
acts | +0.049 |
attitude | +0.048 |
offer | +0.046 |
Neg logit contributions | |
nowhere | -0.091 |
there | -0.079 |
we | -0.078 |
in | -0.073 |
aming | -0.073 |
Token | are |
Token ID | 389 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
ses | +0.865 |
This | +0.820 |
Today | +0.789 |
These | +0.783 |
Novel | +0.775 |
Neg logit contributions | |
nowhere | -1.426 |
in | -1.320 |
there | -1.286 |
pr | -1.286 |
aming | -1.278 |
Token | my |
Token ID | 616 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
This | +0.515 |
These | +0.515 |
Novel | +0.480 |
ses | +0.459 |
They | +0.428 |
Neg logit contributions | |
nowhere | -0.773 |
aming | -0.692 |
pr | -0.678 |
amed | -0.663 |
we | -0.654 |
Token | blocks |
Token ID | 7021 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
These | +0.329 |
This | +0.325 |
Novel | +0.309 |
ses | +0.302 |
Today | +0.289 |
Neg logit contributions | |
nowhere | -0.379 |
pr | -0.304 |
there | -0.302 |
in | -0.301 |
aming | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
These | +0.057 |
This | +0.056 |
Novel | +0.055 |
ses | +0.052 |
Today | +0.050 |
Neg logit contributions | |
nowhere | -0.074 |
aming | -0.063 |
pr | -0.063 |
amed | -0.059 |
we | -0.059 |
Token | You |
Token ID | 921 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
ses | +0.051 |
Novel | +0.049 |
attitude | +0.049 |
acts | +0.049 |
ness | +0.045 |
Neg logit contributions | |
nowhere | -0.100 |
we | -0.088 |
there | -0.086 |
aming | -0.085 |
We | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
ses | +0.327 |
These | +0.325 |
Novel | +0.314 |
This | +0.310 |
acts | +0.294 |
Neg logit contributions | |
nowhere | -0.421 |
aming | -0.362 |
pr | -0.357 |
amed | -0.342 |
we | -0.341 |
Token | G |
Token ID | 402 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
These | +0.390 |
This | +0.386 |
ses | +0.383 |
Novel | +0.372 |
Today | +0.354 |
Neg logit contributions | |
nowhere | -0.466 |
pr | -0.379 |
in | -0.369 |
aming | -0.366 |
there | -0.366 |
Token | ull |
Token ID | 724 |
Feature activation | +9.82e+00 |
Pos logit contributions | |
These | +0.229 |
This | +0.225 |
Novel | +0.217 |
ses | +0.214 |
acts | +0.207 |
Neg logit contributions | |
nowhere | -0.180 |
aming | -0.148 |
pr | -0.148 |
we | -0.139 |
amed | -0.136 |
Token | iver |
Token ID | 1428 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
nowhere | +0.470 |
in | +0.469 |
a | +0.441 |
we | +0.438 |
ep | +0.434 |
Neg logit contributions | |
These | -0.553 |
ses | -0.548 |
Novel | -0.539 |
Today | -0.531 |
This | -0.527 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
These | +0.051 |
This | +0.050 |
Novel | +0.049 |
ses | +0.047 |
Today | +0.045 |
Neg logit contributions | |
nowhere | -0.054 |
aming | -0.046 |
pr | -0.046 |
we | -0.044 |
amed | -0.043 |
Token | These |
Token ID | 2312 |
Feature activation | -2.00e+01 |
Pos logit contributions | |
attitude | +0.054 |
choice | +0.053 |
ses | +0.053 |
acts | +0.053 |
ness | +0.050 |
Neg logit contributions | |
nowhere | -0.088 |
there | -0.078 |
we | -0.075 |
B | -0.074 |
THE | -0.074 |
Token | are |
Token ID | 389 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
This | +0.690 |
These | +0.653 |
ses | +0.633 |
Today | +0.631 |
Novel | +0.626 |
Neg logit contributions | |
nowhere | -1.628 |
aming | -1.449 |
pr | -1.411 |
in | -1.386 |
we | -1.376 |
Token | your |
Token ID | 534 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
This | +0.453 |
Novel | +0.436 |
These | +0.435 |
ses | +0.420 |
They | +0.395 |
Neg logit contributions | |
nowhere | -0.802 |
pr | -0.738 |
aming | -0.735 |
amed | -0.718 |
we | -0.708 |
Token | toys |
Token ID | 14958 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
These | +0.362 |
This | +0.357 |
Novel | +0.342 |
Today | +0.319 |
ses | +0.311 |
Neg logit contributions | |
nowhere | -0.413 |
aming | -0.329 |
pr | -0.329 |
we | -0.318 |
amed | -0.310 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
nowhere | +0.214 |
aming | +0.178 |
pr | +0.171 |
we | +0.166 |
in | +0.164 |
Neg logit contributions | |
These | -0.197 |
This | -0.192 |
ses | -0.184 |
Novel | -0.184 |
Today | -0.179 |
Token | We |
Token ID | 775 |
Feature activation | -7.83e+00 |
Pos logit contributions | |
ses | +0.053 |
attitude | +0.053 |
acts | +0.051 |
ness | +0.051 |
choice | +0.047 |
Neg logit contributions | |
nowhere | -0.096 |
we | -0.084 |
B | -0.083 |
there | -0.083 |
aming | -0.082 |
Token | " |
Token ID | 366 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
These | +0.286 |
This | +0.282 |
Novel | +0.272 |
ses | +0.250 |
Today | +0.241 |
Neg logit contributions | |
nowhere | -0.580 |
aming | -0.511 |
pr | -0.507 |
amed | -0.490 |
we | -0.484 |
Token | You |
Token ID | 1639 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
These | +0.139 |
This | +0.138 |
Novel | +0.135 |
ses | +0.129 |
Today | +0.127 |
Neg logit contributions | |
nowhere | -0.093 |
aming | -0.074 |
pr | -0.073 |
amed | -0.068 |
we | -0.067 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
nowhere | +0.337 |
pr | +0.299 |
there | +0.293 |
aming | +0.288 |
amed | +0.282 |
Neg logit contributions | |
ses | -0.155 |
These | -0.155 |
This | -0.153 |
Novel | -0.145 |
Today | -0.141 |
Token | silly |
Token ID | 14397 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
These | +0.722 |
This | +0.711 |
Novel | +0.699 |
ses | +0.671 |
Today | +0.656 |
Neg logit contributions | |
nowhere | -0.585 |
aming | -0.475 |
pr | -0.468 |
amed | -0.443 |
we | -0.431 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
This | +0.197 |
These | +0.197 |
ses | +0.189 |
Novel | +0.181 |
Today | +0.175 |
Neg logit contributions | |
nowhere | -0.191 |
we | -0.158 |
aming | -0.155 |
there | -0.155 |
pr | -0.154 |
Token | These |
Token ID | 2312 |
Feature activation | -2.00e+01 |
Pos logit contributions | |
taste | +0.058 |
ses | +0.058 |
gasp | +0.056 |
rip | +0.056 |
attitude | +0.056 |
Neg logit contributions | |
nowhere | -0.082 |
we | -0.070 |
there | -0.070 |
B | -0.069 |
P | -0.065 |
Token | are |
Token ID | 389 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
This | +0.759 |
ses | +0.734 |
These | +0.729 |
Today | +0.698 |
Novel | +0.680 |
Neg logit contributions | |
nowhere | -1.569 |
aming | -1.356 |
pr | -1.352 |
in | -1.310 |
we | -1.306 |
Token | not |
Token ID | 407 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
These | +0.564 |
This | +0.560 |
Novel | +0.545 |
ses | +0.515 |
Today | +0.489 |
Neg logit contributions | |
nowhere | -0.730 |
aming | -0.634 |
pr | -0.626 |
amed | -0.602 |
we | -0.599 |
Token | special |
Token ID | 2041 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
nowhere | +0.144 |
aming | +0.120 |
pr | +0.120 |
amed | +0.114 |
we | +0.112 |
Neg logit contributions | |
These | -0.132 |
This | -0.129 |
Novel | -0.127 |
ses | -0.121 |
Today | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ses | +0.087 |
These | +0.086 |
This | +0.086 |
Novel | +0.082 |
Today | +0.079 |
Neg logit contributions | |
nowhere | -0.079 |
there | -0.062 |
pr | -0.060 |
we | -0.059 |
in | -0.058 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
ses | +0.051 |
attitude | +0.047 |
stare | +0.045 |
ness | +0.045 |
taste | +0.044 |
Neg logit contributions | |
nowhere | -0.088 |
we | -0.083 |
B | -0.080 |
there | -0.079 |
together | -0.079 |
Token | " |
Token ID | 366 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
These | +0.303 |
This | +0.295 |
Novel | +0.289 |
ses | +0.272 |
Today | +0.258 |
Neg logit contributions | |
nowhere | -0.560 |
aming | -0.484 |
pr | -0.483 |
amed | -0.465 |
we | -0.464 |
Token | Look |
Token ID | 8567 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
These | +0.135 |
This | +0.133 |
Novel | +0.132 |
ses | +0.127 |
Today | +0.123 |
Neg logit contributions | |
nowhere | -0.094 |
aming | -0.075 |
pr | -0.074 |
amed | -0.070 |
we | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
nowhere | +0.354 |
aming | +0.308 |
pr | +0.304 |
amed | +0.294 |
we | +0.292 |
Neg logit contributions | |
These | -0.213 |
This | -0.211 |
Novel | -0.204 |
ses | -0.188 |
Today | -0.183 |
Token | Max |
Token ID | 5436 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
These | +0.343 |
ses | +0.329 |
This | +0.325 |
Novel | +0.317 |
acts | +0.303 |
Neg logit contributions | |
nowhere | -0.524 |
pr | -0.428 |
there | -0.416 |
aming | -0.407 |
THE | -0.395 |
Token | ! |
Token ID | 0 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
These | +0.019 |
ses | +0.018 |
This | +0.017 |
Today | +0.017 |
attitude | +0.017 |
Neg logit contributions | |
nowhere | -0.014 |
there | -0.011 |
aming | -0.011 |
ep | -0.011 |
in | -0.011 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
attitude | +0.059 |
ses | +0.058 |
acts | +0.055 |
choice | +0.053 |
offer | +0.052 |
Neg logit contributions | |
nowhere | -0.081 |
there | -0.077 |
B | -0.074 |
P | -0.073 |
Peter | -0.071 |
Token | are |
Token ID | 389 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
ses | +0.837 |
Today | +0.754 |
Novel | +0.733 |
This | +0.722 |
attitude | +0.691 |
Neg logit contributions | |
nowhere | -1.322 |
amed | -1.284 |
aming | -1.274 |
pr | -1.272 |
we | -1.266 |
Token | my |
Token ID | 616 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
These | +0.599 |
This | +0.595 |
Novel | +0.576 |
ses | +0.540 |
Today | +0.523 |
Neg logit contributions | |
nowhere | -0.702 |
aming | -0.595 |
pr | -0.591 |
we | -0.562 |
amed | -0.561 |
Token | past |
Token ID | 1613 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
These | +0.342 |
This | +0.341 |
Novel | +0.338 |
ses | +0.330 |
Today | +0.318 |
Neg logit contributions | |
nowhere | -0.340 |
pr | -0.283 |
aming | -0.281 |
amed | -0.276 |
we | -0.272 |
Token | els |
Token ID | 1424 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ses | +0.217 |
These | +0.212 |
Novel | +0.212 |
This | +0.210 |
attitude | +0.200 |
Neg logit contributions | |
nowhere | -0.174 |
pr | -0.146 |
we | -0.142 |
aming | -0.141 |
amed | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
nowhere | +0.079 |
pr | +0.067 |
aming | +0.067 |
we | +0.064 |
amed | +0.063 |
Neg logit contributions | |
These | -0.083 |
Novel | -0.081 |
This | -0.080 |
ses | -0.080 |
acts | -0.076 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
This | +0.698 |
These | +0.678 |
Novel | +0.677 |
ses | +0.665 |
Today | +0.654 |
Neg logit contributions | |
nowhere | -1.549 |
aming | -1.397 |
pr | -1.368 |
we | -1.365 |
amed | -1.350 |
Token | not |
Token ID | 407 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
This | +0.591 |
These | +0.589 |
Novel | +0.569 |
ses | +0.552 |
thank | +0.513 |
Neg logit contributions | |
nowhere | -0.678 |
aming | -0.596 |
pr | -0.580 |
we | -0.563 |
amed | -0.562 |
Token | your |
Token ID | 534 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
nowhere | +0.156 |
aming | +0.133 |
pr | +0.131 |
amed | +0.126 |
we | +0.125 |
Neg logit contributions | |
These | -0.126 |
This | -0.126 |
Novel | -0.123 |
ses | -0.116 |
Today | -0.111 |
Token | pictures |
Token ID | 5986 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
These | +0.310 |
This | +0.300 |
Novel | +0.294 |
Today | +0.268 |
ses | +0.266 |
Neg logit contributions | |
nowhere | -0.451 |
aming | -0.365 |
pr | -0.363 |
we | -0.363 |
amed | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
These | +0.111 |
This | +0.107 |
ses | +0.106 |
Novel | +0.104 |
Today | +0.099 |
Neg logit contributions | |
nowhere | -0.123 |
aming | -0.102 |
pr | -0.102 |
we | -0.099 |
in | -0.096 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
attitude | +0.045 |
ses | +0.045 |
acts | +0.042 |
choice | +0.042 |
stare | +0.041 |
Neg logit contributions | |
we | -0.089 |
nowhere | -0.088 |
aming | -0.084 |
together | -0.083 |
We | -0.083 |
Token | are |
Token ID | 389 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
This | +0.674 |
Novel | +0.655 |
ses | +0.655 |
These | +0.655 |
Today | +0.636 |
Neg logit contributions | |
nowhere | -1.550 |
aming | -1.404 |
pr | -1.380 |
we | -1.377 |
amed | -1.364 |
Token | my |
Token ID | 616 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
These | +0.603 |
This | +0.601 |
Novel | +0.584 |
ses | +0.560 |
Today | +0.528 |
Neg logit contributions | |
nowhere | -0.680 |
aming | -0.587 |
pr | -0.576 |
amed | -0.556 |
we | -0.548 |
Token | pictures |
Token ID | 5986 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
These | +0.299 |
This | +0.294 |
Novel | +0.285 |
Today | +0.263 |
ses | +0.263 |
Neg logit contributions | |
nowhere | -0.416 |
aming | -0.345 |
pr | -0.340 |
we | -0.337 |
amed | -0.331 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
These | +0.110 |
This | +0.106 |
Novel | +0.103 |
ses | +0.103 |
Today | +0.098 |
Neg logit contributions | |
nowhere | -0.131 |
aming | -0.110 |
pr | -0.109 |
we | -0.105 |
amed | -0.103 |
Token | I |
Token ID | 314 |
Feature activation | -6.92e+00 |
Pos logit contributions | |
ses | +0.047 |
attitude | +0.047 |
acts | +0.044 |
ness | +0.043 |
stare | +0.042 |
Neg logit contributions | |
nowhere | -0.098 |
we | -0.094 |
aming | -0.090 |
We | -0.088 |
P | -0.088 |
Token | 't |
Token ID | 470 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
These | +0.063 |
ses | +0.062 |
Novel | +0.061 |
This | +0.061 |
acts | +0.058 |
Neg logit contributions | |
nowhere | -0.075 |
aming | -0.063 |
pr | -0.063 |
we | -0.060 |
amed | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ses | +0.200 |
These | +0.193 |
This | +0.182 |
Novel | +0.179 |
acts | +0.163 |
Neg logit contributions | |
nowhere | -0.267 |
pr | -0.232 |
there | -0.220 |
aming | -0.219 |
in | -0.217 |
Token | Go |
Token ID | 1514 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
ses | +0.057 |
taste | +0.055 |
acts | +0.054 |
offer | +0.054 |
choice | +0.053 |
Neg logit contributions | |
nowhere | -0.076 |
we | -0.067 |
there | -0.066 |
B | -0.062 |
who | -0.060 |
Token | away |
Token ID | 1497 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
This | +0.401 |
These | +0.399 |
Novel | +0.392 |
ses | +0.369 |
Today | +0.368 |
Neg logit contributions | |
nowhere | -0.292 |
aming | -0.236 |
pr | -0.233 |
we | -0.218 |
amed | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
nowhere | +0.401 |
aming | +0.328 |
pr | +0.326 |
we | +0.322 |
in | +0.318 |
Neg logit contributions | |
These | -0.354 |
This | -0.340 |
ses | -0.332 |
Novel | -0.323 |
Today | -0.308 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
ses | +0.055 |
taste | +0.054 |
attitude | +0.052 |
offer | +0.052 |
choice | +0.052 |
Neg logit contributions | |
nowhere | -0.086 |
we | -0.072 |
B | -0.072 |
there | -0.069 |
We | -0.066 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ses | +0.761 |
This | +0.743 |
Today | +0.703 |
Novel | +0.700 |
These | +0.694 |
Neg logit contributions | |
nowhere | -1.521 |
there | -1.332 |
pr | -1.321 |
in | -1.319 |
aming | -1.312 |
Token | my |
Token ID | 616 |
Feature activation | -6.05e+00 |
Pos logit contributions | |
This | +0.485 |
These | +0.483 |
Novel | +0.462 |
ses | +0.437 |
They | +0.403 |
Neg logit contributions | |
nowhere | -0.793 |
aming | -0.715 |
pr | -0.702 |
amed | -0.683 |
we | -0.669 |
Token | toys |
Token ID | 14958 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
This | +0.392 |
These | +0.391 |
Novel | +0.376 |
Today | +0.355 |
ses | +0.353 |
Neg logit contributions | |
nowhere | -0.306 |
pr | -0.220 |
there | -0.218 |
we | -0.217 |
aming | -0.213 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
nowhere | +0.216 |
aming | +0.176 |
pr | +0.173 |
we | +0.166 |
in | +0.165 |
Neg logit contributions | |
These | -0.198 |
This | -0.192 |
Novel | -0.186 |
ses | -0.183 |
Today | -0.179 |
Token | You |
Token ID | 921 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
ses | +0.054 |
attitude | +0.052 |
acts | +0.052 |
Novel | +0.049 |
taste | +0.048 |
Neg logit contributions | |
nowhere | -0.095 |
B | -0.081 |
we | -0.081 |
there | -0.078 |
aming | -0.078 |
Token | shouted |
Token ID | 17293 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
nowhere | +0.100 |
aming | +0.088 |
pr | +0.087 |
amed | +0.081 |
THE | +0.079 |
Neg logit contributions | |
This | -0.104 |
These | -0.103 |
Novel | -0.100 |
ses | -0.097 |
They | -0.094 |
Token | , |
Token ID | 11 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
nowhere | +0.253 |
pr | +0.211 |
aming | +0.206 |
we | +0.202 |
amed | +0.197 |
Neg logit contributions | |
These | -0.256 |
Novel | -0.249 |
ses | -0.246 |
This | -0.242 |
acts | -0.241 |
Token | " |
Token ID | 366 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
These | +0.310 |
This | +0.300 |
Novel | +0.298 |
ses | +0.275 |
Today | +0.265 |
Neg logit contributions | |
nowhere | -0.554 |
aming | -0.475 |
pr | -0.474 |
we | -0.457 |
amed | -0.457 |
Token | No |
Token ID | 2949 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
These | +0.093 |
This | +0.091 |
Novel | +0.085 |
Today | +0.080 |
But | +0.075 |
Neg logit contributions | |
nowhere | -0.132 |
pr | -0.112 |
aming | -0.109 |
amed | -0.107 |
bled | -0.103 |
Token | ! |
Token ID | 0 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
These | +0.219 |
Novel | +0.216 |
ses | +0.214 |
This | +0.210 |
acts | +0.195 |
Neg logit contributions | |
nowhere | -0.191 |
pr | -0.154 |
ths | -0.149 |
aming | -0.141 |
there | -0.141 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
offer | +0.053 |
acts | +0.052 |
Novel | +0.050 |
ses | +0.050 |
attitude | +0.050 |
Neg logit contributions | |
nowhere | -0.089 |
we | -0.078 |
there | -0.073 |
it | -0.072 |
B | -0.071 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ses | +0.919 |
Novel | +0.906 |
This | +0.883 |
These | +0.874 |
Today | +0.849 |
Neg logit contributions | |
nowhere | -1.366 |
in | -1.192 |
pr | -1.190 |
aming | -1.184 |
ep | -1.168 |
Token | mine |
Token ID | 6164 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
These | +0.564 |
This | +0.559 |
Novel | +0.540 |
ses | +0.513 |
Today | +0.490 |
Neg logit contributions | |
nowhere | -0.727 |
aming | -0.627 |
pr | -0.619 |
amed | -0.595 |
we | -0.590 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
nowhere | +0.004 |
aming | +0.004 |
pr | +0.004 |
we | +0.003 |
amed | +0.003 |
Neg logit contributions | |
These | -0.003 |
This | -0.003 |
Novel | -0.003 |
ses | -0.003 |
Today | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
These | +0.093 |
Novel | +0.087 |
ses | +0.085 |
This | +0.081 |
acts | +0.079 |
Neg logit contributions | |
nowhere | -0.287 |
we | -0.250 |
pr | -0.249 |
aming | -0.246 |
amed | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
nowhere | +0.289 |
aming | +0.256 |
pr | +0.250 |
amed | +0.238 |
lling | +0.232 |
Neg logit contributions | |
This | -0.215 |
These | -0.207 |
Novel | -0.197 |
Today | -0.187 |
They | -0.181 |
Token | plants |
Token ID | 6134 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
These | +0.248 |
This | +0.246 |
Novel | +0.239 |
ses | +0.226 |
Today | +0.220 |
Neg logit contributions | |
nowhere | -0.303 |
aming | -0.257 |
pr | -0.254 |
amed | -0.244 |
we | -0.240 |
Token | to |
Token ID | 284 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
This | +0.124 |
These | +0.124 |
Novel | +0.119 |
ses | +0.112 |
Today | +0.111 |
Neg logit contributions | |
nowhere | -0.123 |
aming | -0.102 |
pr | -0.100 |
amed | -0.097 |
we | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
These | +0.055 |
Novel | +0.054 |
This | +0.054 |
ses | +0.052 |
Today | +0.050 |
Neg logit contributions | |
nowhere | -0.059 |
aming | -0.048 |
pr | -0.048 |
we | -0.045 |
amed | -0.045 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
These | +0.126 |
This | +0.123 |
Novel | +0.120 |
ses | +0.114 |
Today | +0.109 |
Neg logit contributions | |
nowhere | -0.182 |
pr | -0.157 |
aming | -0.156 |
amed | -0.149 |
we | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
nowhere | +0.119 |
aming | +0.102 |
pr | +0.101 |
amed | +0.097 |
we | +0.096 |
Neg logit contributions | |
These | -0.090 |
This | -0.089 |
Novel | -0.087 |
ses | -0.082 |
Today | -0.079 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
ses | +0.053 |
Novel | +0.053 |
acts | +0.050 |
These | +0.050 |
This | +0.047 |
Neg logit contributions | |
nowhere | -0.106 |
aming | -0.089 |
pr | -0.086 |
amed | -0.085 |
we | -0.085 |
Token | plants |
Token ID | 6134 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
These | +1.022 |
This | +0.982 |
Novel | +0.956 |
acts | +0.903 |
ses | +0.891 |
Neg logit contributions | |
nowhere | -1.350 |
pr | -1.140 |
aming | -1.139 |
amed | -1.091 |
we | -1.066 |
Token | were |
Token ID | 547 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
These | +0.120 |
This | +0.119 |
Novel | +0.116 |
ses | +0.108 |
acts | +0.107 |
Neg logit contributions | |
nowhere | -0.116 |
aming | -0.096 |
pr | -0.095 |
amed | -0.091 |
we | -0.089 |
Token | called |
Token ID | 1444 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
nowhere | +0.032 |
pr | +0.027 |
we | +0.026 |
aming | +0.025 |
in | +0.024 |
Neg logit contributions | |
This | -0.032 |
These | -0.032 |
Novel | -0.030 |
They | -0.029 |
ses | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
nowhere | +0.468 |
aming | +0.394 |
pr | +0.391 |
amed | +0.371 |
we | +0.370 |
Neg logit contributions | |
These | -0.378 |
Novel | -0.375 |
This | -0.366 |
ses | -0.358 |
Today | -0.345 |
Token | spring |
Token ID | 16469 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
These | +0.118 |
This | +0.115 |
Novel | +0.105 |
Today | +0.104 |
They | +0.100 |
Neg logit contributions | |
nowhere | -0.104 |
aming | -0.080 |
amed | -0.076 |
bled | -0.073 |
pr | -0.073 |
Token | did |
Token ID | 750 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
nowhere | +0.538 |
pr | +0.473 |
aming | +0.468 |
amed | +0.451 |
in | +0.444 |
Neg logit contributions | |
Novel | -0.239 |
These | -0.237 |
This | -0.230 |
ses | -0.219 |
Today | -0.216 |
Token | a |
Token ID | 257 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
nowhere | +0.193 |
pr | +0.142 |
aming | +0.141 |
we | +0.127 |
there | +0.127 |
Neg logit contributions | |
These | -0.321 |
Novel | -0.306 |
ses | -0.304 |
This | -0.303 |
Today | -0.295 |
Token | great |
Token ID | 1049 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
nowhere | +0.051 |
pr | +0.042 |
aming | +0.041 |
in | +0.039 |
dd | +0.037 |
Neg logit contributions | |
These | -0.059 |
This | -0.057 |
Novel | -0.057 |
ses | -0.055 |
Today | -0.052 |
Token | job |
Token ID | 1693 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
These | +0.167 |
Novel | +0.167 |
ses | +0.157 |
hy | +0.156 |
acts | +0.154 |
Neg logit contributions | |
nowhere | -0.183 |
pr | -0.167 |
in | -0.163 |
together | -0.160 |
dd | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
These | +0.284 |
This | +0.278 |
Novel | +0.276 |
ses | +0.263 |
Today | +0.251 |
Neg logit contributions | |
nowhere | -0.379 |
aming | -0.322 |
pr | -0.319 |
we | -0.311 |
amed | -0.297 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
ses | +0.054 |
attitude | +0.053 |
backs | +0.052 |
taste | +0.052 |
offer | +0.051 |
Neg logit contributions | |
nowhere | -0.082 |
aming | -0.068 |
there | -0.068 |
B | -0.068 |
we | -0.067 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
This | +1.011 |
These | +0.994 |
Novel | +0.977 |
Today | +0.940 |
ses | +0.919 |
Neg logit contributions | |
nowhere | -1.333 |
aming | -1.150 |
in | -1.114 |
pr | -1.100 |
we | -1.087 |
Token | different |
Token ID | 1180 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
This | +0.567 |
These | +0.560 |
Novel | +0.539 |
ses | +0.537 |
thank | +0.505 |
Neg logit contributions | |
nowhere | -0.695 |
aming | -0.617 |
pr | -0.611 |
amed | -0.594 |
we | -0.582 |
Token | kinds |
Token ID | 6982 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
This | +0.186 |
These | +0.185 |
Novel | +0.179 |
ses | +0.176 |
Today | +0.171 |
Neg logit contributions | |
nowhere | -0.177 |
aming | -0.148 |
in | -0.146 |
we | -0.145 |
pr | -0.140 |
Token | of |
Token ID | 286 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
These | +0.534 |
This | +0.529 |
Novel | +0.517 |
ses | +0.508 |
Today | +0.497 |
Neg logit contributions | |
nowhere | -0.364 |
aming | -0.286 |
pr | -0.273 |
we | -0.262 |
in | -0.258 |
Token | fish |
Token ID | 5916 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
nowhere | +0.040 |
aming | +0.034 |
pr | +0.033 |
we | +0.032 |
in | +0.032 |
Neg logit contributions | |
These | -0.036 |
This | -0.036 |
Novel | -0.035 |
Today | -0.033 |
ses | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
These | +0.174 |
This | +0.170 |
Novel | +0.166 |
Today | +0.156 |
ses | +0.154 |
Neg logit contributions | |
nowhere | -0.444 |
pr | -0.394 |
aming | -0.384 |
amed | -0.372 |
in | -0.367 |
Token | ruining |
Token ID | 39842 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
This | +0.657 |
These | +0.654 |
Novel | +0.641 |
ses | +0.620 |
acts | +0.576 |
Neg logit contributions | |
nowhere | -0.598 |
pr | -0.510 |
aming | -0.509 |
we | -0.489 |
amed | -0.483 |
Token | my |
Token ID | 616 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
This | +0.071 |
These | +0.071 |
Novel | +0.069 |
ses | +0.063 |
Today | +0.060 |
Neg logit contributions | |
nowhere | -0.108 |
aming | -0.095 |
pr | -0.095 |
amed | -0.092 |
we | -0.089 |
Token | pictures |
Token ID | 5986 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
These | +0.285 |
This | +0.277 |
Novel | +0.271 |
ses | +0.251 |
Today | +0.246 |
Neg logit contributions | |
nowhere | -0.427 |
aming | -0.357 |
pr | -0.352 |
we | -0.343 |
amed | -0.343 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
These | +0.103 |
This | +0.100 |
Novel | +0.098 |
ses | +0.095 |
Today | +0.090 |
Neg logit contributions | |
nowhere | -0.129 |
aming | -0.109 |
pr | -0.109 |
we | -0.103 |
amed | -0.103 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
attitude | +0.054 |
choice | +0.053 |
offer | +0.051 |
ses | +0.050 |
acts | +0.049 |
Neg logit contributions | |
nowhere | -0.081 |
we | -0.076 |
aming | -0.072 |
P | -0.072 |
there | -0.071 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
This | +0.698 |
These | +0.678 |
Novel | +0.677 |
ses | +0.665 |
Today | +0.654 |
Neg logit contributions | |
nowhere | -1.549 |
aming | -1.397 |
pr | -1.368 |
we | -1.365 |
amed | -1.350 |
Token | not |
Token ID | 407 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
This | +0.591 |
These | +0.589 |
Novel | +0.569 |
ses | +0.552 |
thank | +0.513 |
Neg logit contributions | |
nowhere | -0.678 |
aming | -0.596 |
pr | -0.580 |
we | -0.563 |
amed | -0.562 |
Token | your |
Token ID | 534 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
nowhere | +0.156 |
aming | +0.133 |
pr | +0.131 |
amed | +0.126 |
we | +0.125 |
Neg logit contributions | |
These | -0.126 |
This | -0.126 |
Novel | -0.123 |
ses | -0.116 |
Today | -0.111 |
Token | pictures |
Token ID | 5986 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
These | +0.310 |
This | +0.300 |
Novel | +0.294 |
Today | +0.268 |
ses | +0.266 |
Neg logit contributions | |
nowhere | -0.451 |
aming | -0.365 |
pr | -0.363 |
we | -0.363 |
amed | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
These | +0.111 |
This | +0.107 |
ses | +0.106 |
Novel | +0.104 |
Today | +0.099 |
Neg logit contributions | |
nowhere | -0.123 |
aming | -0.102 |
pr | -0.102 |
we | -0.099 |
in | -0.096 |
Token | said |
Token ID | 531 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
nowhere | +0.100 |
aming | +0.084 |
pr | +0.083 |
amed | +0.078 |
we | +0.076 |
Neg logit contributions | |
These | -0.111 |
This | -0.111 |
Novel | -0.108 |
ses | -0.103 |
acts | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
nowhere | +0.293 |
pr | +0.267 |
in | +0.255 |
there | +0.245 |
amed | +0.243 |
Neg logit contributions | |
ses | -0.242 |
These | -0.225 |
Novel | -0.224 |
acts | -0.215 |
Today | -0.213 |
Token | " |
Token ID | 366 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
These | +0.278 |
This | +0.277 |
Novel | +0.262 |
ses | +0.237 |
Today | +0.232 |
Neg logit contributions | |
nowhere | -0.585 |
aming | -0.518 |
pr | -0.512 |
amed | -0.495 |
we | -0.487 |
Token | Wow |
Token ID | 22017 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
These | +0.124 |
This | +0.122 |
Novel | +0.115 |
Today | +0.108 |
They | +0.108 |
Neg logit contributions | |
nowhere | -0.105 |
pr | -0.081 |
aming | -0.077 |
amed | -0.074 |
ths | -0.072 |
Token | ! |
Token ID | 0 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
nowhere | +0.390 |
pr | +0.358 |
aming | +0.339 |
there | +0.331 |
in | +0.328 |
Neg logit contributions | |
ses | -0.373 |
These | -0.372 |
Novel | -0.357 |
This | -0.356 |
acts | -0.350 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
ses | +0.050 |
attitude | +0.048 |
acts | +0.047 |
Novel | +0.045 |
backs | +0.045 |
Neg logit contributions | |
nowhere | -0.081 |
aming | -0.075 |
THE | -0.073 |
pr | -0.073 |
there | -0.073 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
Novel | +0.839 |
ses | +0.810 |
Today | +0.788 |
This | +0.771 |
These | +0.722 |
Neg logit contributions | |
nowhere | -1.358 |
aming | -1.282 |
in | -1.254 |
we | -1.242 |
pr | -1.236 |
Token | so |
Token ID | 523 |
Feature activation | +9.95e+00 |
Pos logit contributions | |
These | +0.700 |
This | +0.696 |
Novel | +0.676 |
ses | +0.642 |
Today | +0.627 |
Neg logit contributions | |
nowhere | -0.591 |
aming | -0.484 |
pr | -0.481 |
amed | -0.456 |
we | -0.450 |
Token | ooo |
Token ID | 34160 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
nowhere | +0.443 |
aming | +0.383 |
pr | +0.358 |
in | +0.353 |
we | +0.336 |
Neg logit contributions | |
ses | -0.692 |
Novel | -0.674 |
These | -0.650 |
This | -0.647 |
acts | -0.644 |
Token | spicy |
Token ID | 26880 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
nowhere | +0.211 |
pr | +0.188 |
aming | +0.188 |
we | +0.177 |
in | +0.176 |
Neg logit contributions | |
ses | -0.236 |
Novel | -0.234 |
These | -0.229 |
This | -0.224 |
acts | -0.220 |
Token | ". |
Token ID | 1911 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
These | +0.242 |
This | +0.237 |
Novel | +0.233 |
ses | +0.233 |
Today | +0.218 |
Neg logit contributions | |
nowhere | -0.281 |
pr | -0.243 |
aming | -0.241 |
we | -0.241 |
in | -0.230 |
Token | What |
Token ID | 2061 |
Feature activation | +9.43e+00 |
Pos logit contributions | |
These | +0.125 |
This | +0.124 |
Novel | +0.122 |
They | +0.111 |
Today | +0.111 |
Neg logit contributions | |
nowhere | -0.107 |
pr | -0.092 |
amed | -0.088 |
aming | -0.088 |
exactly | -0.083 |
Token | have |
Token ID | 423 |
Feature activation | -8.44e+00 |
Pos logit contributions | |
nowhere | +0.761 |
pr | +0.656 |
aming | +0.646 |
in | +0.632 |
we | +0.628 |
Neg logit contributions | |
These | -0.340 |
This | -0.330 |
Novel | -0.330 |
ses | -0.325 |
Today | -0.309 |
Token | you |
Token ID | 345 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
This | +0.440 |
These | +0.437 |
Novel | +0.417 |
ses | +0.381 |
acts | +0.371 |
Neg logit contributions | |
nowhere | -0.549 |
aming | -0.493 |
pr | -0.484 |
amed | -0.477 |
we | -0.448 |
Token | done |
Token ID | 1760 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
nowhere | +0.170 |
aming | +0.138 |
pr | +0.137 |
amed | +0.129 |
we | +0.128 |
Neg logit contributions | |
These | -0.214 |
This | -0.212 |
Novel | -0.208 |
ses | -0.199 |
Today | -0.194 |
Token | ? |
Token ID | 30 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
nowhere | +0.510 |
aming | +0.435 |
pr | +0.429 |
we | +0.410 |
amed | +0.402 |
Neg logit contributions | |
These | -0.438 |
This | -0.424 |
Novel | -0.417 |
ses | -0.414 |
Today | -0.384 |
Token | These |
Token ID | 2312 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
attitude | +0.051 |
Novel | +0.050 |
ses | +0.050 |
ness | +0.049 |
offer | +0.048 |
Neg logit contributions | |
nowhere | -0.078 |
we | -0.065 |
there | -0.065 |
aming | -0.063 |
pr | -0.062 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
This | +0.724 |
These | +0.708 |
Novel | +0.690 |
Today | +0.674 |
ses | +0.660 |
Neg logit contributions | |
nowhere | -1.591 |
in | -1.388 |
pr | -1.379 |
we | -1.376 |
aming | -1.364 |
Token | not |
Token ID | 407 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
These | +0.553 |
This | +0.552 |
Novel | +0.531 |
ses | +0.514 |
Today | +0.473 |
Neg logit contributions | |
nowhere | -0.722 |
aming | -0.631 |
pr | -0.623 |
amed | -0.600 |
we | -0.590 |
Token | toys |
Token ID | 14958 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
nowhere | +0.174 |
aming | +0.153 |
pr | +0.151 |
amed | +0.145 |
we | +0.145 |
Neg logit contributions | |
This | -0.114 |
These | -0.111 |
Novel | -0.110 |
ses | -0.103 |
They | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
nowhere | +0.226 |
aming | +0.182 |
pr | +0.177 |
in | +0.174 |
we | +0.173 |
Neg logit contributions | |
These | -0.202 |
This | -0.195 |
ses | -0.193 |
Novel | -0.192 |
Today | -0.187 |
Token | These |
Token ID | 2312 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
attitude | +0.043 |
offer | +0.042 |
choice | +0.041 |
thank | +0.040 |
ses | +0.040 |
Neg logit contributions | |
nowhere | -0.088 |
we | -0.082 |
P | -0.080 |
there | -0.079 |
B | -0.078 |
Token | " |
Token ID | 366 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
These | +0.272 |
This | +0.272 |
Novel | +0.258 |
ses | +0.236 |
Today | +0.227 |
Neg logit contributions | |
nowhere | -0.583 |
aming | -0.518 |
pr | -0.514 |
amed | -0.495 |
we | -0.490 |
Token | No |
Token ID | 2949 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
These | +0.108 |
This | +0.106 |
Novel | +0.101 |
ses | +0.094 |
Today | +0.094 |
Neg logit contributions | |
nowhere | -0.113 |
aming | -0.096 |
pr | -0.095 |
amed | -0.090 |
we | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
ses | +0.207 |
These | +0.202 |
This | +0.200 |
Novel | +0.199 |
hy | +0.186 |
Neg logit contributions | |
nowhere | -0.167 |
exactly | -0.146 |
there | -0.142 |
soon | -0.139 |
pr | -0.136 |
Token | Tom |
Token ID | 4186 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
These | +0.344 |
This | +0.336 |
Novel | +0.330 |
ses | +0.321 |
Today | +0.311 |
Neg logit contributions | |
nowhere | -0.510 |
pr | -0.420 |
aming | -0.419 |
we | -0.404 |
amed | -0.390 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
These | +0.193 |
ses | +0.183 |
This | +0.182 |
Novel | +0.179 |
Today | +0.174 |
Neg logit contributions | |
nowhere | -0.189 |
aming | -0.153 |
pr | -0.153 |
in | -0.150 |
we | -0.149 |
Token | These |
Token ID | 2312 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
Novel | +0.043 |
ses | +0.042 |
offer | +0.042 |
acts | +0.042 |
attitude | +0.040 |
Neg logit contributions | |
nowhere | -0.096 |
we | -0.086 |
there | -0.083 |
together | -0.080 |
amed | -0.078 |
Token | are |
Token ID | 389 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ses | +0.691 |
This | +0.648 |
Today | +0.616 |
Novel | +0.614 |
These | +0.610 |
Neg logit contributions | |
nowhere | -1.575 |
aming | -1.445 |
we | -1.432 |
pr | -1.429 |
in | -1.427 |
Token | my |
Token ID | 616 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
These | +0.542 |
This | +0.536 |
Novel | +0.521 |
ses | +0.492 |
Today | +0.470 |
Neg logit contributions | |
nowhere | -0.742 |
aming | -0.642 |
pr | -0.635 |
amed | -0.612 |
we | -0.604 |
Token | designs |
Token ID | 9824 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
These | +0.316 |
This | +0.313 |
Novel | +0.301 |
ses | +0.293 |
Today | +0.285 |
Neg logit contributions | |
nowhere | -0.369 |
we | -0.305 |
aming | -0.302 |
pr | -0.294 |
amed | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
These | +0.355 |
This | +0.344 |
Novel | +0.335 |
ses | +0.327 |
Today | +0.317 |
Neg logit contributions | |
nowhere | -0.403 |
aming | -0.339 |
pr | -0.335 |
we | -0.320 |
amed | -0.319 |
Token | I |
Token ID | 314 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
ses | +0.045 |
attitude | +0.043 |
acts | +0.043 |
Novel | +0.041 |
offer | +0.041 |
Neg logit contributions | |
nowhere | -0.092 |
we | -0.083 |
there | -0.079 |
together | -0.079 |
B | -0.078 |
Token | a |
Token ID | 257 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
This | +0.051 |
These | +0.051 |
Novel | +0.050 |
ses | +0.046 |
Today | +0.045 |
Neg logit contributions | |
nowhere | -0.051 |
aming | -0.046 |
amed | -0.045 |
pr | -0.045 |
we | -0.042 |
Token | long |
Token ID | 890 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
nowhere | +0.060 |
aming | +0.059 |
amed | +0.059 |
pr | +0.055 |
we | +0.053 |
Neg logit contributions | |
These | -0.052 |
This | -0.051 |
Novel | -0.049 |
Today | -0.046 |
thank | -0.046 |
Token | time |
Token ID | 640 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
Novel | +0.362 |
This | +0.360 |
These | +0.359 |
Today | +0.337 |
attitude | +0.333 |
Neg logit contributions | |
nowhere | -0.385 |
aming | -0.377 |
pr | -0.368 |
amed | -0.363 |
we | -0.354 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
nowhere | +0.565 |
aming | +0.522 |
amed | +0.514 |
pr | +0.509 |
we | +0.485 |
Neg logit contributions | |
This | -0.298 |
These | -0.296 |
Novel | -0.276 |
Today | -0.259 |
They | -0.241 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
These | +0.068 |
Novel | +0.067 |
ses | +0.066 |
acts | +0.065 |
This | +0.064 |
Neg logit contributions | |
nowhere | -0.080 |
aming | -0.062 |
pr | -0.061 |
we | -0.060 |
amed | -0.060 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
nowhere | +0.851 |
pr | +0.794 |
aming | +0.772 |
ths | +0.749 |
amed | +0.740 |
Neg logit contributions | |
This | -0.649 |
These | -0.622 |
Novel | -0.609 |
Today | -0.565 |
They | -0.557 |
Token | upon |
Token ID | 2402 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
nowhere | +0.505 |
aming | +0.468 |
pr | +0.449 |
we | +0.436 |
amed | +0.433 |
Neg logit contributions | |
This | -0.799 |
These | -0.792 |
Novel | -0.767 |
Today | -0.759 |
They | -0.712 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
nowhere | +0.483 |
pr | +0.447 |
ths | +0.444 |
aming | +0.434 |
amed | +0.426 |
Neg logit contributions | |
This | -0.430 |
Novel | -0.414 |
These | -0.403 |
They | -0.375 |
Today | -0.375 |
Token | time |
Token ID | 640 |
Feature activation | +7.58e+00 |
Pos logit contributions | |
nowhere | +0.058 |
pr | +0.049 |
aming | +0.048 |
we | +0.047 |
amed | +0.047 |
Neg logit contributions | |
These | -0.064 |
This | -0.064 |
Novel | -0.062 |
Today | -0.059 |
ses | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
nowhere | +0.584 |
pr | +0.501 |
aming | +0.501 |
amed | +0.478 |
we | +0.475 |
Neg logit contributions | |
These | -0.311 |
This | -0.303 |
Novel | -0.300 |
ses | -0.285 |
acts | -0.267 |
Token | there |
Token ID | 612 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
This | +0.553 |
These | +0.531 |
Today | +0.524 |
The | +0.513 |
They | +0.510 |
Neg logit contributions | |
nowhere | -0.236 |
we | -0.231 |
aming | -0.222 |
ths | -0.220 |
pr | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +0.468 |
aming | +0.411 |
pr | +0.404 |
amed | +0.392 |
we | +0.376 |
Neg logit contributions | |
This | -0.440 |
These | -0.434 |
Novel | -0.426 |
ses | -0.398 |
Today | -0.394 |
Token | wondering |
Token ID | 11263 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
This | +0.416 |
These | +0.397 |
Novel | +0.394 |
ses | +0.386 |
But | +0.375 |
Neg logit contributions | |
nowhere | -0.380 |
pr | -0.351 |
aming | -0.334 |
in | -0.331 |
amed | -0.318 |
Token | what |
Token ID | 644 |
Feature activation | +9.81e+00 |
Pos logit contributions | |
nowhere | +0.166 |
aming | +0.147 |
amed | +0.141 |
pr | +0.136 |
dd | +0.132 |
Neg logit contributions | |
This | -0.184 |
Novel | -0.179 |
These | -0.179 |
thank | -0.168 |
Today | -0.165 |
Token | else |
Token ID | 2073 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
nowhere | +0.527 |
aming | +0.503 |
amed | +0.477 |
pr | +0.472 |
pped | +0.431 |
Neg logit contributions | |
This | -0.613 |
These | -0.602 |
Novel | -0.569 |
acts | -0.556 |
They | -0.530 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
nowhere | +0.557 |
aming | +0.497 |
amed | +0.477 |
pr | +0.472 |
we | +0.430 |
Neg logit contributions | |
This | -0.713 |
These | -0.698 |
Novel | -0.680 |
acts | -0.645 |
Today | -0.626 |
Token | there |
Token ID | 612 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
nowhere | +0.152 |
sudden | +0.133 |
aming | +0.131 |
pr | +0.129 |
amed | +0.123 |
Neg logit contributions | |
This | -0.238 |
Novel | -0.226 |
These | -0.223 |
ses | -0.207 |
opens | -0.205 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
nowhere | +1.122 |
aming | +1.029 |
amed | +1.014 |
pr | +0.997 |
sudden | +0.979 |
Neg logit contributions | |
This | -0.653 |
These | -0.618 |
Today | -0.573 |
Novel | -0.573 |
Show | -0.511 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
Novel | +0.037 |
ses | +0.037 |
acts | +0.035 |
These | +0.035 |
attitude | +0.032 |
Neg logit contributions | |
nowhere | -0.078 |
amed | -0.065 |
pr | -0.065 |
aming | -0.065 |
we | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
These | +0.101 |
This | +0.099 |
Novel | +0.096 |
ses | +0.087 |
Today | +0.084 |
Neg logit contributions | |
nowhere | -0.215 |
aming | -0.190 |
pr | -0.188 |
amed | -0.182 |
we | -0.181 |
Token | she |
Token ID | 673 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
This | +0.336 |
These | +0.322 |
Novel | +0.307 |
The | +0.298 |
thank | +0.294 |
Neg logit contributions | |
nowhere | -0.445 |
aming | -0.429 |
amed | -0.407 |
we | -0.397 |
pr | -0.393 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
pr | +0.059 |
nowhere | +0.057 |
THE | +0.056 |
we | +0.055 |
prisingly | +0.053 |
Neg logit contributions | |
opens | -0.057 |
acts | -0.056 |
snaps | -0.054 |
try | -0.054 |
ses | -0.054 |
Token | collar |
Token ID | 19908 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
These | +0.159 |
This | +0.156 |
Novel | +0.151 |
ses | +0.142 |
Today | +0.138 |
Neg logit contributions | |
nowhere | -0.222 |
aming | -0.189 |
pr | -0.188 |
amed | -0.180 |
we | -0.179 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
This | +0.088 |
These | +0.084 |
Novel | +0.081 |
ses | +0.072 |
hy | +0.072 |
Neg logit contributions | |
nowhere | -0.149 |
aming | -0.133 |
pr | -0.132 |
amed | -0.127 |
we | -0.125 |
Token | The |
Token ID | 383 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
These | +0.065 |
ses | +0.063 |
Novel | +0.063 |
acts | +0.062 |
This | +0.061 |
Neg logit contributions | |
nowhere | -0.060 |
aming | -0.047 |
amed | -0.045 |
pr | -0.044 |
THE | -0.044 |
Token | end |
Token ID | 886 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
These | +0.746 |
This | +0.725 |
Novel | +0.703 |
ses | +0.695 |
Today | +0.666 |
Neg logit contributions | |
nowhere | -1.078 |
pr | -0.973 |
aming | -0.951 |
we | -0.945 |
amed | -0.914 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
nowhere | +0.056 |
aming | +0.048 |
pr | +0.047 |
amed | +0.046 |
we | +0.045 |
Neg logit contributions | |
This | -0.037 |
These | -0.037 |
Novel | -0.036 |
Today | -0.033 |
ses | -0.033 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
This | +0.060 |
These | +0.059 |
Novel | +0.056 |
Today | +0.053 |
ses | +0.051 |
Neg logit contributions | |
nowhere | -0.069 |
pr | -0.061 |
aming | -0.060 |
we | -0.057 |
amed | -0.057 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
nowhere | +0.858 |
pr | +0.792 |
aming | +0.771 |
ths | +0.745 |
amed | +0.734 |
Neg logit contributions | |
This | -0.668 |
These | -0.645 |
Novel | -0.620 |
Today | -0.587 |
They | -0.576 |
Token | upon |
Token ID | 2402 |
Feature activation | +8.09e+00 |
Pos logit contributions | |
nowhere | +0.534 |
aming | +0.492 |
pr | +0.473 |
we | +0.454 |
amed | +0.454 |
Neg logit contributions | |
This | -0.794 |
These | -0.789 |
Novel | -0.765 |
Today | -0.749 |
ses | -0.709 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
nowhere | +0.513 |
ths | +0.489 |
pr | +0.481 |
amed | +0.462 |
aming | +0.462 |
Neg logit contributions | |
This | -0.415 |
Novel | -0.390 |
These | -0.381 |
They | -0.364 |
Today | -0.359 |
Token | time |
Token ID | 640 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
nowhere | +0.071 |
we | +0.063 |
pr | +0.063 |
amed | +0.062 |
aming | +0.061 |
Neg logit contributions | |
This | -0.064 |
These | -0.063 |
Today | -0.062 |
Novel | -0.062 |
ses | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
nowhere | +0.601 |
aming | +0.520 |
pr | +0.520 |
amed | +0.498 |
we | +0.496 |
Neg logit contributions | |
These | -0.308 |
This | -0.301 |
Novel | -0.296 |
ses | -0.277 |
Today | -0.259 |
Token | there |
Token ID | 612 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
nowhere | +0.596 |
pr | +0.511 |
aming | +0.508 |
we | +0.484 |
amed | +0.484 |
Neg logit contributions | |
These | -0.320 |
This | -0.311 |
Novel | -0.310 |
ses | -0.294 |
acts | -0.275 |
Token | was |
Token ID | 373 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
nowhere | +0.702 |
pr | +0.579 |
aming | +0.579 |
amed | +0.542 |
we | +0.520 |
Neg logit contributions | |
These | -1.071 |
This | -1.071 |
Novel | -1.045 |
Today | -0.985 |
ses | -0.983 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
nowhere | +0.214 |
pr | +0.195 |
we | +0.190 |
ths | +0.189 |
amed | +0.178 |
Neg logit contributions | |
This | -0.182 |
These | -0.177 |
Novel | -0.169 |
Today | -0.165 |
They | -0.161 |
Token | young |
Token ID | 1862 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
nowhere | +0.077 |
aming | +0.064 |
pr | +0.064 |
amed | +0.060 |
we | +0.060 |
Neg logit contributions | |
These | -0.069 |
This | -0.069 |
Novel | -0.067 |
ses | -0.064 |
Today | -0.062 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
These | +0.097 |
This | +0.097 |
Novel | +0.091 |
ses | +0.090 |
Today | +0.088 |
Neg logit contributions | |
nowhere | -0.100 |
aming | -0.081 |
in | -0.080 |
pr | -0.078 |
we | -0.076 |
Token | who |
Token ID | 508 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
nowhere | +0.074 |
aming | +0.066 |
amed | +0.065 |
pr | +0.064 |
ths | +0.061 |
Neg logit contributions | |
This | -0.066 |
Novel | -0.063 |
These | -0.063 |
Today | -0.058 |
They | -0.057 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
nowhere | +0.590 |
aming | +0.473 |
pr | +0.462 |
amed | +0.442 |
we | +0.440 |
Neg logit contributions | |
These | -0.789 |
This | -0.768 |
Novel | -0.752 |
ses | -0.733 |
Today | -0.715 |
Token | to |
Token ID | 284 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
nowhere | +0.011 |
aming | +0.009 |
pr | +0.009 |
amed | +0.009 |
we | +0.009 |
Neg logit contributions | |
This | -0.009 |
These | -0.009 |
Novel | -0.009 |
ses | -0.008 |
acts | -0.008 |
Token | see |
Token ID | 766 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
These | +0.031 |
ses | +0.030 |
Today | +0.026 |
Novel | +0.026 |
This | +0.026 |
Neg logit contributions | |
nowhere | -0.033 |
pr | -0.028 |
there | -0.027 |
ep | -0.027 |
soon | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
This | +0.415 |
These | +0.406 |
Novel | +0.406 |
acts | +0.371 |
ses | +0.369 |
Neg logit contributions | |
nowhere | -0.445 |
aming | -0.391 |
pr | -0.376 |
amed | -0.375 |
we | -0.368 |
Token | world |
Token ID | 995 |
Feature activation | +5.80e+00 |
Pos logit contributions | |
These | +0.097 |
This | +0.096 |
Novel | +0.095 |
ses | +0.091 |
acts | +0.088 |
Neg logit contributions | |
nowhere | -0.155 |
pr | -0.140 |
aming | -0.139 |
amed | -0.135 |
dd | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
nowhere | +0.249 |
pr | +0.205 |
aming | +0.205 |
we | +0.195 |
amed | +0.195 |
Neg logit contributions | |
These | -0.225 |
This | -0.217 |
Novel | -0.211 |
ses | -0.210 |
Today | -0.195 |
Token |
|
Token ID | 198 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
These | +0.072 |
This | +0.070 |
Novel | +0.069 |
ses | +0.068 |
acts | +0.065 |
Neg logit contributions | |
nowhere | -0.069 |
aming | -0.055 |
pr | -0.055 |
amed | -0.052 |
we | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
nowhere | +0.277 |
aming | +0.237 |
pr | +0.236 |
amed | +0.224 |
we | +0.221 |
Neg logit contributions | |
This | -0.242 |
These | -0.241 |
Novel | -0.235 |
Today | -0.218 |
ses | -0.214 |
Token | " |
Token ID | 1 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
nowhere | +0.238 |
aming | +0.195 |
pr | +0.193 |
amed | +0.183 |
we | +0.181 |
Neg logit contributions | |
These | -0.285 |
This | -0.282 |
Novel | -0.277 |
ses | -0.266 |
Today | -0.258 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
nowhere | +0.050 |
aming | +0.043 |
amed | +0.040 |
pr | +0.040 |
lling | +0.039 |
Neg logit contributions | |
These | -0.043 |
This | -0.041 |
Novel | -0.038 |
They | -0.037 |
Show | -0.036 |
Token | later |
Token ID | 1568 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
nowhere | +0.329 |
pr | +0.273 |
aming | +0.270 |
we | +0.259 |
amed | +0.250 |
Neg logit contributions | |
These | -0.307 |
This | -0.302 |
Novel | -0.296 |
ses | -0.287 |
Today | -0.273 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
nowhere | +0.827 |
pr | +0.674 |
aming | +0.659 |
there | +0.659 |
we | +0.658 |
Neg logit contributions | |
These | -0.586 |
Novel | -0.558 |
This | -0.556 |
ses | -0.551 |
Today | -0.506 |
Token | First |
Token ID | 3274 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
attitude | +0.043 |
Novel | +0.042 |
acts | +0.042 |
ness | +0.041 |
ses | +0.041 |
Neg logit contributions | |
nowhere | -0.078 |
there | -0.067 |
soon | -0.066 |
we | -0.065 |
Where | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
These | +0.230 |
ses | +0.225 |
Novel | +0.222 |
This | +0.221 |
Today | +0.202 |
Neg logit contributions | |
nowhere | -0.304 |
there | -0.250 |
aming | -0.247 |
we | -0.243 |
soon | -0.239 |
Token | we |
Token ID | 356 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
These | +0.395 |
This | +0.390 |
Novel | +0.381 |
ses | +0.358 |
Today | +0.350 |
Neg logit contributions | |
nowhere | -0.444 |
aming | -0.378 |
pr | -0.371 |
amed | -0.360 |
we | -0.350 |
Token | have |
Token ID | 423 |
Feature activation | -8.15e+00 |
Pos logit contributions | |
These | +0.090 |
This | +0.089 |
Novel | +0.087 |
ses | +0.084 |
Today | +0.075 |
Neg logit contributions | |
nowhere | -0.197 |
pr | -0.170 |
aming | -0.168 |
amed | -0.161 |
in | -0.160 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
nowhere | +0.199 |
aming | +0.171 |
pr | +0.170 |
amed | +0.162 |
we | +0.161 |
Neg logit contributions | |
These | -0.178 |
This | -0.177 |
Novel | -0.174 |
ses | -0.163 |
Today | -0.161 |
Token | take |
Token ID | 1011 |
Feature activation | -8.68e+00 |
Pos logit contributions | |
nowhere | +0.143 |
soon | +0.114 |
aming | +0.113 |
there | +0.113 |
amed | +0.112 |
Neg logit contributions | |
These | -0.088 |
This | -0.081 |
Novel | -0.079 |
Today | -0.076 |
ses | -0.070 |
Token | out |
Token ID | 503 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
These | +0.434 |
This | +0.421 |
Novel | +0.417 |
ses | +0.401 |
Today | +0.388 |
Neg logit contributions | |
nowhere | -0.592 |
aming | -0.504 |
pr | -0.497 |
amed | -0.486 |
we | -0.476 |
Token | their |
Token ID | 511 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
nowhere | +0.281 |
aming | +0.238 |
pr | +0.235 |
amed | +0.225 |
we | +0.223 |
Neg logit contributions | |
These | -0.260 |
This | -0.258 |
Novel | -0.252 |
ses | -0.236 |
Today | -0.231 |
Token | favorite |
Token ID | 4004 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
These | +0.210 |
This | +0.206 |
Novel | +0.202 |
Today | +0.187 |
ses | +0.187 |
Neg logit contributions | |
nowhere | -0.254 |
aming | -0.202 |
pr | -0.201 |
we | -0.195 |
amed | -0.191 |
Token | dolls |
Token ID | 36062 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
These | +0.231 |
This | +0.226 |
Novel | +0.219 |
ses | +0.216 |
Today | +0.206 |
Neg logit contributions | |
nowhere | -0.243 |
pr | -0.190 |
aming | -0.188 |
we | -0.183 |
amed | -0.178 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nowhere | +0.084 |
pr | +0.074 |
aming | +0.074 |
amed | +0.071 |
we | +0.070 |
Neg logit contributions | |
This | -0.054 |
These | -0.053 |
Novel | -0.053 |
ses | -0.048 |
Today | -0.046 |
Token | cars |
Token ID | 5006 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
nowhere | +0.119 |
soon | +0.095 |
aming | +0.093 |
there | +0.092 |
amed | +0.091 |
Neg logit contributions | |
These | -0.108 |
This | -0.105 |
Novel | -0.100 |
Today | -0.100 |
ses | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
These | +0.035 |
This | +0.035 |
Novel | +0.034 |
ses | +0.031 |
Today | +0.030 |
Neg logit contributions | |
nowhere | -0.051 |
aming | -0.044 |
pr | -0.044 |
amed | -0.041 |
we | -0.041 |
Token | They |
Token ID | 1119 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
acts | +0.036 |
ses | +0.033 |
These | +0.033 |
Novel | +0.032 |
hy | +0.030 |
Neg logit contributions | |
nowhere | -0.096 |
there | -0.082 |
together | -0.080 |
soon | -0.079 |
sudden | -0.077 |
Token | make |
Token ID | 787 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
These | +0.526 |
This | +0.523 |
ses | +0.477 |
Today | +0.465 |
Dogs | +0.443 |
Neg logit contributions | |
nowhere | -0.714 |
soon | -0.659 |
there | -0.622 |
eps | -0.620 |
pr | -0.617 |
Token | that |
Token ID | 326 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
These | +0.305 |
This | +0.302 |
Novel | +0.295 |
ses | +0.279 |
Today | +0.272 |
Neg logit contributions | |
nowhere | -0.348 |
aming | -0.294 |
pr | -0.292 |
amed | -0.279 |
we | -0.276 |
Token | he |
Token ID | 339 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
nowhere | +0.174 |
aming | +0.158 |
pr | +0.157 |
amed | +0.151 |
we | +0.148 |
Neg logit contributions | |
This | -0.146 |
These | -0.142 |
Novel | -0.136 |
Today | -0.127 |
acts | -0.126 |
Token | kept |
Token ID | 4030 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
nowhere | +0.028 |
pr | +0.025 |
aming | +0.024 |
we | +0.023 |
amed | +0.022 |
Neg logit contributions | |
Novel | -0.026 |
This | -0.025 |
thank | -0.025 |
acts | -0.025 |
try | -0.024 |
Token | on |
Token ID | 319 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
nowhere | +0.028 |
pr | +0.025 |
aming | +0.024 |
amed | +0.024 |
we | +0.023 |
Neg logit contributions | |
This | -0.031 |
Novel | -0.028 |
These | -0.028 |
try | -0.027 |
thank | -0.027 |
Token | growing |
Token ID | 3957 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
nowhere | +0.475 |
aming | +0.401 |
pr | +0.401 |
amed | +0.387 |
we | +0.375 |
Neg logit contributions | |
This | -0.524 |
These | -0.506 |
Novel | -0.496 |
ses | -0.463 |
Today | -0.462 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
nowhere | +0.330 |
aming | +0.277 |
pr | +0.275 |
amed | +0.260 |
we | +0.259 |
Neg logit contributions | |
These | -0.319 |
This | -0.313 |
Novel | -0.306 |
ses | -0.295 |
Today | -0.284 |
Token | growing |
Token ID | 3957 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
nowhere | +0.100 |
pr | +0.085 |
aming | +0.084 |
P | +0.078 |
amed | +0.078 |
Neg logit contributions | |
This | -0.111 |
These | -0.107 |
Novel | -0.102 |
ses | -0.101 |
acts | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
nowhere | +0.310 |
aming | +0.257 |
pr | +0.255 |
amed | +0.241 |
we | +0.239 |
Neg logit contributions | |
These | -0.337 |
This | -0.333 |
Novel | -0.326 |
ses | -0.312 |
Today | -0.303 |
Token | He |
Token ID | 679 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
ses | +0.044 |
acts | +0.041 |
Novel | +0.040 |
These | +0.035 |
icks | +0.035 |
Neg logit contributions | |
nowhere | -0.101 |
amed | -0.084 |
aming | -0.084 |
year | -0.082 |
John | -0.081 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
acts | +0.490 |
This | +0.484 |
opens | +0.480 |
Novel | +0.475 |
These | +0.470 |
Neg logit contributions | |
nowhere | -0.536 |
pr | -0.461 |
aming | -0.448 |
we | -0.425 |
THE | -0.415 |
Token | turned |
Token ID | 2900 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
nowhere | +0.583 |
pr | +0.515 |
we | +0.504 |
aming | +0.467 |
ths | +0.430 |
Neg logit contributions | |
This | -0.729 |
These | -0.727 |
Novel | -0.708 |
acts | -0.678 |
thank | -0.675 |
Token | says |
Token ID | 1139 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
These | +0.385 |
This | +0.377 |
Novel | +0.354 |
ses | +0.323 |
hy | +0.320 |
Neg logit contributions | |
nowhere | -0.844 |
aming | -0.722 |
pr | -0.713 |
ep | -0.696 |
amed | -0.693 |
Token | they |
Token ID | 484 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ses | +0.359 |
Novel | +0.350 |
These | +0.349 |
This | +0.345 |
Today | +0.333 |
Neg logit contributions | |
nowhere | -0.487 |
pr | -0.419 |
there | -0.395 |
in | -0.393 |
aming | -0.388 |
Token | are |
Token ID | 389 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
nowhere | +0.185 |
aming | +0.161 |
pr | +0.159 |
amed | +0.154 |
eps | +0.153 |
Neg logit contributions | |
This | -0.095 |
Novel | -0.095 |
ses | -0.095 |
These | -0.094 |
Today | -0.084 |
Token | from |
Token ID | 422 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
These | +0.704 |
This | +0.700 |
Novel | +0.687 |
ses | +0.652 |
Today | +0.634 |
Neg logit contributions | |
nowhere | -0.559 |
pr | -0.453 |
aming | -0.453 |
we | -0.430 |
amed | -0.425 |
Token | her |
Token ID | 607 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
nowhere | +0.148 |
aming | +0.133 |
pr | +0.131 |
amed | +0.128 |
we | +0.126 |
Neg logit contributions | |
This | -0.095 |
These | -0.095 |
Novel | -0.090 |
ses | -0.086 |
Today | -0.081 |
Token | friend |
Token ID | 1545 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
These | +0.009 |
This | +0.009 |
Novel | +0.009 |
ses | +0.008 |
Today | +0.008 |
Neg logit contributions | |
nowhere | -0.012 |
aming | -0.009 |
pr | -0.009 |
we | -0.009 |
amed | -0.009 |
Token | who |
Token ID | 508 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
nowhere | +0.365 |
aming | +0.315 |
pr | +0.312 |
amed | +0.300 |
we | +0.298 |
Neg logit contributions | |
These | -0.221 |
This | -0.216 |
Novel | -0.211 |
ses | -0.201 |
Today | -0.190 |
Token | has |
Token ID | 468 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
nowhere | +0.869 |
aming | +0.762 |
pr | +0.760 |
in | +0.752 |
ep | +0.728 |
Neg logit contributions | |
These | -0.429 |
This | -0.421 |
ses | -0.414 |
Novel | -0.411 |
Today | -0.391 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
This | +0.501 |
These | +0.498 |
Novel | +0.479 |
ses | +0.452 |
They | +0.439 |
Neg logit contributions | |
nowhere | -0.523 |
pr | -0.467 |
aming | -0.464 |
amed | -0.436 |
we | -0.434 |
Token | baby |
Token ID | 5156 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
nowhere | +0.073 |
aming | +0.061 |
pr | +0.061 |
amed | +0.058 |
we | +0.057 |
Neg logit contributions | |
These | -0.059 |
This | -0.058 |
Novel | -0.058 |
ses | -0.054 |
Today | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
These | +0.005 |
This | +0.005 |
Novel | +0.005 |
ses | +0.005 |
Today | +0.005 |
Neg logit contributions | |
nowhere | -0.007 |
aming | -0.006 |
pr | -0.006 |
we | -0.006 |
amed | -0.006 |
Token | sharing |
Token ID | 7373 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
nowhere | +0.122 |
pr | +0.110 |
aming | +0.106 |
in | +0.100 |
amed | +0.100 |
Neg logit contributions | |
ses | -0.110 |
This | -0.108 |
Novel | -0.107 |
These | -0.107 |
acts | -0.102 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
These | +0.007 |
This | +0.007 |
Novel | +0.007 |
ses | +0.007 |
Today | +0.006 |
Neg logit contributions | |
nowhere | -0.008 |
aming | -0.007 |
pr | -0.007 |
we | -0.006 |
amed | -0.006 |
Token | medal |
Token ID | 18279 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
These | +0.099 |
This | +0.099 |
Novel | +0.098 |
acts | +0.092 |
ses | +0.090 |
Neg logit contributions | |
nowhere | -0.161 |
aming | -0.148 |
pr | -0.146 |
amed | -0.140 |
we | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
nowhere | +0.015 |
aming | +0.013 |
pr | +0.013 |
amed | +0.013 |
we | +0.012 |
Neg logit contributions | |
These | -0.011 |
This | -0.011 |
Novel | -0.011 |
ses | -0.010 |
Today | -0.010 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
acts | +0.030 |
These | +0.029 |
hy | +0.028 |
ses | +0.025 |
offer | +0.025 |
Neg logit contributions | |
nowhere | -0.089 |
there | -0.075 |
THE | -0.072 |
aming | -0.072 |
together | -0.072 |
Token | was |
Token ID | 373 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
nowhere | +0.118 |
pr | +0.102 |
dd | +0.099 |
aming | +0.099 |
P | +0.095 |
Neg logit contributions | |
Novel | -0.096 |
acts | -0.092 |
This | -0.091 |
opens | -0.091 |
These | -0.090 |
Token | proud |
Token ID | 6613 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
dd | +0.194 |
nowhere | +0.193 |
ths | +0.189 |
we | +0.188 |
B | +0.185 |
Neg logit contributions | |
This | -0.156 |
Novel | -0.155 |
thank | -0.155 |
name | -0.153 |
The | -0.150 |
Token | of |
Token ID | 286 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
nowhere | +0.139 |
aming | +0.125 |
amed | +0.124 |
pr | +0.123 |
dd | +0.115 |
Neg logit contributions | |
Novel | -0.110 |
These | -0.109 |
This | -0.109 |
They | -0.102 |
Today | -0.102 |
Token | them |
Token ID | 606 |
Feature activation | +8.38e+00 |
Pos logit contributions | |
nowhere | +0.045 |
aming | +0.035 |
pr | +0.034 |
we | +0.032 |
amed | +0.032 |
Neg logit contributions | |
These | -0.074 |
This | -0.074 |
Novel | -0.072 |
ses | -0.070 |
Today | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
nowhere | +0.535 |
aming | +0.453 |
pr | +0.449 |
amed | +0.427 |
we | +0.425 |
Neg logit contributions | |
These | -0.455 |
This | -0.447 |
Novel | -0.439 |
ses | -0.419 |
Today | -0.401 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
nowhere | +0.112 |
pr | +0.092 |
aming | +0.092 |
we | +0.085 |
amed | +0.085 |
Neg logit contributions | |
This | -0.132 |
These | -0.132 |
Novel | -0.130 |
ses | -0.126 |
acts | -0.121 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
nowhere | +0.309 |
aming | +0.262 |
pr | +0.261 |
amed | +0.251 |
we | +0.250 |
Neg logit contributions | |
This | -0.240 |
These | -0.238 |
Novel | -0.223 |
Today | -0.214 |
They | -0.205 |
Token | â |
Token ID | 22940 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
nowhere | +0.249 |
aming | +0.187 |
pr | +0.187 |
we | +0.183 |
amed | +0.181 |
Neg logit contributions | |
These | -0.306 |
This | -0.302 |
Novel | -0.284 |
Today | -0.275 |
They | -0.264 |
Token | € |
Token ID | 26391 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
These | +0.188 |
This | +0.178 |
ses | +0.177 |
Novel | +0.177 |
acts | +0.166 |
Neg logit contributions | |
nowhere | -0.256 |
aming | -0.233 |
pr | -0.220 |
amed | -0.219 |
we | -0.214 |
Token | � |
Token ID | 129 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
These | +0.137 |
Novel | +0.133 |
This | +0.131 |
ses | +0.131 |
acts | +0.126 |
Neg logit contributions | |
nowhere | -0.161 |
aming | -0.137 |
we | -0.130 |
pr | -0.128 |
amed | -0.127 |
Token | � |
Token ID | 241 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
These | +0.331 |
This | +0.305 |
Novel | +0.304 |
ses | +0.297 |
acts | +0.293 |
Neg logit contributions | |
nowhere | -0.468 |
aming | -0.412 |
amed | -0.389 |
pr | -0.385 |
dd | -0.379 |
Token | You |
Token ID | 1639 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
This | +0.475 |
These | +0.475 |
Novel | +0.446 |
Today | +0.442 |
They | +0.431 |
Neg logit contributions | |
nowhere | -0.360 |
pr | -0.287 |
aming | -0.281 |
amed | -0.275 |
ths | -0.262 |
Token | silly |
Token ID | 14397 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
nowhere | +0.358 |
aming | +0.312 |
pr | +0.310 |
amed | +0.299 |
we | +0.293 |
Neg logit contributions | |
These | -0.197 |
This | -0.192 |
Novel | -0.187 |
ses | -0.178 |
Today | -0.169 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
These | +0.146 |
This | +0.141 |
Novel | +0.139 |
ses | +0.138 |
Today | +0.129 |
Neg logit contributions | |
nowhere | -0.193 |
pr | -0.169 |
aming | -0.168 |
we | -0.165 |
in | -0.161 |
Token | ! |
Token ID | 0 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
nowhere | +0.076 |
pr | +0.065 |
aming | +0.064 |
we | +0.062 |
in | +0.061 |
Neg logit contributions | |
These | -0.066 |
Novel | -0.064 |
This | -0.064 |
ses | -0.061 |
Today | -0.060 |
Token | â |
Token ID | 22940 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
ses | +0.035 |
Novel | +0.032 |
attitude | +0.030 |
acts | +0.030 |
These | +0.029 |
Neg logit contributions | |
nowhere | -0.074 |
aming | -0.067 |
pr | -0.066 |
we | -0.064 |
amed | -0.063 |
Token | € |
Token ID | 26391 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
These | +0.197 |
ses | +0.193 |
Novel | +0.189 |
This | +0.189 |
acts | +0.175 |
Neg logit contributions | |
nowhere | -0.244 |
aming | -0.222 |
pr | -0.213 |
amed | -0.208 |
we | -0.199 |
Token | in |
Token ID | 287 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
This | +0.388 |
These | +0.387 |
Novel | +0.375 |
Today | +0.355 |
ses | +0.351 |
Neg logit contributions | |
nowhere | -0.333 |
aming | -0.270 |
pr | -0.265 |
amed | -0.254 |
we | -0.250 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
nowhere | +0.498 |
aming | +0.422 |
pr | +0.420 |
amed | +0.403 |
we | +0.397 |
Neg logit contributions | |
These | -0.469 |
This | -0.468 |
Novel | -0.455 |
ses | -0.428 |
Today | -0.425 |
Token | morning |
Token ID | 3329 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
These | +0.098 |
This | +0.097 |
Novel | +0.092 |
ses | +0.086 |
Today | +0.084 |
Neg logit contributions | |
nowhere | -0.166 |
pr | -0.146 |
aming | -0.145 |
we | -0.139 |
amed | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
nowhere | +0.236 |
aming | +0.198 |
pr | +0.196 |
amed | +0.187 |
we | +0.185 |
Neg logit contributions | |
These | -0.223 |
This | -0.220 |
Novel | -0.216 |
ses | -0.205 |
Today | -0.199 |
Token | when |
Token ID | 618 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
This | +0.354 |
These | +0.346 |
Novel | +0.337 |
ses | +0.315 |
Today | +0.312 |
Neg logit contributions | |
nowhere | -0.464 |
pr | -0.412 |
aming | -0.412 |
amed | -0.400 |
we | -0.385 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
nowhere | +0.512 |
aming | +0.462 |
pr | +0.459 |
amed | +0.450 |
we | +0.424 |
Neg logit contributions | |
This | -0.440 |
These | -0.434 |
Novel | -0.420 |
Today | -0.400 |
ses | -0.394 |
Token | sun |
Token ID | 4252 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
These | +0.086 |
This | +0.083 |
Novel | +0.082 |
ses | +0.078 |
Today | +0.074 |
Neg logit contributions | |
nowhere | -0.175 |
pr | -0.157 |
aming | -0.152 |
amed | -0.148 |
we | -0.145 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
nowhere | +0.136 |
pr | +0.112 |
aming | +0.110 |
amed | +0.103 |
ths | +0.097 |
Neg logit contributions | |
This | -0.142 |
Novel | -0.142 |
These | -0.141 |
ses | -0.132 |
Today | -0.132 |
Token | out |
Token ID | 503 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
nowhere | +0.176 |
we | +0.174 |
in | +0.153 |
dd | +0.150 |
ppa | +0.148 |
Neg logit contributions | |
Today | -0.192 |
This | -0.183 |
Novel | -0.180 |
One | -0.175 |
taste | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
nowhere | +0.281 |
aming | +0.234 |
pr | +0.232 |
amed | +0.220 |
we | +0.218 |
Neg logit contributions | |
These | -0.283 |
This | -0.279 |
Novel | -0.273 |
ses | -0.261 |
Today | -0.252 |
Token |
|
Token ID | 198 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
ses | +0.042 |
acts | +0.040 |
Novel | +0.037 |
These | +0.036 |
attitude | +0.035 |
Neg logit contributions | |
nowhere | -0.077 |
there | -0.065 |
aming | -0.063 |
sudden | -0.063 |
B | -0.062 |
Token | living |
Token ID | 2877 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
These | +0.122 |
This | +0.122 |
Novel | +0.116 |
ses | +0.110 |
Today | +0.109 |
Neg logit contributions | |
nowhere | -0.144 |
pr | -0.126 |
aming | -0.123 |
we | -0.118 |
amed | -0.117 |
Token | room |
Token ID | 2119 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
pr | +0.216 |
nowhere | +0.207 |
dd | +0.201 |
aming | +0.193 |
we | +0.186 |
Neg logit contributions | |
This | -0.165 |
These | -0.153 |
Novel | -0.151 |
They | -0.145 |
The | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
nowhere | +0.510 |
aming | +0.440 |
pr | +0.440 |
amed | +0.422 |
we | +0.412 |
Neg logit contributions | |
These | -0.357 |
This | -0.352 |
Novel | -0.339 |
ses | -0.317 |
Today | -0.310 |
Token | They |
Token ID | 1119 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
ses | +0.034 |
Novel | +0.034 |
hy | +0.033 |
acts | +0.032 |
These | +0.031 |
Neg logit contributions | |
nowhere | -0.093 |
there | -0.076 |
aming | -0.076 |
sudden | -0.073 |
amed | -0.072 |
Token | make |
Token ID | 787 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
These | +0.691 |
This | +0.689 |
Novel | +0.674 |
ses | +0.652 |
Today | +0.634 |
Neg logit contributions | |
nowhere | -0.590 |
aming | -0.480 |
pr | -0.465 |
amed | -0.454 |
we | -0.443 |
Token | v |
Token ID | 410 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
This | +0.613 |
These | +0.605 |
Novel | +0.592 |
ses | +0.541 |
They | +0.541 |
Neg logit contributions | |
nowhere | -0.770 |
pr | -0.664 |
aming | -0.648 |
we | -0.597 |
amed | -0.597 |
Token | room |
Token ID | 3823 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
These | +0.156 |
This | +0.153 |
Novel | +0.149 |
ses | +0.137 |
Today | +0.130 |
Neg logit contributions | |
nowhere | -0.303 |
aming | -0.261 |
pr | -0.260 |
amed | -0.248 |
we | -0.248 |
Token | - |
Token ID | 12 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
These | +0.182 |
This | +0.178 |
ses | +0.177 |
Novel | +0.172 |
Today | +0.169 |
Neg logit contributions | |
nowhere | -0.176 |
we | -0.157 |
pr | -0.157 |
aming | -0.155 |
ep | -0.153 |
Token | v |
Token ID | 85 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
nowhere | +0.167 |
aming | +0.133 |
pr | +0.130 |
amed | +0.121 |
ths | +0.119 |
Neg logit contributions | |
These | -0.153 |
This | -0.149 |
Novel | -0.141 |
hy | -0.129 |
They | -0.128 |
Token | room |
Token ID | 3823 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
These | +0.075 |
This | +0.074 |
Novel | +0.071 |
ses | +0.067 |
Today | +0.064 |
Neg logit contributions | |
nowhere | -0.128 |
aming | -0.112 |
pr | -0.111 |
amed | -0.108 |
we | -0.107 |
Token | noises |
Token ID | 26782 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
These | +0.179 |
This | +0.174 |
ses | +0.174 |
Novel | +0.168 |
Today | +0.167 |
Neg logit contributions | |
nowhere | -0.177 |
we | -0.161 |
ep | -0.159 |
pr | -0.159 |
aming | -0.159 |
Token | go |
Token ID | 467 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
These | +0.025 |
ses | +0.025 |
Novel | +0.022 |
This | +0.022 |
hy | +0.021 |
Neg logit contributions | |
nowhere | -0.047 |
pr | -0.041 |
aming | -0.040 |
there | -0.039 |
soon | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
This | +0.398 |
These | +0.393 |
Novel | +0.386 |
Today | +0.367 |
Show | +0.356 |
Neg logit contributions | |
nowhere | -0.327 |
aming | -0.262 |
pr | -0.254 |
amed | -0.248 |
we | -0.241 |
Token | take |
Token ID | 1011 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
nowhere | +0.168 |
pr | +0.147 |
aming | +0.145 |
amed | +0.139 |
we | +0.138 |
Neg logit contributions | |
These | -0.073 |
Novel | -0.069 |
This | -0.067 |
ses | -0.066 |
Today | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
This | +0.547 |
These | +0.547 |
Novel | +0.533 |
ses | +0.502 |
Today | +0.494 |
Neg logit contributions | |
nowhere | -0.466 |
aming | -0.381 |
pr | -0.378 |
we | -0.356 |
amed | -0.355 |
Token | closer |
Token ID | 5699 |
Feature activation | +7.72e+00 |
Pos logit contributions | |
nowhere | +0.100 |
aming | +0.090 |
pr | +0.088 |
amed | +0.087 |
we | +0.087 |
Neg logit contributions | |
This | -0.039 |
These | -0.038 |
Novel | -0.036 |
ses | -0.032 |
Today | -0.032 |
Token | look |
Token ID | 804 |
Feature activation | -9.23e+00 |
Pos logit contributions | |
nowhere | +0.614 |
pr | +0.560 |
there | +0.536 |
in | +0.514 |
aming | +0.508 |
Neg logit contributions | |
These | -0.275 |
ses | -0.244 |
Novel | -0.235 |
This | -0.226 |
acts | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
This | +0.332 |
These | +0.326 |
Novel | +0.317 |
Today | +0.289 |
acts | +0.280 |
Neg logit contributions | |
nowhere | -0.745 |
aming | -0.659 |
amed | -0.651 |
pr | -0.642 |
ths | -0.619 |
Token | When |
Token ID | 1649 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
These | +0.036 |
Novel | +0.035 |
ses | +0.035 |
acts | +0.033 |
This | +0.032 |
Neg logit contributions | |
nowhere | -0.091 |
aming | -0.078 |
pr | -0.077 |
amed | -0.077 |
we | -0.075 |
Token | she |
Token ID | 673 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
This | +0.004 |
These | +0.004 |
Novel | +0.004 |
Today | +0.004 |
They | +0.004 |
Neg logit contributions | |
nowhere | -0.005 |
aming | -0.004 |
pr | -0.004 |
amed | -0.004 |
we | -0.004 |
Token | got |
Token ID | 1392 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
nowhere | +0.066 |
aming | +0.058 |
we | +0.058 |
amed | +0.057 |
pr | +0.057 |
Neg logit contributions | |
This | -0.063 |
These | -0.060 |
Novel | -0.060 |
opens | -0.055 |
Today | -0.055 |
Token | near |
Token ID | 1474 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
nowhere | +0.116 |
we | +0.110 |
if | +0.107 |
aming | +0.102 |
ep | +0.100 |
Neg logit contributions | |
This | -0.143 |
Novel | -0.134 |
try | -0.131 |
The | -0.131 |
These | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Novel | +0.567 |
This | +0.565 |
These | +0.556 |
Today | +0.527 |
ses | +0.520 |
Neg logit contributions | |
nowhere | -0.689 |
aming | -0.585 |
pr | -0.583 |
amed | -0.556 |
we | -0.556 |
Token | say |
Token ID | 910 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
nowhere | +0.117 |
aming | +0.108 |
soon | +0.108 |
together | +0.106 |
there | +0.104 |
Neg logit contributions | |
These | -0.086 |
This | -0.080 |
Today | -0.074 |
ses | -0.070 |
Dogs | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
These | +0.332 |
ses | +0.329 |
Novel | +0.322 |
This | +0.319 |
Today | +0.304 |
Neg logit contributions | |
nowhere | -0.445 |
pr | -0.406 |
aming | -0.381 |
in | -0.379 |
amed | -0.373 |
Token | " |
Token ID | 366 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
These | +0.279 |
This | +0.276 |
Novel | +0.264 |
ses | +0.241 |
Today | +0.232 |
Neg logit contributions | |
nowhere | -0.586 |
aming | -0.516 |
pr | -0.514 |
amed | -0.495 |
we | -0.487 |
Token | Yes |
Token ID | 5297 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
These | +0.111 |
This | +0.109 |
Novel | +0.107 |
ses | +0.102 |
Today | +0.099 |
Neg logit contributions | |
nowhere | -0.116 |
aming | -0.097 |
pr | -0.096 |
amed | -0.091 |
we | -0.090 |
Token | , |
Token ID | 11 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
nowhere | +0.053 |
aming | +0.044 |
pr | +0.044 |
there | +0.043 |
soon | +0.042 |
Neg logit contributions | |
ses | -0.044 |
These | -0.044 |
This | -0.042 |
acts | -0.041 |
Novel | -0.041 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
These | +0.278 |
This | +0.276 |
Novel | +0.264 |
ses | +0.237 |
Today | +0.236 |
Neg logit contributions | |
nowhere | -0.583 |
aming | -0.527 |
pr | -0.517 |
amed | -0.513 |
we | -0.505 |
Token | ." |
Token ID | 526 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
nowhere | +0.083 |
pr | +0.070 |
aming | +0.069 |
in | +0.067 |
we | +0.067 |
Neg logit contributions | |
These | -0.095 |
ses | -0.092 |
This | -0.091 |
Novel | -0.088 |
acts | -0.084 |
Token | They |
Token ID | 1119 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
These | +0.207 |
This | +0.199 |
Novel | +0.196 |
ses | +0.194 |
acts | +0.190 |
Neg logit contributions | |
nowhere | -0.258 |
aming | -0.216 |
we | -0.201 |
amed | -0.201 |
pr | -0.200 |
Token | help |
Token ID | 1037 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
These | +0.529 |
This | +0.523 |
ses | +0.498 |
Today | +0.476 |
Dogs | +0.467 |
Neg logit contributions | |
nowhere | -0.718 |
aming | -0.699 |
pr | -0.681 |
amed | -0.680 |
in | -0.631 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
This | +0.443 |
Novel | +0.441 |
These | +0.436 |
They | +0.389 |
Today | +0.374 |
Neg logit contributions | |
nowhere | -0.849 |
pr | -0.752 |
aming | -0.728 |
amed | -0.712 |
we | -0.702 |
Token | picking |
Token ID | 10868 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
nowhere | +0.127 |
aming | +0.108 |
pr | +0.106 |
amed | +0.103 |
we | +0.099 |
Neg logit contributions | |
This | -0.121 |
These | -0.120 |
Novel | -0.115 |
ses | -0.109 |
Today | -0.106 |
Token | some |
Token ID | 617 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
These | +0.065 |
This | +0.064 |
Novel | +0.063 |
ses | +0.059 |
Today | +0.058 |
Neg logit contributions | |
nowhere | -0.068 |
aming | -0.057 |
pr | -0.056 |
amed | -0.054 |
we | -0.053 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
nowhere | +0.070 |
aming | +0.060 |
pr | +0.059 |
amed | +0.056 |
we | +0.056 |
Neg logit contributions | |
These | -0.060 |
This | -0.059 |
Novel | -0.058 |
ses | -0.054 |
Today | -0.053 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
These | +0.017 |
This | +0.017 |
Novel | +0.016 |
ses | +0.016 |
Today | +0.015 |
Neg logit contributions | |
nowhere | -0.017 |
aming | -0.014 |
pr | -0.014 |
amed | -0.013 |
we | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
nowhere | +0.094 |
aming | +0.081 |
pr | +0.079 |
amed | +0.078 |
we | +0.076 |
Neg logit contributions | |
These | -0.062 |
This | -0.062 |
Novel | -0.059 |
ses | -0.054 |
Today | -0.054 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
These | +0.068 |
Novel | +0.067 |
ses | +0.067 |
This | +0.065 |
acts | +0.064 |
Neg logit contributions | |
nowhere | -0.077 |
aming | -0.063 |
pr | -0.062 |
amed | -0.061 |
we | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -7.20e+00 |
Pos logit contributions | |
These | +0.129 |
This | +0.126 |
Novel | +0.123 |
ses | +0.120 |
Today | +0.111 |
Neg logit contributions | |
nowhere | -0.214 |
pr | -0.182 |
aming | -0.182 |
amed | -0.174 |
we | -0.170 |
Token | she |
Token ID | 673 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
This | +0.352 |
These | +0.344 |
Novel | +0.319 |
They | +0.305 |
The | +0.304 |
Neg logit contributions | |
nowhere | -0.472 |
aming | -0.442 |
pr | -0.425 |
we | -0.423 |
amed | -0.421 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
pr | +0.061 |
year | +0.055 |
THE | +0.054 |
prisingly | +0.053 |
ths | +0.052 |
Neg logit contributions | |
ses | -0.037 |
The | -0.037 |
drop | -0.036 |
This | -0.036 |
mouth | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
nowhere | +0.062 |
pr | +0.060 |
aming | +0.059 |
we | +0.058 |
if | +0.056 |
Neg logit contributions | |
This | -0.049 |
These | -0.048 |
Novel | -0.046 |
The | -0.044 |
ses | -0.043 |
Token | small |
Token ID | 1402 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
nowhere | +0.066 |
aming | +0.058 |
pr | +0.057 |
amed | +0.055 |
we | +0.055 |
Neg logit contributions | |
These | -0.049 |
This | -0.048 |
Novel | -0.047 |
ses | -0.045 |
Today | -0.043 |
Token | small |
Token ID | 1402 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
nowhere | +0.075 |
aming | +0.068 |
pr | +0.068 |
amed | +0.066 |
we | +0.064 |
Neg logit contributions | |
This | -0.054 |
These | -0.054 |
Novel | -0.051 |
Today | -0.049 |
ses | -0.047 |
Token | shed |
Token ID | 14999 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
These | +0.176 |
This | +0.171 |
Novel | +0.167 |
ses | +0.165 |
Show | +0.149 |
Neg logit contributions | |
nowhere | -0.195 |
aming | -0.157 |
pr | -0.153 |
in | -0.149 |
sudden | -0.148 |
Token | without |
Token ID | 1231 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
nowhere | +0.024 |
aming | +0.021 |
pr | +0.020 |
amed | +0.020 |
we | +0.019 |
Neg logit contributions | |
These | -0.017 |
This | -0.017 |
Novel | -0.016 |
ses | -0.016 |
Today | -0.015 |
Token | anything |
Token ID | 1997 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
nowhere | +0.192 |
aming | +0.172 |
pr | +0.171 |
amed | +0.166 |
we | +0.159 |
Neg logit contributions | |
This | -0.173 |
These | -0.170 |
Novel | -0.166 |
ses | -0.159 |
acts | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
These | +0.040 |
This | +0.039 |
Novel | +0.038 |
ses | +0.036 |
Today | +0.035 |
Neg logit contributions | |
nowhere | -0.048 |
aming | -0.040 |
pr | -0.040 |
amed | -0.038 |
we | -0.038 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
These | +0.034 |
ses | +0.034 |
This | +0.031 |
Novel | +0.028 |
acts | +0.027 |
Neg logit contributions | |
nowhere | -0.051 |
pr | -0.044 |
soon | -0.043 |
there | -0.042 |
aming | -0.042 |
Token | or |
Token ID | 393 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
These | +0.536 |
This | +0.533 |
Novel | +0.520 |
ses | +0.481 |
Today | +0.471 |
Neg logit contributions | |
nowhere | -0.743 |
aming | -0.641 |
pr | -0.637 |
amed | -0.614 |
we | -0.603 |
Token | drink |
Token ID | 4144 |
Feature activation | -8.40e+00 |
Pos logit contributions | |
This | +0.136 |
These | +0.135 |
Novel | +0.129 |
ses | +0.124 |
acts | +0.117 |
Neg logit contributions | |
nowhere | -0.219 |
aming | -0.199 |
pr | -0.198 |
amed | -0.191 |
we | -0.184 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
These | +0.460 |
This | +0.450 |
Novel | +0.441 |
ses | +0.426 |
Today | +0.407 |
Neg logit contributions | |
nowhere | -0.534 |
aming | -0.450 |
pr | -0.448 |
we | -0.425 |
amed | -0.424 |
Token | The |
Token ID | 383 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
ses | +0.052 |
Novel | +0.051 |
These | +0.050 |
acts | +0.048 |
This | +0.047 |
Neg logit contributions | |
nowhere | -0.088 |
aming | -0.070 |
pr | -0.070 |
we | -0.068 |
amed | -0.067 |
Token | m |
Token ID | 285 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
These | +0.739 |
This | +0.729 |
Novel | +0.720 |
Today | +0.671 |
ses | +0.665 |
Neg logit contributions | |
nowhere | -1.130 |
pr | -0.982 |
aming | -0.967 |
amed | -0.940 |
we | -0.930 |
Token | up |
Token ID | 510 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
This | +0.535 |
These | +0.518 |
Novel | +0.498 |
ses | +0.476 |
They | +0.475 |
Neg logit contributions | |
nowhere | -0.390 |
pr | -0.337 |
aming | -0.336 |
we | -0.313 |
amed | -0.309 |
Token | and |
Token ID | 290 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
nowhere | +0.124 |
pr | +0.112 |
ppa | +0.110 |
dd | +0.110 |
amed | +0.110 |
Neg logit contributions | |
This | -0.101 |
They | -0.097 |
Novel | -0.094 |
Today | -0.092 |
These | -0.091 |
Token | down |
Token ID | 866 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
nowhere | +0.111 |
aming | +0.091 |
pr | +0.091 |
amed | +0.086 |
we | +0.086 |
Neg logit contributions | |
These | -0.117 |
This | -0.116 |
Novel | -0.114 |
ses | -0.108 |
Today | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
nowhere | +0.228 |
aming | +0.197 |
pr | +0.196 |
amed | +0.190 |
we | +0.185 |
Neg logit contributions | |
These | -0.166 |
This | -0.166 |
Novel | -0.162 |
ses | -0.151 |
Today | -0.147 |
Token | It |
Token ID | 632 |
Feature activation | -7.69e+00 |
Pos logit contributions | |
Novel | +0.054 |
ses | +0.053 |
hy | +0.053 |
These | +0.052 |
acts | +0.051 |
Neg logit contributions | |
nowhere | -0.087 |
aming | -0.068 |
there | -0.068 |
sudden | -0.065 |
amed | -0.064 |
Token | makes |
Token ID | 1838 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
These | +0.310 |
Novel | +0.297 |
This | +0.294 |
ses | +0.264 |
attitude | +0.258 |
Neg logit contributions | |
nowhere | -0.596 |
aming | -0.494 |
we | -0.493 |
pr | -0.489 |
there | -0.478 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
This | +0.736 |
These | +0.726 |
Novel | +0.713 |
ses | +0.665 |
They | +0.656 |
Neg logit contributions | |
nowhere | -0.820 |
pr | -0.706 |
aming | -0.682 |
we | -0.653 |
amed | -0.644 |
Token | nice |
Token ID | 3621 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
nowhere | +0.072 |
aming | +0.062 |
pr | +0.061 |
amed | +0.059 |
we | +0.058 |
Neg logit contributions | |
These | -0.053 |
This | -0.052 |
Novel | -0.051 |
ses | -0.048 |
Today | -0.046 |
Token | sound |
Token ID | 2128 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
These | +0.030 |
This | +0.029 |
Novel | +0.028 |
ses | +0.027 |
acts | +0.026 |
Neg logit contributions | |
nowhere | -0.030 |
aming | -0.025 |
pr | -0.025 |
we | -0.024 |
amed | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
nowhere | +0.243 |
aming | +0.205 |
pr | +0.204 |
amed | +0.197 |
we | +0.189 |
Neg logit contributions | |
These | -0.200 |
This | -0.200 |
Novel | -0.194 |
ses | -0.180 |
Today | -0.178 |
Token |
|
Token ID | 198 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Novel | +0.064 |
These | +0.064 |
ses | +0.063 |
hy | +0.061 |
This | +0.061 |
Neg logit contributions | |
nowhere | -0.078 |
aming | -0.061 |
amed | -0.058 |
there | -0.058 |
pr | -0.057 |
Token | feel |
Token ID | 1254 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
nowhere | +0.214 |
aming | +0.178 |
pr | +0.177 |
amed | +0.168 |
we | +0.166 |
Neg logit contributions | |
These | -0.210 |
This | -0.207 |
Novel | -0.202 |
ses | -0.192 |
Today | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
These | +0.451 |
This | +0.443 |
Novel | +0.430 |
ses | +0.406 |
Today | +0.390 |
Neg logit contributions | |
nowhere | -0.699 |
aming | -0.603 |
pr | -0.599 |
amed | -0.574 |
we | -0.571 |
Token | I |
Token ID | 314 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
ses | +0.040 |
attitude | +0.039 |
acts | +0.037 |
Novel | +0.037 |
ness | +0.037 |
Neg logit contributions | |
nowhere | -0.069 |
we | -0.058 |
B | -0.057 |
there | -0.057 |
aming | -0.056 |
Token | will |
Token ID | 481 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
These | +0.366 |
This | +0.361 |
Novel | +0.353 |
ses | +0.335 |
Today | +0.325 |
Neg logit contributions | |
nowhere | -0.404 |
aming | -0.340 |
pr | -0.338 |
amed | -0.322 |
we | -0.319 |
Token | not |
Token ID | 407 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
These | +0.023 |
This | +0.022 |
ses | +0.021 |
Novel | +0.021 |
Today | +0.020 |
Neg logit contributions | |
nowhere | -0.031 |
aming | -0.026 |
pr | -0.026 |
soon | -0.025 |
amed | -0.024 |
Token | use |
Token ID | 779 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
nowhere | +0.217 |
pr | +0.188 |
aming | +0.184 |
soon | +0.175 |
we | +0.174 |
Neg logit contributions | |
These | -0.109 |
This | -0.102 |
ses | -0.100 |
Novel | -0.099 |
Today | -0.089 |
Token | so |
Token ID | 523 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
These | +0.719 |
This | +0.716 |
Novel | +0.697 |
ses | +0.659 |
Today | +0.638 |
Neg logit contributions | |
nowhere | -0.764 |
aming | -0.658 |
pr | -0.651 |
amed | -0.622 |
we | -0.612 |
Token | much |
Token ID | 881 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
nowhere | +0.493 |
pr | +0.383 |
aming | +0.383 |
amed | +0.351 |
we | +0.350 |
Neg logit contributions | |
These | -0.724 |
This | -0.716 |
Novel | -0.706 |
ses | -0.681 |
Today | -0.663 |
Token | perfume |
Token ID | 40094 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
nowhere | +0.229 |
pr | +0.193 |
aming | +0.193 |
amed | +0.182 |
we | +0.182 |
Neg logit contributions | |
These | -0.163 |
This | -0.160 |
Novel | -0.154 |
ses | -0.148 |
Today | -0.141 |
Token | next |
Token ID | 1306 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
nowhere | +0.013 |
pr | +0.011 |
aming | +0.011 |
we | +0.011 |
amed | +0.010 |
Neg logit contributions | |
These | -0.013 |
This | -0.013 |
Novel | -0.013 |
ses | -0.012 |
Today | -0.012 |
Token | time |
Token ID | 640 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
nowhere | +0.537 |
aming | +0.489 |
pr | +0.467 |
we | +0.464 |
amed | +0.461 |
Neg logit contributions | |
This | -0.491 |
Novel | -0.478 |
These | -0.471 |
Today | -0.465 |
attitude | -0.438 |
Token | ladder |
Token ID | 18002 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
These | +0.098 |
This | +0.096 |
Novel | +0.093 |
ses | +0.085 |
Today | +0.084 |
Neg logit contributions | |
nowhere | -0.174 |
aming | -0.150 |
pr | -0.148 |
amed | -0.144 |
we | -0.142 |
Token | on |
Token ID | 319 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
This | +0.288 |
Novel | +0.280 |
These | +0.276 |
They | +0.268 |
Today | +0.264 |
Neg logit contributions | |
nowhere | -0.212 |
dd | -0.167 |
aming | -0.165 |
pr | -0.165 |
we | -0.163 |
Token | the |
Token ID | 262 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
nowhere | +0.515 |
aming | +0.428 |
pr | +0.423 |
amed | +0.402 |
we | +0.399 |
Neg logit contributions | |
These | -0.515 |
This | -0.507 |
Novel | -0.497 |
ses | -0.475 |
Today | -0.461 |
Token | wall |
Token ID | 3355 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
These | +0.090 |
This | +0.088 |
Novel | +0.084 |
acts | +0.076 |
Today | +0.076 |
Neg logit contributions | |
nowhere | -0.182 |
aming | -0.158 |
we | -0.152 |
pr | -0.152 |
amed | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
These | +0.211 |
This | +0.210 |
Novel | +0.204 |
ses | +0.192 |
Today | +0.189 |
Neg logit contributions | |
nowhere | -0.237 |
aming | -0.201 |
pr | -0.200 |
amed | -0.190 |
we | -0.189 |
Token | They |
Token ID | 1119 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
acts | +0.028 |
Novel | +0.027 |
hy | +0.026 |
ses | +0.026 |
offer | +0.024 |
Neg logit contributions | |
nowhere | -0.096 |
there | -0.082 |
sudden | -0.080 |
together | -0.079 |
aming | -0.079 |
Token | climb |
Token ID | 12080 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
These | +0.494 |
This | +0.481 |
Novel | +0.433 |
ses | +0.421 |
Today | +0.412 |
Neg logit contributions | |
nowhere | -0.794 |
pr | -0.687 |
aming | -0.681 |
soon | -0.675 |
ep | -0.664 |
Token | up |
Token ID | 510 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
This | +0.425 |
Novel | +0.416 |
These | +0.415 |
Today | +0.387 |
ses | +0.387 |
Neg logit contributions | |
nowhere | -0.363 |
aming | -0.308 |
pr | -0.306 |
amed | -0.284 |
we | -0.275 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
nowhere | +0.132 |
aming | +0.117 |
pr | +0.114 |
amed | +0.112 |
we | +0.108 |
Neg logit contributions | |
This | -0.110 |
Novel | -0.109 |
These | -0.107 |
They | -0.099 |
Today | -0.098 |
Token | They |
Token ID | 1119 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
acts | +0.027 |
Novel | +0.026 |
ses | +0.025 |
attitude | +0.024 |
hy | +0.023 |
Neg logit contributions | |
nowhere | -0.100 |
there | -0.086 |
sudden | -0.085 |
aming | -0.085 |
we | -0.084 |
Token | look |
Token ID | 804 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
These | +0.496 |
This | +0.479 |
Novel | +0.427 |
ses | +0.417 |
Today | +0.416 |
Neg logit contributions | |
nowhere | -0.788 |
soon | -0.686 |
aming | -0.679 |
pr | -0.678 |
eps | -0.667 |
Token | rock |
Token ID | 3881 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
These | +0.109 |
This | +0.107 |
Novel | +0.104 |
ses | +0.096 |
Today | +0.095 |
Neg logit contributions | |
nowhere | -0.165 |
aming | -0.140 |
pr | -0.139 |
amed | -0.134 |
we | -0.133 |
Token | and |
Token ID | 290 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
These | +0.074 |
This | +0.073 |
Novel | +0.072 |
ses | +0.068 |
Today | +0.066 |
Neg logit contributions | |
nowhere | -0.083 |
aming | -0.072 |
pr | -0.070 |
amed | -0.068 |
we | -0.066 |
Token | lift |
Token ID | 10303 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
nowhere | +0.153 |
there | +0.127 |
soon | +0.127 |
perched | +0.120 |
pr | +0.119 |
Neg logit contributions | |
These | -0.094 |
This | -0.081 |
Novel | -0.080 |
Today | -0.076 |
Dogs | -0.069 |
Token | it |
Token ID | 340 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
These | +0.475 |
This | +0.467 |
Novel | +0.459 |
ses | +0.440 |
Today | +0.429 |
Neg logit contributions | |
nowhere | -0.379 |
aming | -0.307 |
pr | -0.304 |
amed | -0.287 |
we | -0.285 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
nowhere | +0.357 |
pr | +0.295 |
aming | +0.271 |
amed | +0.265 |
there | +0.260 |
Neg logit contributions | |
These | -0.502 |
This | -0.464 |
Novel | -0.463 |
ses | -0.458 |
acts | -0.441 |
Token | They |
Token ID | 1119 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
These | +0.027 |
acts | +0.027 |
Novel | +0.026 |
ses | +0.025 |
hy | +0.024 |
Neg logit contributions | |
nowhere | -0.095 |
there | -0.081 |
we | -0.080 |
together | -0.079 |
sudden | -0.079 |
Token | find |
Token ID | 1064 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
These | +0.535 |
This | +0.499 |
Today | +0.464 |
Novel | +0.429 |
Dogs | +0.425 |
Neg logit contributions | |
nowhere | -0.761 |
soon | -0.651 |
there | -0.637 |
eps | -0.630 |
ep | -0.625 |
Token | the |
Token ID | 262 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
These | +0.325 |
This | +0.321 |
Novel | +0.315 |
ses | +0.300 |
Today | +0.293 |
Neg logit contributions | |
nowhere | -0.275 |
aming | -0.225 |
pr | -0.223 |
amed | -0.211 |
we | -0.208 |
Token | key |
Token ID | 1994 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
These | +0.102 |
This | +0.101 |
Novel | +0.099 |
ses | +0.096 |
Today | +0.089 |
Neg logit contributions | |
nowhere | -0.163 |
aming | -0.145 |
pr | -0.143 |
amed | -0.138 |
we | -0.137 |
Token | and |
Token ID | 290 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
nowhere | +0.102 |
aming | +0.086 |
pr | +0.085 |
amed | +0.081 |
we | +0.079 |
Neg logit contributions | |
This | -0.112 |
These | -0.111 |
Novel | -0.109 |
ses | -0.104 |
Today | -0.101 |
Token | run |
Token ID | 1057 |
Feature activation | -7.77e+00 |
Pos logit contributions | |
nowhere | +0.131 |
aming | +0.098 |
pr | +0.097 |
there | +0.096 |
amed | +0.095 |
Neg logit contributions | |
These | -0.123 |
This | -0.117 |
Novel | -0.114 |
Today | -0.110 |
ses | -0.104 |