Token | decided |
Token ID | 3066 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
| +0.090 |
" | +0.078 |
because | +0.076 |
She | +0.072 |
. | +0.070 |
Neg logit contributions | |
ts | -0.138 |
riches | -0.136 |
pollen | -0.134 |
turrets | -0.133 |
miles | -0.133 |
Token | to |
Token ID | 284 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
| +0.016 |
She | +0.013 |
because | +0.012 |
" | +0.011 |
And | +0.010 |
Neg logit contributions | |
ts | -0.046 |
miles | -0.046 |
riches | -0.045 |
seas | -0.045 |
turrets | -0.045 |
Token | have |
Token ID | 423 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
| +0.126 |
" | +0.109 |
. | +0.107 |
because | +0.104 |
She | +0.102 |
Neg logit contributions | |
pollen | -0.132 |
isher | -0.132 |
riches | -0.131 |
ts | -0.131 |
ounces | -0.129 |
Token | a |
Token ID | 257 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ts | +0.015 |
isher | +0.015 |
riches | +0.015 |
ubb | +0.015 |
pollen | +0.015 |
Neg logit contributions | |
| -0.009 |
" | -0.007 |
because | -0.007 |
. | -0.007 |
She | -0.006 |
Token | race |
Token ID | 3234 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ts | +0.057 |
ounces | +0.054 |
isher | +0.054 |
ubb | +0.052 |
ief | +0.052 |
Neg logit contributions | |
| -0.076 |
" | -0.069 |
because | -0.066 |
. | -0.064 |
She | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ts | +0.418 |
miles | +0.409 |
seas | +0.401 |
turrets | +0.398 |
riches | +0.397 |
Neg logit contributions | |
| -0.123 |
She | -0.095 |
" | -0.093 |
because | -0.080 |
: | -0.064 |
Token | Each |
Token ID | 5501 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
because | +0.234 |
? | +0.150 |
. | +0.140 |
: | +0.132 |
; | +0.131 |
Neg logit contributions | |
turrets | -1.188 |
riches | -1.165 |
seas | -1.163 |
ts | -1.160 |
fishes | -1.156 |
Token | race |
Token ID | 3234 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
| +0.237 |
" | +0.212 |
because | +0.206 |
. | +0.196 |
She | +0.196 |
Neg logit contributions | |
ts | -0.237 |
riches | -0.229 |
turrets | -0.225 |
pollen | -0.224 |
Majesty | -0.221 |
Token | had |
Token ID | 550 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
ts | +0.399 |
riches | +0.389 |
miles | +0.384 |
turrets | +0.384 |
pollen | +0.381 |
Neg logit contributions | |
| -0.148 |
" | -0.116 |
because | -0.112 |
She | -0.107 |
. | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
| +0.083 |
" | +0.074 |
because | +0.069 |
She | +0.066 |
. | +0.065 |
Neg logit contributions | |
ts | -0.130 |
isher | -0.127 |
pollen | -0.126 |
riches | -0.126 |
Majesty | -0.124 |
Token | leader |
Token ID | 3554 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ts | +0.056 |
isher | +0.053 |
pollen | +0.052 |
ief | +0.052 |
riches | +0.052 |
Neg logit contributions | |
| -0.063 |
" | -0.059 |
because | -0.055 |
. | -0.053 |
She | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
miles | +0.267 |
ts | +0.267 |
turrets | +0.261 |
stones | +0.260 |
seas | +0.260 |
Neg logit contributions | |
| -0.079 |
She | -0.059 |
" | -0.058 |
And | -0.053 |
They | -0.049 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
| +0.326 |
" | +0.288 |
because | +0.276 |
She | +0.259 |
. | +0.245 |
Neg logit contributions | |
ts | -0.536 |
ief | -0.533 |
riches | -0.527 |
isher | -0.522 |
ubb | -0.521 |
Token | to |
Token ID | 284 |
Feature activation | +6.45e-02 |
Pos logit contributions | |
| +0.019 |
She | +0.015 |
because | +0.014 |
" | +0.013 |
And | +0.013 |
Neg logit contributions | |
ts | -0.048 |
riches | -0.048 |
miles | -0.047 |
seas | -0.047 |
turrets | -0.047 |
Token | keep |
Token ID | 1394 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
| +0.120 |
" | +0.101 |
because | +0.101 |
She | +0.100 |
. | +0.099 |
Neg logit contributions | |
ts | -0.143 |
ounces | -0.139 |
pollen | -0.138 |
isher | -0.138 |
unnecessary | -0.138 |
Token | it |
Token ID | 340 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
ts | +0.022 |
isher | +0.022 |
pollen | +0.022 |
ounces | +0.022 |
turrets | +0.022 |
Neg logit contributions | |
| -0.015 |
" | -0.013 |
because | -0.013 |
. | -0.012 |
: | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ts | +0.185 |
riches | +0.183 |
pollen | +0.177 |
seas | +0.177 |
miles | +0.177 |
Neg logit contributions | |
| -0.081 |
" | -0.068 |
She | -0.065 |
because | -0.055 |
They | -0.054 |
Token | He |
Token ID | 679 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
because | +0.362 |
| +0.349 |
" | +0.297 |
. | +0.291 |
: | +0.278 |
Neg logit contributions | |
turrets | -1.112 |
stones | -1.086 |
ts | -1.078 |
seas | -1.065 |
riches | -1.064 |
Token | took |
Token ID | 1718 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
| +0.199 |
" | +0.170 |
because | +0.165 |
and | +0.163 |
: | +0.155 |
Neg logit contributions | |
decisions | -0.316 |
ief | -0.314 |
ocol | -0.311 |
ubb | -0.308 |
riches | -0.307 |
Token | it |
Token ID | 340 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
Majesty | +0.180 |
immers | +0.175 |
majesty | +0.174 |
ymes | +0.173 |
asis | +0.173 |
Neg logit contributions | |
| -0.064 |
and | -0.043 |
. | -0.043 |
, | -0.040 |
" | -0.039 |
Token | everywhere |
Token ID | 8347 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ts | +0.170 |
riches | +0.165 |
turrets | +0.163 |
pollen | +0.162 |
miles | +0.162 |
Neg logit contributions | |
| -0.095 |
" | -0.080 |
because | -0.079 |
She | -0.074 |
. | -0.070 |
Token | he |
Token ID | 339 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
ts | +0.072 |
miles | +0.069 |
stones | +0.067 |
seas | +0.066 |
turrets | +0.064 |
Neg logit contributions | |
| -0.039 |
They | -0.038 |
She | -0.037 |
Together | -0.035 |
One | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
ts | +0.240 |
miles | +0.234 |
pollen | +0.229 |
stones | +0.224 |
riches | +0.224 |
Neg logit contributions | |
| -0.102 |
" | -0.080 |
She | -0.078 |
because | -0.076 |
They | -0.067 |
Token | yard |
Token ID | 12699 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
ts | +0.053 |
riches | +0.051 |
ubb | +0.051 |
ounces | +0.051 |
isher | +0.050 |
Neg logit contributions | |
| -0.050 |
" | -0.043 |
because | -0.041 |
She | -0.041 |
. | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
ts | +0.217 |
miles | +0.214 |
turrets | +0.211 |
pollen | +0.208 |
riches | +0.208 |
Neg logit contributions | |
| -0.063 |
" | -0.042 |
She | -0.040 |
because | -0.039 |
: | -0.031 |
Token | feel |
Token ID | 1254 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
| +0.114 |
" | +0.098 |
because | +0.095 |
. | +0.094 |
She | +0.092 |
Neg logit contributions | |
riches | -0.149 |
ounces | -0.146 |
isher | -0.145 |
turrets | -0.141 |
ubb | -0.140 |
Token | better |
Token ID | 1365 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ounces | +0.175 |
ts | +0.175 |
turrets | +0.174 |
Majesty | +0.174 |
riches | +0.173 |
Neg logit contributions | |
| -0.134 |
because | -0.118 |
" | -0.115 |
. | -0.112 |
She | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
ts | +0.087 |
pollen | +0.082 |
miles | +0.082 |
riches | +0.082 |
fortune | +0.081 |
Neg logit contributions | |
| -0.027 |
" | -0.022 |
She | -0.022 |
Her | -0.016 |
� | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
because | +0.145 |
? | +0.143 |
: | +0.135 |
" | +0.068 |
. | +0.066 |
Neg logit contributions | |
pollen | -1.214 |
seas | -1.188 |
treasures | -1.182 |
riches | -1.167 |
stones | -1.161 |
Token |
|
Token ID | 198 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
because | +0.202 |
" | +0.167 |
She | +0.112 |
Why | +0.084 |
� | +0.080 |
Neg logit contributions | |
miles | -1.148 |
ts | -1.131 |
seas | -1.086 |
pollen | -1.064 |
riches | -1.056 |
Token | As |
Token ID | 1722 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
" | +0.718 |
| +0.717 |
: | +0.687 |
because | +0.679 |
She | +0.639 |
Neg logit contributions | |
miles | -0.695 |
ts | -0.644 |
seas | -0.630 |
pollen | -0.617 |
stones | -0.602 |
Token | B |
Token ID | 347 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
| +0.112 |
" | +0.111 |
: | +0.102 |
Why | +0.099 |
She | +0.096 |
Neg logit contributions | |
miles | -0.268 |
seas | -0.267 |
pollen | -0.251 |
stones | -0.242 |
weeds | -0.240 |
Token | ally |
Token ID | 453 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
| +0.100 |
" | +0.093 |
because | +0.087 |
She | +0.085 |
. | +0.083 |
Neg logit contributions | |
pollen | -0.075 |
ts | -0.074 |
riches | -0.074 |
isher | -0.072 |
miles | -0.071 |
Token | walks |
Token ID | 11114 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
| +0.066 |
because | +0.058 |
" | +0.057 |
. | +0.054 |
She | +0.053 |
Neg logit contributions | |
isher | -0.076 |
turrets | -0.072 |
riches | -0.071 |
Majesty | -0.071 |
ubb | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
ts | +0.106 |
miles | +0.103 |
seas | +0.102 |
riches | +0.100 |
pollen | +0.098 |
Neg logit contributions | |
| -0.064 |
" | -0.061 |
She | -0.053 |
: | -0.050 |
� | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
| +0.009 |
" | +0.008 |
because | +0.008 |
She | +0.008 |
: | +0.007 |
Neg logit contributions | |
ts | -0.007 |
miles | -0.007 |
seas | -0.007 |
riches | -0.007 |
pollen | -0.007 |
Token | special |
Token ID | 2041 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ts | +0.052 |
riches | +0.050 |
miles | +0.049 |
pollen | +0.049 |
turrets | +0.049 |
Neg logit contributions | |
| -0.070 |
" | -0.064 |
because | -0.062 |
She | -0.061 |
. | -0.058 |
Token | trail |
Token ID | 8025 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ts | +0.144 |
riches | +0.139 |
miles | +0.134 |
turrets | +0.134 |
pollen | +0.134 |
Neg logit contributions | |
| -0.266 |
" | -0.244 |
because | -0.239 |
She | -0.235 |
. | -0.226 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ts | +0.330 |
miles | +0.327 |
seas | +0.321 |
riches | +0.317 |
pollen | +0.312 |
Neg logit contributions | |
| -0.100 |
" | -0.082 |
She | -0.070 |
because | -0.060 |
: | -0.055 |
Token | One |
Token ID | 1881 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
because | +0.200 |
| +0.167 |
" | +0.141 |
. | +0.113 |
: | +0.104 |
Neg logit contributions | |
angles | -1.221 |
turrets | -1.216 |
seas | -1.211 |
stones | -1.211 |
riches | -1.203 |
Token | day |
Token ID | 1110 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
| +0.446 |
" | +0.410 |
because | +0.390 |
She | +0.390 |
: | +0.369 |
Neg logit contributions | |
ts | -0.340 |
riches | -0.339 |
pollen | -0.333 |
miles | -0.331 |
seas | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ts | +0.016 |
miles | +0.016 |
seas | +0.016 |
riches | +0.016 |
turrets | +0.016 |
Neg logit contributions | |
| -0.005 |
because | -0.004 |
" | -0.004 |
She | -0.003 |
They | -0.003 |
Token | Helen |
Token ID | 22695 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
| +0.452 |
" | +0.389 |
because | +0.381 |
She | +0.366 |
: | +0.348 |
Neg logit contributions | |
ts | -0.637 |
miles | -0.629 |
riches | -0.620 |
turrets | -0.616 |
seas | -0.616 |
Token | was |
Token ID | 373 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
ts | +0.179 |
riches | +0.177 |
ief | +0.176 |
ubb | +0.175 |
isher | +0.175 |
Neg logit contributions | |
| -0.120 |
" | -0.100 |
because | -0.099 |
She | -0.094 |
. | -0.093 |
Token | out |
Token ID | 503 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ts | +0.251 |
riches | +0.242 |
Majesty | +0.240 |
isher | +0.239 |
ief | +0.239 |
Neg logit contributions | |
| -0.131 |
" | -0.111 |
because | -0.106 |
. | -0.104 |
She | -0.099 |
Token | how |
Token ID | 703 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
ts | +0.323 |
riches | +0.318 |
miles | +0.314 |
pollen | +0.313 |
turrets | +0.312 |
Neg logit contributions | |
| -0.096 |
" | -0.069 |
because | -0.066 |
She | -0.063 |
: | -0.049 |
Token | long |
Token ID | 890 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
| +0.073 |
" | +0.066 |
. | +0.063 |
because | +0.060 |
She | +0.058 |
Neg logit contributions | |
isher | -0.107 |
ts | -0.106 |
ief | -0.106 |
Majesty | -0.105 |
riches | -0.104 |
Token | it |
Token ID | 340 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
ts | +0.137 |
riches | +0.133 |
pollen | +0.132 |
miles | +0.132 |
turrets | +0.131 |
Neg logit contributions | |
| -0.084 |
" | -0.071 |
because | -0.068 |
She | -0.066 |
: | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
ts | +0.169 |
riches | +0.166 |
turrets | +0.164 |
pollen | +0.163 |
miles | +0.163 |
Neg logit contributions | |
| -0.096 |
" | -0.081 |
because | -0.079 |
She | -0.075 |
. | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
| +0.046 |
She | +0.036 |
" | +0.028 |
They | +0.027 |
And | +0.022 |
Neg logit contributions | |
ts | -0.179 |
riches | -0.176 |
miles | -0.174 |
stones | -0.171 |
pollen | -0.170 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
because | +0.274 |
: | +0.202 |
; | +0.155 |
but | +0.154 |
? | +0.145 |
Neg logit contributions | |
pollen | -1.094 |
bons | -1.084 |
turrets | -1.084 |
nests | -1.081 |
riches | -1.073 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
because | +0.228 |
" | +0.160 |
She | +0.098 |
: | +0.076 |
They | +0.061 |
Neg logit contributions | |
miles | -1.142 |
ts | -1.109 |
seas | -1.090 |
riches | -1.071 |
ren | -1.049 |
Token | One |
Token ID | 3198 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
because | +0.546 |
| +0.529 |
" | +0.526 |
: | +0.482 |
. | +0.462 |
Neg logit contributions | |
miles | -0.868 |
ts | -0.831 |
confidence | -0.809 |
ief | -0.808 |
turrets | -0.802 |
Token | day |
Token ID | 1110 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
| +0.357 |
" | +0.315 |
because | +0.313 |
She | +0.297 |
. | +0.291 |
Neg logit contributions | |
ts | -0.369 |
riches | -0.354 |
turrets | -0.349 |
miles | -0.349 |
pollen | -0.347 |
Token | , |
Token ID | 11 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ts | +0.021 |
miles | +0.020 |
riches | +0.020 |
pollen | +0.020 |
turrets | +0.020 |
Neg logit contributions | |
| -0.006 |
" | -0.004 |
because | -0.004 |
She | -0.004 |
They | -0.003 |
Token | but |
Token ID | 475 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
| +0.161 |
" | +0.093 |
because | +0.079 |
She | +0.076 |
. | +0.052 |
Neg logit contributions | |
ts | -0.932 |
riches | -0.910 |
miles | -0.908 |
turrets | -0.905 |
pollen | -0.903 |
Token | he |
Token ID | 339 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
| +0.286 |
" | +0.243 |
because | +0.237 |
She | +0.211 |
. | +0.201 |
Neg logit contributions | |
ts | -0.607 |
riches | -0.600 |
pollen | -0.595 |
turrets | -0.591 |
Majesty | -0.591 |
Token | still |
Token ID | 991 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
| +0.066 |
because | +0.055 |
" | +0.055 |
She | +0.049 |
. | +0.048 |
Neg logit contributions | |
ts | -0.133 |
riches | -0.133 |
turrets | -0.131 |
ief | -0.130 |
pollen | -0.130 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
| +0.028 |
" | +0.024 |
She | +0.023 |
because | +0.023 |
. | +0.021 |
Neg logit contributions | |
ts | -0.039 |
riches | -0.037 |
turrets | -0.037 |
pollen | -0.037 |
miles | -0.037 |
Token | lonely |
Token ID | 21757 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
ts | +0.087 |
riches | +0.085 |
turrets | +0.083 |
pollen | +0.083 |
miles | +0.083 |
Neg logit contributions | |
| -0.074 |
" | -0.065 |
because | -0.063 |
She | -0.061 |
. | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ts | +0.196 |
miles | +0.189 |
riches | +0.189 |
treasures | +0.187 |
seas | +0.185 |
Neg logit contributions | |
| -0.054 |
She | -0.039 |
" | -0.037 |
They | -0.032 |
Her | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
because | +0.283 |
| +0.252 |
: | +0.242 |
" | +0.227 |
. | +0.226 |
Neg logit contributions | |
riches | -1.141 |
turrets | -1.117 |
ounces | -1.098 |
ts | -1.096 |
miles | -1.095 |
Token |
|
Token ID | 198 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
because | +0.167 |
" | +0.085 |
She | +0.072 |
. | +0.023 |
but | +0.023 |
Neg logit contributions | |
miles | -1.229 |
ts | -1.200 |
ounces | -1.180 |
riches | -1.178 |
turrets | -1.171 |
Token | Then |
Token ID | 6423 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
| +0.650 |
because | +0.597 |
" | +0.593 |
She | +0.570 |
. | +0.537 |
Neg logit contributions | |
ts | -0.845 |
miles | -0.825 |
riches | -0.819 |
turrets | -0.816 |
ounces | -0.811 |
Token | one |
Token ID | 530 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
| +0.166 |
" | +0.130 |
She | +0.121 |
because | +0.121 |
: | +0.102 |
Neg logit contributions | |
ts | -0.450 |
riches | -0.442 |
miles | -0.436 |
turrets | -0.435 |
seas | -0.428 |
Token | day |
Token ID | 1110 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
ts | +0.009 |
ief | +0.009 |
riches | +0.009 |
Majesty | +0.009 |
miles | +0.009 |
Neg logit contributions | |
| -0.007 |
because | -0.007 |
" | -0.006 |
. | -0.006 |
She | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
ts | +0.286 |
miles | +0.279 |
riches | +0.276 |
pollen | +0.274 |
seas | +0.271 |
Neg logit contributions | |
| -0.103 |
" | -0.083 |
She | -0.078 |
because | -0.076 |
They | -0.064 |
Token | he |
Token ID | 339 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
| +0.305 |
" | +0.248 |
because | +0.235 |
She | +0.209 |
. | +0.197 |
Neg logit contributions | |
isher | -0.820 |
ts | -0.813 |
riches | -0.812 |
ief | -0.806 |
turrets | -0.800 |
Token | noticed |
Token ID | 6810 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
| +0.089 |
" | +0.075 |
because | +0.074 |
. | +0.069 |
She | +0.068 |
Neg logit contributions | |
isher | -0.117 |
riches | -0.116 |
ts | -0.116 |
ief | -0.114 |
ounces | -0.114 |
Token | something |
Token ID | 1223 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
ts | +0.031 |
riches | +0.030 |
turrets | +0.030 |
pollen | +0.030 |
isher | +0.030 |
Neg logit contributions | |
| -0.018 |
" | -0.015 |
because | -0.015 |
She | -0.014 |
. | -0.014 |
Token | red |
Token ID | 2266 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ts | +0.055 |
riches | +0.052 |
pollen | +0.052 |
miles | +0.051 |
seas | +0.050 |
Neg logit contributions | |
| -0.085 |
" | -0.076 |
She | -0.075 |
because | -0.074 |
They | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
stones | +0.303 |
ts | +0.302 |
seas | +0.299 |
pollen | +0.296 |
miles | +0.295 |
Neg logit contributions | |
| -0.147 |
" | -0.109 |
She | -0.104 |
And | -0.098 |
because | -0.093 |
Token | He |
Token ID | 679 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
| +0.480 |
because | +0.375 |
" | +0.370 |
She | +0.338 |
. | +0.329 |
Neg logit contributions | |
ts | -1.169 |
riches | -1.154 |
turrets | -1.144 |
pollen | -1.135 |
miles | -1.129 |
Token | went |
Token ID | 1816 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
| +0.205 |
" | +0.176 |
because | +0.167 |
: | +0.158 |
She | +0.157 |
Neg logit contributions | |
isher | -0.311 |
ief | -0.308 |
ts | -0.307 |
riches | -0.306 |
decisions | -0.303 |
Token | closer |
Token ID | 5699 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ts | +0.010 |
pollen | +0.009 |
miles | +0.009 |
riches | +0.009 |
turrets | +0.009 |
Neg logit contributions | |
| -0.007 |
" | -0.006 |
because | -0.006 |
She | -0.006 |
. | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
miles | +0.422 |
ts | +0.416 |
stones | +0.412 |
pollen | +0.412 |
seas | +0.406 |
Neg logit contributions | |
| -0.124 |
" | -0.094 |
She | -0.090 |
because | -0.085 |
And | -0.077 |
Token | take |
Token ID | 1011 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
| +0.126 |
" | +0.103 |
because | +0.099 |
. | +0.094 |
She | +0.091 |
Neg logit contributions | |
isher | -0.172 |
ounces | -0.167 |
ymes | -0.167 |
Majesty | -0.166 |
ubb | -0.164 |
Token | with |
Token ID | 351 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
ts | +0.288 |
miles | +0.276 |
riches | +0.275 |
turrets | +0.271 |
isher | +0.268 |
Neg logit contributions | |
| -0.090 |
She | -0.070 |
" | -0.066 |
� | -0.056 |
because | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
| +0.070 |
" | +0.056 |
because | +0.052 |
She | +0.052 |
. | +0.050 |
Neg logit contributions | |
isher | -0.145 |
ts | -0.143 |
ounces | -0.142 |
plank | -0.142 |
pollen | -0.141 |
Token | fence |
Token ID | 13990 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ts | +0.065 |
isher | +0.062 |
ief | +0.062 |
ounces | +0.061 |
ieve | +0.060 |
Neg logit contributions | |
| -0.068 |
" | -0.062 |
because | -0.057 |
She | -0.057 |
. | -0.056 |
Token | around |
Token ID | 1088 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
turrets | +0.276 |
seas | +0.276 |
stones | +0.274 |
ts | +0.273 |
miles | +0.272 |
Neg logit contributions | |
| -0.086 |
" | -0.060 |
She | -0.055 |
because | -0.053 |
And | -0.049 |
Token | it |
Token ID | 340 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
ts | +0.235 |
miles | +0.228 |
turrets | +0.222 |
riches | +0.221 |
pollen | +0.217 |
Neg logit contributions | |
| -0.083 |
because | -0.067 |
She | -0.066 |
" | -0.065 |
And | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
pollen | +0.200 |
ts | +0.200 |
riches | +0.199 |
miles | +0.196 |
turrets | +0.194 |
Neg logit contributions | |
| -0.041 |
She | -0.029 |
" | -0.027 |
because | -0.026 |
And | -0.019 |
Token | The |
Token ID | 383 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
because | +0.435 |
: | +0.374 |
. | +0.369 |
; | +0.366 |
? | +0.361 |
Neg logit contributions | |
turrets | -0.985 |
seas | -0.937 |
riches | -0.923 |
nests | -0.922 |
fishes | -0.914 |
Token | dad |
Token ID | 9955 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
| +0.248 |
" | +0.223 |
because | +0.214 |
She | +0.199 |
. | +0.198 |
Neg logit contributions | |
ts | -0.309 |
ief | -0.297 |
ounces | -0.293 |
ieve | -0.292 |
isher | -0.290 |
Token | was |
Token ID | 373 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
ts | +0.188 |
riches | +0.184 |
turrets | +0.181 |
pollen | +0.180 |
miles | +0.180 |
Neg logit contributions | |
| -0.095 |
" | -0.079 |
because | -0.077 |
She | -0.073 |
. | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
| +0.098 |
" | +0.086 |
because | +0.082 |
She | +0.077 |
. | +0.073 |
Neg logit contributions | |
ts | -0.148 |
ounces | -0.146 |
isher | -0.146 |
riches | -0.145 |
pollen | -0.144 |
Token | tall |
Token ID | 7331 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ts | +0.051 |
riches | +0.050 |
turrets | +0.049 |
pollen | +0.048 |
miles | +0.048 |
Neg logit contributions | |
| -0.062 |
" | -0.055 |
because | -0.055 |
She | -0.054 |
. | -0.051 |
Token | over |
Token ID | 625 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
ts | +0.115 |
riches | +0.115 |
turrets | +0.112 |
Majesty | +0.112 |
pollen | +0.112 |
Neg logit contributions | |
| -0.069 |
" | -0.058 |
because | -0.057 |
She | -0.052 |
. | -0.052 |
Token | anything |
Token ID | 1997 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
Majesty | +0.214 |
riches | +0.212 |
pollen | +0.210 |
ts | +0.210 |
ubb | +0.208 |
Neg logit contributions | |
| -0.108 |
" | -0.087 |
because | -0.083 |
and | -0.079 |
. | -0.079 |
Token | that |
Token ID | 326 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ts | +0.182 |
miles | +0.177 |
riches | +0.177 |
pollen | +0.176 |
seas | +0.173 |
Neg logit contributions | |
| -0.074 |
" | -0.060 |
She | -0.058 |
because | -0.053 |
They | -0.048 |
Token | he |
Token ID | 339 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
| +0.212 |
because | +0.180 |
" | +0.175 |
. | +0.157 |
She | +0.157 |
Neg logit contributions | |
Majesty | -0.361 |
riches | -0.352 |
turrets | -0.351 |
ts | -0.351 |
isher | -0.349 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.78e-03 |
Pos logit contributions | |
| +0.080 |
because | +0.068 |
" | +0.067 |
. | +0.062 |
She | +0.059 |
Neg logit contributions | |
riches | -0.134 |
turrets | -0.133 |
pollen | -0.130 |
ocol | -0.130 |
decisions | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ts | +0.023 |
miles | +0.022 |
riches | +0.022 |
turrets | +0.022 |
seas | +0.022 |
Neg logit contributions | |
| -0.011 |
She | -0.009 |
" | -0.009 |
because | -0.009 |
They | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
because | +0.425 |
| +0.395 |
: | +0.344 |
; | +0.339 |
. | +0.337 |
Neg logit contributions | |
turrets | -1.054 |
angles | -0.980 |
ounces | -0.978 |
patterns | -0.967 |
ts | -0.960 |
Token | especially |
Token ID | 2592 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
| +0.200 |
" | +0.173 |
because | +0.166 |
. | +0.152 |
and | +0.150 |
Neg logit contributions | |
riches | -0.322 |
ocol | -0.319 |
ief | -0.317 |
isher | -0.313 |
turrets | -0.312 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
riches | +0.102 |
turrets | +0.102 |
ts | +0.101 |
isher | +0.100 |
Majesty | +0.099 |
Neg logit contributions | |
| -0.063 |
" | -0.055 |
because | -0.053 |
She | -0.048 |
. | -0.047 |
Token | kicking |
Token ID | 17997 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
ts | +0.026 |
riches | +0.025 |
miles | +0.025 |
pollen | +0.024 |
turrets | +0.024 |
Neg logit contributions | |
| -0.021 |
" | -0.018 |
because | -0.018 |
She | -0.018 |
. | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
riches | +0.207 |
turrets | +0.205 |
ts | +0.205 |
Majesty | +0.205 |
isher | +0.205 |
Neg logit contributions | |
| -0.120 |
" | -0.101 |
because | -0.098 |
. | -0.093 |
She | -0.089 |
Token | She |
Token ID | 1375 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
| +0.252 |
because | +0.149 |
" | +0.121 |
. | +0.110 |
: | +0.091 |
Neg logit contributions | |
Majesty | -1.313 |
turrets | -1.306 |
riches | -1.297 |
ts | -1.296 |
pollen | -1.285 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
| +0.210 |
because | +0.181 |
" | +0.176 |
She | +0.165 |
: | +0.164 |
Neg logit contributions | |
riches | -0.357 |
pollen | -0.354 |
ts | -0.354 |
miles | -0.352 |
ief | -0.349 |
Token | stupid |
Token ID | 8531 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
ts | +0.079 |
isher | +0.077 |
turrets | +0.077 |
riches | +0.076 |
ounces | +0.076 |
Neg logit contributions | |
| -0.071 |
because | -0.065 |
" | -0.063 |
She | -0.060 |
. | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ts | +0.220 |
decisions | +0.217 |
riches | +0.216 |
treasures | +0.216 |
miles | +0.216 |
Neg logit contributions | |
| -0.077 |
" | -0.050 |
She | -0.046 |
They | -0.039 |
: | -0.036 |
Token | ashamed |
Token ID | 22461 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
| +0.295 |
because | +0.288 |
" | +0.275 |
She | +0.261 |
. | +0.247 |
Neg logit contributions | |
plank | -0.571 |
turrets | -0.571 |
isher | -0.570 |
riches | -0.568 |
ounces | -0.564 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
| +0.017 |
� | +0.012 |
" | +0.011 |
o | +0.011 |
They | +0.010 |
Neg logit contributions | |
decisions | -0.038 |
risks | -0.037 |
notes | -0.037 |
choices | -0.037 |
emotion | -0.036 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
| +0.300 |
because | +0.223 |
. | +0.186 |
" | +0.172 |
? | +0.171 |
Neg logit contributions | |
Majesty | -1.209 |
turrets | -1.146 |
floors | -1.144 |
riches | -1.140 |
pollen | -1.138 |
Token | teacher |
Token ID | 4701 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
| +0.216 |
" | +0.186 |
because | +0.181 |
. | +0.168 |
She | +0.158 |
Neg logit contributions | |
ts | -0.404 |
ief | -0.396 |
isher | -0.393 |
miles | -0.390 |
ounces | -0.387 |
Token | helped |
Token ID | 4193 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
ts | +0.208 |
riches | +0.198 |
miles | +0.193 |
turrets | +0.192 |
ief | +0.191 |
Neg logit contributions | |
| -0.151 |
" | -0.126 |
because | -0.124 |
She | -0.122 |
They | -0.112 |
Token | her |
Token ID | 607 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
| +0.094 |
" | +0.081 |
because | +0.077 |
She | +0.073 |
: | +0.069 |
Neg logit contributions | |
ts | -0.158 |
pollen | -0.149 |
riches | -0.148 |
miles | -0.148 |
turrets | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
ts | +0.111 |
riches | +0.107 |
turrets | +0.105 |
pollen | +0.105 |
miles | +0.105 |
Neg logit contributions | |
| -0.113 |
" | -0.100 |
because | -0.098 |
She | -0.095 |
. | -0.091 |
Token | a |
Token ID | 257 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
| +0.080 |
" | +0.070 |
because | +0.067 |
She | +0.064 |
. | +0.060 |
Neg logit contributions | |
ts | -0.135 |
riches | -0.132 |
miles | -0.130 |
turrets | -0.130 |
pollen | -0.130 |
Token | fire |
Token ID | 2046 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
ts | +0.059 |
riches | +0.057 |
turrets | +0.056 |
pollen | +0.056 |
miles | +0.056 |
Neg logit contributions | |
| -0.068 |
" | -0.061 |
because | -0.060 |
She | -0.058 |
. | -0.056 |
Token | man |
Token ID | 805 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
ts | +0.074 |
isher | +0.069 |
an | +0.068 |
plank | +0.067 |
riches | +0.067 |
Neg logit contributions | |
| -0.110 |
She | -0.104 |
" | -0.096 |
because | -0.092 |
� | -0.092 |
Token | named |
Token ID | 3706 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
ts | +0.084 |
an | +0.074 |
miles | +0.073 |
plank | +0.073 |
riches | +0.073 |
Neg logit contributions | |
She | -0.055 |
� | -0.054 |
| -0.053 |
" | -0.053 |
They | -0.046 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
| +0.211 |
because | +0.174 |
She | +0.173 |
" | +0.171 |
: | +0.153 |
Neg logit contributions | |
ts | -0.480 |
riches | -0.458 |
turrets | -0.457 |
miles | -0.454 |
seas | -0.450 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ts | +0.030 |
pirate | +0.025 |
crown | +0.024 |
riches | +0.024 |
ck | +0.023 |
Neg logit contributions | |
She | -0.015 |
� | -0.014 |
Together | -0.013 |
" | -0.012 |
� | -0.012 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
| +0.500 |
: | +0.453 |
because | +0.440 |
" | +0.412 |
. | +0.407 |
Neg logit contributions | |
ts | -1.009 |
turrets | -0.957 |
miles | -0.920 |
stones | -0.916 |
riches | -0.913 |
Token | was |
Token ID | 373 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
ts | +0.028 |
riches | +0.025 |
turrets | +0.024 |
treasures | +0.024 |
seas | +0.023 |
Neg logit contributions | |
| -0.019 |
She | -0.018 |
" | -0.017 |
because | -0.017 |
but | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
| +0.078 |
" | +0.066 |
because | +0.063 |
She | +0.060 |
. | +0.056 |
Neg logit contributions | |
ts | -0.156 |
riches | -0.153 |
turrets | -0.151 |
pollen | -0.150 |
miles | -0.150 |
Token | brave |
Token ID | 14802 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
miles | +0.006 |
ts | +0.006 |
isher | +0.006 |
turrets | +0.006 |
riches | +0.006 |
Neg logit contributions | |
| -0.007 |
" | -0.006 |
because | -0.006 |
. | -0.006 |
She | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ts | +0.232 |
riches | +0.227 |
miles | +0.225 |
pollen | +0.223 |
turrets | +0.223 |
Neg logit contributions | |
| -0.045 |
" | -0.028 |
She | -0.024 |
because | -0.021 |
: | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
| +0.201 |
" | +0.176 |
because | +0.169 |
. | +0.151 |
She | +0.151 |
Neg logit contributions | |
isher | -0.362 |
ts | -0.358 |
ief | -0.353 |
Majesty | -0.352 |
turrets | -0.351 |
Token | house |
Token ID | 2156 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ts | +0.046 |
ief | +0.046 |
isher | +0.045 |
ocol | +0.043 |
ubb | +0.043 |
Neg logit contributions | |
| -0.049 |
" | -0.044 |
because | -0.042 |
. | -0.041 |
and | -0.040 |
Token | had |
Token ID | 550 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
ts | +0.291 |
riches | +0.287 |
pollen | +0.284 |
turrets | +0.282 |
miles | +0.281 |
Neg logit contributions | |
| -0.127 |
" | -0.106 |
because | -0.102 |
She | -0.095 |
. | -0.091 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
| +0.083 |
" | +0.077 |
because | +0.073 |
. | +0.071 |
She | +0.068 |
Neg logit contributions | |
isher | -0.112 |
ts | -0.111 |
ief | -0.109 |
ieve | -0.109 |
Majesty | -0.108 |
Token | piano |
Token ID | 19132 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ts | +0.064 |
ief | +0.060 |
isher | +0.059 |
miles | +0.057 |
lled | +0.057 |
Neg logit contributions | |
| -0.070 |
" | -0.066 |
because | -0.062 |
. | -0.060 |
: | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ts | +0.408 |
miles | +0.398 |
riches | +0.397 |
turrets | +0.397 |
pollen | +0.392 |
Neg logit contributions | |
| -0.144 |
" | -0.102 |
She | -0.096 |
because | -0.095 |
They | -0.077 |
Token | So |
Token ID | 1406 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
| +0.415 |
because | +0.411 |
: | +0.352 |
" | +0.348 |
. | +0.346 |
Neg logit contributions | |
ts | -1.085 |
pollen | -1.085 |
miles | -1.068 |
turrets | -1.065 |
riches | -1.060 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
| +0.296 |
" | +0.248 |
because | +0.236 |
She | +0.220 |
. | +0.209 |
Neg logit contributions | |
ts | -0.651 |
riches | -0.639 |
turrets | -0.630 |
isher | -0.629 |
pollen | -0.626 |
Token | rat |
Token ID | 4227 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ts | +0.040 |
isher | +0.039 |
turrets | +0.039 |
ief | +0.039 |
riches | +0.039 |
Neg logit contributions | |
| -0.046 |
" | -0.042 |
because | -0.040 |
She | -0.038 |
. | -0.038 |
Token | decided |
Token ID | 3066 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
ts | +0.334 |
riches | +0.328 |
isher | +0.324 |
ief | +0.323 |
turrets | +0.322 |
Neg logit contributions | |
| -0.232 |
" | -0.205 |
because | -0.200 |
. | -0.187 |
She | -0.185 |
Token | to |
Token ID | 284 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
| +0.021 |
because | +0.015 |
" | +0.015 |
She | +0.014 |
. | +0.012 |
Neg logit contributions | |
ts | -0.065 |
riches | -0.064 |
miles | -0.064 |
turrets | -0.063 |
pollen | -0.062 |
Token | little |
Token ID | 1310 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
ts | +0.067 |
riches | +0.065 |
pollen | +0.063 |
turrets | +0.063 |
miles | +0.063 |
Neg logit contributions | |
| -0.082 |
" | -0.073 |
because | -0.072 |
She | -0.071 |
. | -0.067 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ts | +0.113 |
riches | +0.107 |
turrets | +0.105 |
ounces | +0.105 |
Majesty | +0.105 |
Neg logit contributions | |
| -0.136 |
" | -0.123 |
because | -0.122 |
She | -0.119 |
. | -0.114 |
Token | noticed |
Token ID | 6810 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ts | +0.409 |
riches | +0.400 |
turrets | +0.395 |
miles | +0.395 |
pollen | +0.394 |
Neg logit contributions | |
| -0.173 |
" | -0.144 |
because | -0.137 |
She | -0.129 |
. | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ts | +0.037 |
riches | +0.036 |
miles | +0.036 |
turrets | +0.036 |
pollen | +0.036 |
Neg logit contributions | |
| -0.020 |
" | -0.017 |
because | -0.017 |
She | -0.016 |
. | -0.014 |
Token | pond |
Token ID | 16723 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
ts | +0.070 |
ief | +0.066 |
isher | +0.065 |
riches | +0.065 |
miles | +0.065 |
Neg logit contributions | |
| -0.074 |
" | -0.068 |
because | -0.065 |
She | -0.062 |
. | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ts | +0.219 |
pollen | +0.215 |
miles | +0.214 |
stones | +0.210 |
seas | +0.210 |
Neg logit contributions | |
| -0.134 |
" | -0.113 |
She | -0.107 |
And | -0.104 |
because | -0.098 |
Token | It |
Token ID | 632 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
| +0.247 |
because | +0.182 |
" | +0.134 |
. | +0.131 |
: | +0.120 |
Neg logit contributions | |
pollen | -1.289 |
turrets | -1.267 |
riches | -1.251 |
ts | -1.238 |
stones | -1.234 |
Token | was |
Token ID | 373 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
| +0.027 |
" | +0.022 |
because | +0.022 |
She | +0.021 |
. | +0.019 |
Neg logit contributions | |
ts | -0.053 |
riches | -0.051 |
pollen | -0.051 |
turrets | -0.051 |
miles | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
| +0.100 |
" | +0.087 |
because | +0.085 |
She | +0.082 |
. | +0.078 |
Neg logit contributions | |
ts | -0.125 |
riches | -0.121 |
pollen | -0.120 |
turrets | -0.119 |
miles | -0.119 |
Token | big |
Token ID | 1263 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
ts | +0.063 |
riches | +0.060 |
ief | +0.059 |
turrets | +0.059 |
isher | +0.059 |
Neg logit contributions | |
| -0.070 |
" | -0.063 |
because | -0.061 |
She | -0.058 |
. | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ts | +0.181 |
riches | +0.175 |
turrets | +0.172 |
ief | +0.171 |
ounces | +0.171 |
Neg logit contributions | |
| -0.140 |
" | -0.123 |
because | -0.123 |
She | -0.114 |
. | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
| +0.077 |
" | +0.062 |
because | +0.061 |
She | +0.059 |
. | +0.054 |
Neg logit contributions | |
ts | -0.153 |
riches | -0.148 |
isher | -0.146 |
turrets | -0.146 |
pollen | -0.146 |
Token | little |
Token ID | 1310 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
ts | +0.056 |
riches | +0.055 |
pollen | +0.053 |
turrets | +0.053 |
miles | +0.053 |
Neg logit contributions | |
| -0.073 |
" | -0.066 |
because | -0.066 |
She | -0.064 |
: | -0.061 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ts | +0.105 |
riches | +0.100 |
miles | +0.099 |
ounces | +0.099 |
turrets | +0.099 |
Neg logit contributions | |
| -0.129 |
" | -0.119 |
because | -0.118 |
She | -0.114 |
. | -0.112 |
Token | called |
Token ID | 1444 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ts | +0.270 |
pollen | +0.248 |
miles | +0.246 |
nests | +0.239 |
riches | +0.237 |
Neg logit contributions | |
| -0.230 |
" | -0.224 |
She | -0.209 |
� | -0.200 |
They | -0.196 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
| +0.215 |
" | +0.185 |
because | +0.181 |
She | +0.169 |
: | +0.165 |
Neg logit contributions | |
ts | -0.295 |
pollen | -0.288 |
miles | -0.286 |
riches | -0.286 |
turrets | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ts | +0.092 |
treasures | +0.085 |
pollen | +0.084 |
riches | +0.084 |
miles | +0.082 |
Neg logit contributions | |
| -0.032 |
" | -0.030 |
She | -0.028 |
but | -0.025 |
Together | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
| +0.268 |
because | +0.234 |
: | +0.214 |
" | +0.205 |
? | +0.187 |
Neg logit contributions | |
miles | -1.144 |
pollen | -1.142 |
turrets | -1.126 |
ts | -1.112 |
nests | -1.111 |
Token | was |
Token ID | 373 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
| +0.220 |
" | +0.195 |
because | +0.187 |
She | +0.180 |
. | +0.167 |
Neg logit contributions | |
ts | -0.319 |
riches | -0.302 |
pollen | -0.298 |
miles | -0.297 |
turrets | -0.296 |
Token | three |
Token ID | 1115 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
| +0.093 |
" | +0.081 |
because | +0.080 |
She | +0.076 |
. | +0.069 |
Neg logit contributions | |
ts | -0.150 |
riches | -0.146 |
ounces | -0.145 |
isher | -0.145 |
turrets | -0.144 |
Token | years |
Token ID | 812 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
ts | +0.359 |
riches | +0.343 |
turrets | +0.334 |
pollen | +0.333 |
miles | +0.333 |
Neg logit contributions | |
| -0.366 |
" | -0.325 |
She | -0.312 |
because | -0.309 |
: | -0.284 |
Token | old |
Token ID | 1468 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
| +0.183 |
" | +0.167 |
because | +0.164 |
She | +0.160 |
. | +0.156 |
Neg logit contributions | |
ts | -0.124 |
riches | -0.118 |
miles | -0.116 |
turrets | -0.115 |
pollen | -0.115 |
Token | ble |
Token ID | 903 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ts | +0.136 |
turrets | +0.124 |
riches | +0.123 |
isher | +0.121 |
Majesty | +0.119 |
Neg logit contributions | |
| -0.412 |
" | -0.383 |
because | -0.381 |
She | -0.375 |
They | -0.362 |
Token | that |
Token ID | 326 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ts | +0.350 |
seas | +0.341 |
pollen | +0.339 |
miles | +0.336 |
riches | +0.332 |
Neg logit contributions | |
| -0.111 |
She | -0.087 |
" | -0.086 |
They | -0.069 |
because | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
| +0.213 |
" | +0.185 |
because | +0.176 |
She | +0.169 |
. | +0.160 |
Neg logit contributions | |
ts | -0.345 |
riches | -0.337 |
ief | -0.332 |
isher | -0.332 |
turrets | -0.331 |
Token | very |
Token ID | 845 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
| +0.090 |
" | +0.076 |
because | +0.074 |
She | +0.072 |
. | +0.066 |
Neg logit contributions | |
ts | -0.141 |
riches | -0.137 |
pollen | -0.136 |
turrets | -0.136 |
miles | -0.135 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ts | +0.013 |
ief | +0.013 |
miles | +0.013 |
isher | +0.013 |
riches | +0.012 |
Neg logit contributions | |
| -0.013 |
" | -0.012 |
because | -0.012 |
. | -0.011 |
She | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
seas | +0.281 |
riches | +0.276 |
ts | +0.271 |
treasures | +0.270 |
decisions | +0.269 |
Neg logit contributions | |
| -0.100 |
She | -0.071 |
" | -0.063 |
And | -0.054 |
� | -0.053 |
Token | It |
Token ID | 632 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
| +0.505 |
because | +0.466 |
. | +0.421 |
: | +0.418 |
" | +0.416 |
Neg logit contributions | |
turrets | -1.006 |
riches | -0.976 |
miles | -0.948 |
ounces | -0.941 |
ts | -0.940 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
| +0.030 |
" | +0.026 |
because | +0.025 |
She | +0.024 |
: | +0.022 |
Neg logit contributions | |
ts | -0.051 |
pollen | -0.050 |
riches | -0.049 |
turrets | -0.049 |
miles | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
| +0.019 |
" | +0.012 |
because | +0.011 |
. | +0.007 |
She | +0.006 |
Neg logit contributions | |
ts | -0.114 |
isher | -0.113 |
ief | -0.112 |
Majesty | -0.111 |
ubb | -0.110 |
Token | go |
Token ID | 467 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
| +0.132 |
because | +0.107 |
. | +0.106 |
" | +0.106 |
She | +0.106 |
Neg logit contributions | |
isher | -0.164 |
ts | -0.156 |
ounces | -0.155 |
riches | -0.151 |
ief | -0.150 |
Token | on |
Token ID | 319 |
Feature activation | +7.20e-03 |
Pos logit contributions | |
ts | +0.133 |
miles | +0.131 |
riches | +0.131 |
seas | +0.130 |
pollen | +0.128 |
Neg logit contributions | |
| -0.068 |
" | -0.059 |
She | -0.055 |
because | -0.053 |
: | -0.048 |
Token | bunny |
Token ID | 44915 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
ts | +0.190 |
riches | +0.182 |
turrets | +0.180 |
miles | +0.179 |
pollen | +0.177 |
Neg logit contributions | |
| -0.225 |
" | -0.203 |
because | -0.201 |
She | -0.194 |
. | -0.188 |
Token | who |
Token ID | 508 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
pollen | +0.203 |
ts | +0.199 |
miles | +0.192 |
riches | +0.191 |
seas | +0.190 |
Neg logit contributions | |
| -0.105 |
" | -0.094 |
She | -0.093 |
� | -0.080 |
Her | -0.079 |
Token | always |
Token ID | 1464 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
| +0.204 |
" | +0.175 |
because | +0.170 |
She | +0.163 |
. | +0.153 |
Neg logit contributions | |
ts | -0.318 |
riches | -0.310 |
pollen | -0.305 |
turrets | -0.304 |
miles | -0.304 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
| +0.041 |
" | +0.035 |
because | +0.035 |
She | +0.033 |
. | +0.031 |
Neg logit contributions | |
ts | -0.057 |
riches | -0.056 |
turrets | -0.055 |
pollen | -0.055 |
miles | -0.055 |
Token | adventures |
Token ID | 17545 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
| +0.020 |
" | +0.014 |
because | +0.013 |
She | +0.011 |
. | +0.010 |
Neg logit contributions | |
ts | -0.091 |
isher | -0.089 |
riches | -0.089 |
turrets | -0.089 |
ief | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ts | +0.115 |
riches | +0.112 |
miles | +0.111 |
seas | +0.111 |
pollen | +0.109 |
Neg logit contributions | |
| -0.039 |
" | -0.033 |
She | -0.031 |
because | -0.025 |
: | -0.024 |
Token | One |
Token ID | 1881 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
because | +0.360 |
: | +0.310 |
" | +0.293 |
| +0.277 |
. | +0.272 |
Neg logit contributions | |
riches | -1.051 |
turrets | -1.046 |
miles | -1.025 |
seas | -1.006 |
ounces | -1.005 |
Token | day |
Token ID | 1110 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
| +0.432 |
" | +0.391 |
because | +0.378 |
She | +0.373 |
. | +0.354 |
Neg logit contributions | |
ts | -0.369 |
riches | -0.363 |
pollen | -0.357 |
miles | -0.353 |
turrets | -0.351 |
Token | he |
Token ID | 339 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ts | +0.019 |
riches | +0.018 |
miles | +0.018 |
turrets | +0.018 |
seas | +0.018 |
Neg logit contributions | |
| -0.007 |
She | -0.006 |
because | -0.005 |
" | -0.005 |
They | -0.004 |
Token | went |
Token ID | 1816 |
Feature activation | -3.16e-03 |
Pos logit contributions | |
| +0.101 |
" | +0.087 |
because | +0.085 |
She | +0.082 |
. | +0.079 |
Neg logit contributions | |
ts | -0.122 |
riches | -0.119 |
turrets | -0.118 |
isher | -0.118 |
ief | -0.116 |
Token | on |
Token ID | 319 |
Feature activation | +7.32e-03 |
Pos logit contributions | |
pollen | +0.008 |
miles | +0.008 |
seas | +0.008 |
riches | +0.007 |
stones | +0.007 |
Neg logit contributions | |
| -0.004 |
" | -0.003 |
She | -0.003 |
because | -0.003 |
They | -0.003 |
Token | everyone |
Token ID | 2506 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
| +0.430 |
" | +0.391 |
because | +0.381 |
. | +0.371 |
She | +0.365 |
Neg logit contributions | |
ief | -0.430 |
isher | -0.426 |
ubb | -0.419 |
ts | -0.416 |
ieve | -0.406 |
Token | would |
Token ID | 561 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
ts | +0.241 |
riches | +0.233 |
pollen | +0.229 |
turrets | +0.227 |
miles | +0.226 |
Neg logit contributions | |
| -0.139 |
" | -0.116 |
because | -0.114 |
She | -0.111 |
: | -0.098 |
Token | sing |
Token ID | 1702 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
| +0.142 |
" | +0.127 |
because | +0.124 |
She | +0.120 |
. | +0.115 |
Neg logit contributions | |
ts | -0.142 |
riches | -0.138 |
turrets | -0.135 |
pollen | -0.135 |
miles | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
ts | +0.158 |
riches | +0.155 |
turrets | +0.153 |
pollen | +0.153 |
miles | +0.153 |
Neg logit contributions | |
| -0.063 |
" | -0.050 |
because | -0.048 |
She | -0.045 |
. | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
| +0.117 |
" | +0.101 |
because | +0.100 |
. | +0.095 |
She | +0.094 |
Neg logit contributions | |
isher | -0.150 |
ts | -0.148 |
riches | -0.145 |
turrets | -0.144 |
pollen | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ts | +0.167 |
riches | +0.166 |
pollen | +0.161 |
turrets | +0.161 |
Majesty | +0.160 |
Neg logit contributions | |
| -0.078 |
" | -0.064 |
She | -0.061 |
because | -0.060 |
: | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
because | +0.275 |
: | +0.196 |
? | +0.194 |
; | +0.169 |
. | +0.155 |
Neg logit contributions | |
turrets | -1.069 |
pollen | -1.046 |
riches | -1.037 |
angles | -1.035 |
seas | -1.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
because | +0.231 |
" | +0.153 |
She | +0.093 |
: | +0.069 |
but | +0.066 |
Neg logit contributions | |
miles | -1.127 |
ts | -1.093 |
seas | -1.081 |
riches | -1.058 |
ren | -1.035 |
Token | On |
Token ID | 2202 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
because | +0.489 |
| +0.488 |
" | +0.462 |
. | +0.419 |
: | +0.413 |
Neg logit contributions | |
miles | -0.930 |
ts | -0.897 |
turrets | -0.893 |
pollen | -0.868 |
confidence | -0.867 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
| +0.232 |
" | +0.195 |
because | +0.188 |
She | +0.180 |
. | +0.172 |
Neg logit contributions | |
ts | -0.400 |
riches | -0.392 |
ounces | -0.385 |
turrets | -0.385 |
isher | -0.384 |
Token | morning |
Token ID | 3329 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ts | +0.035 |
riches | +0.034 |
turrets | +0.033 |
miles | +0.033 |
pollen | +0.033 |
Neg logit contributions | |
| -0.045 |
" | -0.040 |
because | -0.039 |
She | -0.039 |
. | -0.037 |
Token | where |
Token ID | 810 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
riches | +0.221 |
ts | +0.217 |
miles | +0.216 |
seas | +0.215 |
treasures | +0.214 |
Neg logit contributions | |
| -0.072 |
She | -0.057 |
" | -0.057 |
because | -0.046 |
They | -0.043 |
Token | he |
Token ID | 339 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
| +0.085 |
" | +0.068 |
because | +0.061 |
. | +0.059 |
She | +0.054 |
Neg logit contributions | |
isher | -0.250 |
Majesty | -0.242 |
ief | -0.241 |
ounces | -0.240 |
ts | -0.239 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
| +0.073 |
because | +0.061 |
" | +0.061 |
. | +0.057 |
She | +0.055 |
Neg logit contributions | |
turrets | -0.120 |
ts | -0.120 |
riches | -0.119 |
isher | -0.119 |
pollen | -0.118 |
Token | at |
Token ID | 379 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
ts | +0.113 |
riches | +0.110 |
turrets | +0.109 |
pollen | +0.109 |
miles | +0.108 |
Neg logit contributions | |
| -0.047 |
" | -0.038 |
because | -0.037 |
She | -0.035 |
. | -0.032 |
Token | home |
Token ID | 1363 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
| +0.084 |
because | +0.073 |
" | +0.072 |
. | +0.069 |
: | +0.062 |
Neg logit contributions | |
isher | -0.122 |
ts | -0.121 |
turrets | -0.121 |
ief | -0.120 |
confidence | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ts | +0.396 |
riches | +0.389 |
turrets | +0.385 |
pollen | +0.384 |
miles | +0.384 |
Neg logit contributions | |
| -0.054 |
" | -0.029 |
because | -0.025 |
She | -0.019 |
. | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
because | +0.181 |
| +0.125 |
" | +0.103 |
: | +0.087 |
She | +0.081 |
Neg logit contributions | |
ts | -1.320 |
riches | -1.310 |
seas | -1.291 |
turrets | -1.290 |
pollen | -1.286 |
Token |
|
Token ID | 198 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
because | +0.209 |
" | +0.114 |
She | +0.099 |
but | +0.060 |
; | +0.052 |
Neg logit contributions | |
ts | -1.183 |
miles | -1.167 |
seas | -1.142 |
pollen | -1.127 |
riches | -1.125 |
Token | So |
Token ID | 2396 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
| +0.597 |
because | +0.535 |
" | +0.531 |
She | +0.495 |
. | +0.480 |
Neg logit contributions | |
ts | -0.925 |
miles | -0.892 |
riches | -0.883 |
turrets | -0.878 |
pollen | -0.870 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
| +0.182 |
" | +0.137 |
because | +0.127 |
She | +0.120 |
. | +0.099 |
Neg logit contributions | |
ts | -0.660 |
riches | -0.650 |
miles | -0.639 |
pollen | -0.639 |
turrets | -0.638 |
Token | the |
Token ID | 262 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
| +0.435 |
" | +0.372 |
because | +0.362 |
She | +0.346 |
. | +0.327 |
Neg logit contributions | |
ts | -0.689 |
riches | -0.673 |
turrets | -0.663 |
pollen | -0.661 |
miles | -0.659 |
Token | a |
Token ID | 257 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
| +0.080 |
" | +0.068 |
because | +0.066 |
She | +0.063 |
. | +0.059 |
Neg logit contributions | |
ts | -0.141 |
riches | -0.138 |
turrets | -0.136 |
pollen | -0.136 |
miles | -0.136 |
Token | little |
Token ID | 1310 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
ts | +0.061 |
riches | +0.059 |
turrets | +0.058 |
pollen | +0.058 |
miles | +0.058 |
Neg logit contributions | |
| -0.069 |
" | -0.062 |
because | -0.061 |
She | -0.059 |
. | -0.057 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ts | +0.105 |
riches | +0.102 |
miles | +0.101 |
ounces | +0.100 |
ief | +0.100 |
Neg logit contributions | |
| -0.119 |
because | -0.110 |
" | -0.110 |
She | -0.105 |
. | -0.103 |
Token | named |
Token ID | 3706 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ts | +0.298 |
pollen | +0.281 |
miles | +0.273 |
riches | +0.266 |
isher | +0.265 |
Neg logit contributions | |
| -0.219 |
" | -0.207 |
She | -0.190 |
� | -0.181 |
They | -0.176 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
| +0.253 |
because | +0.219 |
" | +0.216 |
: | +0.203 |
She | +0.191 |
Neg logit contributions | |
ts | -0.391 |
pollen | -0.385 |
miles | -0.374 |
turrets | -0.367 |
riches | -0.362 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ts | +0.105 |
an | +0.095 |
treasures | +0.094 |
riches | +0.094 |
miles | +0.093 |
Neg logit contributions | |
" | -0.039 |
� | -0.035 |
She | -0.034 |
| -0.033 |
Together | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
| +0.280 |
: | +0.218 |
because | +0.210 |
" | +0.205 |
? | +0.161 |
Neg logit contributions | |
pollen | -1.168 |
turrets | -1.144 |
patterns | -1.139 |
stones | -1.121 |
ts | -1.112 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
| +0.227 |
" | +0.203 |
because | +0.195 |
She | +0.191 |
but | +0.176 |
Neg logit contributions | |
ts | -0.315 |
riches | -0.294 |
pollen | -0.290 |
miles | -0.285 |
turrets | -0.283 |
Token | to |
Token ID | 284 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
| +0.014 |
" | +0.010 |
because | +0.010 |
She | +0.009 |
. | +0.008 |
Neg logit contributions | |
ts | -0.054 |
riches | -0.053 |
turrets | -0.053 |
pollen | -0.052 |
miles | -0.052 |
Token | play |
Token ID | 711 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
| +0.134 |
" | +0.118 |
because | +0.116 |
She | +0.113 |
. | +0.109 |
Neg logit contributions | |
ts | -0.141 |
riches | -0.137 |
isher | -0.134 |
turrets | -0.134 |
miles | -0.134 |
Token | with |
Token ID | 351 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
ts | +0.205 |
riches | +0.192 |
miles | +0.192 |
pollen | +0.192 |
turrets | +0.190 |
Neg logit contributions | |
| -0.123 |
" | -0.105 |
because | -0.101 |
She | -0.099 |
: | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
| +0.081 |
" | +0.070 |
because | +0.068 |
She | +0.065 |
. | +0.061 |
Neg logit contributions | |
ts | -0.138 |
riches | -0.135 |
pollen | -0.133 |
miles | -0.133 |
turrets | -0.133 |
Token | little |
Token ID | 1310 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
ts | +0.063 |
riches | +0.061 |
turrets | +0.060 |
pollen | +0.060 |
miles | +0.060 |
Neg logit contributions | |
| -0.070 |
" | -0.063 |
because | -0.061 |
She | -0.059 |
. | -0.057 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ts | +0.107 |
riches | +0.104 |
miles | +0.104 |
ounces | +0.103 |
ief | +0.103 |
Neg logit contributions | |
| -0.118 |
because | -0.108 |
" | -0.108 |
She | -0.103 |
. | -0.103 |
Token | named |
Token ID | 3706 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ts | +0.308 |
pollen | +0.290 |
miles | +0.281 |
riches | +0.276 |
isher | +0.275 |
Neg logit contributions | |
| -0.220 |
" | -0.206 |
She | -0.190 |
� | -0.179 |
because | -0.177 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
| +0.245 |
because | +0.212 |
" | +0.208 |
: | +0.190 |
She | +0.187 |
Neg logit contributions | |
ts | -0.409 |
pollen | -0.400 |
miles | -0.393 |
turrets | -0.386 |
riches | -0.382 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
ts | +0.106 |
an | +0.096 |
treasures | +0.095 |
riches | +0.095 |
miles | +0.094 |
Neg logit contributions | |
" | -0.038 |
� | -0.035 |
She | -0.032 |
| -0.032 |
Together | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
| +0.277 |
: | +0.234 |
because | +0.218 |
" | +0.205 |
; | +0.178 |
Neg logit contributions | |
pollen | -1.169 |
patterns | -1.134 |
turrets | -1.125 |
stones | -1.122 |
ts | -1.119 |
Token | went |
Token ID | 1816 |
Feature activation | -5.88e-03 |
Pos logit contributions | |
| +0.223 |
" | +0.197 |
because | +0.192 |
She | +0.186 |
. | +0.169 |
Neg logit contributions | |
ts | -0.327 |
riches | -0.307 |
pollen | -0.302 |
miles | -0.299 |
turrets | -0.297 |
Token | to |
Token ID | 284 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
ts | +0.016 |
miles | +0.016 |
riches | +0.016 |
pollen | +0.016 |
seas | +0.016 |
Neg logit contributions | |
| -0.006 |
" | -0.005 |
because | -0.005 |
She | -0.005 |
. | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
| +0.104 |
" | +0.088 |
because | +0.085 |
She | +0.081 |
. | +0.077 |
Neg logit contributions | |
ts | -0.169 |
riches | -0.165 |
turrets | -0.163 |
isher | -0.163 |
ounces | -0.162 |
Token | park |
Token ID | 3952 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
ts | +0.032 |
riches | +0.031 |
turrets | +0.030 |
pollen | +0.030 |
miles | +0.030 |
Neg logit contributions | |
| -0.040 |
" | -0.036 |
because | -0.036 |
She | -0.035 |
. | -0.034 |
Token | sand |
Token ID | 6450 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ts | +0.720 |
riches | +0.698 |
turrets | +0.684 |
miles | +0.684 |
pollen | +0.682 |
Neg logit contributions | |
| -0.607 |
" | -0.533 |
because | -0.521 |
She | -0.502 |
. | -0.485 |
Token | , |
Token ID | 11 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
ts | +1.340 |
riches | +1.309 |
turrets | +1.309 |
seas | +1.308 |
pollen | +1.303 |
Neg logit contributions | |
| -0.377 |
" | -0.281 |
She | -0.256 |
because | -0.255 |
: | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
| +0.122 |
" | +0.104 |
because | +0.101 |
She | +0.095 |
. | +0.090 |
Neg logit contributions | |
ts | -0.239 |
riches | -0.235 |
ief | -0.231 |
isher | -0.231 |
ounces | -0.229 |
Token | deep |
Token ID | 2769 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
| +0.046 |
" | +0.041 |
because | +0.039 |
She | +0.037 |
. | +0.036 |
Neg logit contributions | |
ts | -0.077 |
isher | -0.077 |
ief | -0.077 |
riches | -0.075 |
ieve | -0.075 |
Token | blue |
Token ID | 4171 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ts | +0.704 |
riches | +0.694 |
ief | +0.688 |
confidence | +0.684 |
ounces | +0.683 |
Neg logit contributions | |
| -0.378 |
because | -0.325 |
. | -0.321 |
" | -0.318 |
She | -0.295 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
ts | +0.477 |
riches | +0.461 |
pollen | +0.449 |
miles | +0.449 |
ief | +0.448 |
Neg logit contributions | |
| -0.451 |
" | -0.399 |
because | -0.391 |
She | -0.379 |
. | -0.374 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ts | +0.660 |
riches | +0.627 |
turrets | +0.614 |
pollen | +0.613 |
miles | +0.612 |
Neg logit contributions | |
| -1.185 |
" | -1.089 |
because | -1.066 |
She | -1.047 |
. | -0.995 |
Token | |
Token ID | 220 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
| +0.211 |
because | +0.205 |
. | +0.173 |
: | +0.171 |
" | +0.170 |
Neg logit contributions | |
turrets | -0.679 |
Majesty | -0.666 |
pollen | -0.665 |
miles | -0.657 |
riches | -0.656 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
because | +0.021 |
" | +0.003 |
but | +0.001 |
| +0.000 |
She | -0.003 |
Neg logit contributions | |
ts | -0.207 |
pollen | -0.203 |
riches | -0.203 |
turrets | -0.203 |
miles | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
because | +0.038 |
| +0.007 |
" | +0.005 |
. | -0.022 |
She | -0.024 |
Neg logit contributions | |
miles | -0.789 |
ts | -0.788 |
turrets | -0.784 |
riches | -0.781 |
pollen | -0.780 |
Token | One |
Token ID | 3198 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
| +0.328 |
because | +0.290 |
" | +0.287 |
She | +0.262 |
. | +0.258 |
Neg logit contributions | |
ts | -0.559 |
riches | -0.549 |
turrets | -0.548 |
miles | -0.546 |
pollen | -0.541 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ts | +0.874 |
riches | +0.869 |
miles | +0.843 |
decisions | +0.832 |
seas | +0.830 |
Neg logit contributions | |
| -0.225 |
" | -0.184 |
She | -0.163 |
They | -0.117 |
Why | -0.116 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
| +0.144 |
" | +0.118 |
because | +0.112 |
She | +0.109 |
: | +0.101 |
Neg logit contributions | |
ts | -0.311 |
riches | -0.306 |
miles | -0.302 |
turrets | -0.302 |
pollen | -0.300 |
Token | my |
Token ID | 1820 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ts | +0.430 |
riches | +0.417 |
miles | +0.412 |
Majesty | +0.407 |
turrets | +0.407 |
Neg logit contributions | |
| -0.247 |
" | -0.216 |
because | -0.207 |
She | -0.201 |
: | -0.180 |
Token | put |
Token ID | 1234 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ts | +0.463 |
riches | +0.450 |
turrets | +0.442 |
miles | +0.442 |
Majesty | +0.440 |
Neg logit contributions | |
| -0.309 |
" | -0.268 |
because | -0.260 |
She | -0.253 |
. | -0.229 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ts | +0.666 |
Majesty | +0.658 |
riches | +0.654 |
ounces | +0.652 |
turrets | +0.652 |
Neg logit contributions | |
| -0.343 |
" | -0.283 |
because | -0.278 |
. | -0.261 |
She | -0.257 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ts | +0.311 |
ief | +0.299 |
ounces | +0.289 |
ieve | +0.287 |
Majesty | +0.286 |
Neg logit contributions | |
| -0.384 |
" | -0.355 |
. | -0.351 |
because | -0.343 |
and | -0.336 |
Token | hell |
Token ID | 12758 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Majesty | +0.782 |
ubb | +0.734 |
riches | +0.721 |
ts | +0.721 |
ounces | +0.718 |
Neg logit contributions | |
| -1.072 |
. | -0.973 |
because | -0.947 |
and | -0.941 |
" | -0.889 |
Token | in |
Token ID | 287 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ts | +0.495 |
riches | +0.480 |
pollen | +0.474 |
miles | +0.474 |
turrets | +0.472 |
Neg logit contributions | |
| -0.345 |
" | -0.300 |
because | -0.285 |
She | -0.279 |
: | -0.257 |
Token | his |
Token ID | 465 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
miles | +0.300 |
ts | +0.295 |
riches | +0.295 |
seas | +0.292 |
turrets | +0.288 |
Neg logit contributions | |
| -0.253 |
" | -0.240 |
She | -0.224 |
because | -0.223 |
: | -0.214 |
Token | pocket |
Token ID | 10000 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ts | +0.357 |
ief | +0.345 |
miles | +0.338 |
ubb | +0.333 |
ounces | +0.331 |
Neg logit contributions | |
| -0.521 |
" | -0.466 |
because | -0.460 |
. | -0.448 |
She | -0.437 |
Token | and |
Token ID | 290 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
ts | +0.865 |
seas | +0.860 |
riches | +0.858 |
isher | +0.832 |
pollen | +0.830 |
Neg logit contributions | |
| -0.207 |
" | -0.159 |
She | -0.150 |
They | -0.106 |
because | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ts | +1.033 |
riches | +1.031 |
seas | +1.017 |
treasures | +1.004 |
miles | +1.003 |
Neg logit contributions | |
| -0.237 |
" | -0.170 |
She | -0.152 |
because | -0.117 |
They | -0.101 |
Token | He |
Token ID | 679 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
because | +0.174 |
| +0.149 |
. | +0.139 |
: | +0.126 |
? | +0.120 |
Neg logit contributions | |
turrets | -0.641 |
Majesty | -0.640 |
ounces | -0.626 |
riches | -0.625 |
pollen | -0.624 |
Token | was |
Token ID | 373 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ief | +0.093 |
isher | +0.092 |
decisions | +0.092 |
ubb | +0.092 |
ocol | +0.091 |
Neg logit contributions | |
| -0.062 |
" | -0.054 |
because | -0.050 |
: | -0.049 |
and | -0.048 |
Token | sailing |
Token ID | 28499 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
isher | +0.295 |
ts | +0.285 |
ief | +0.281 |
ounces | +0.280 |
riches | +0.279 |
Neg logit contributions | |
| -0.131 |
" | -0.116 |
because | -0.108 |
. | -0.095 |
: | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ts | +0.573 |
riches | +0.561 |
turrets | +0.551 |
ounces | +0.550 |
pollen | +0.549 |
Neg logit contributions | |
| -0.406 |
" | -0.355 |
because | -0.348 |
. | -0.325 |
She | -0.323 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ts | +0.263 |
ief | +0.255 |
ounces | +0.251 |
ocol | +0.250 |
confidence | +0.248 |
Neg logit contributions | |
| -0.447 |
because | -0.405 |
. | -0.405 |
and | -0.395 |
" | -0.393 |
Token | in |
Token ID | 287 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ts | +0.653 |
riches | +0.631 |
turrets | +0.614 |
pollen | +0.610 |
miles | +0.605 |
Neg logit contributions | |
| -1.119 |
" | -1.011 |
because | -1.005 |
She | -0.972 |
. | -0.956 |
Token | his |
Token ID | 465 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ts | +0.382 |
riches | +0.375 |
isher | +0.369 |
ounces | +0.369 |
Majesty | +0.368 |
Neg logit contributions | |
| -0.227 |
" | -0.186 |
because | -0.184 |
She | -0.174 |
. | -0.171 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ts | +0.366 |
ief | +0.365 |
ounces | +0.351 |
ieve | +0.348 |
ubb | +0.347 |
Neg logit contributions | |
| -0.550 |
because | -0.476 |
" | -0.474 |
. | -0.472 |
and | -0.454 |
Token | and |
Token ID | 290 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
ts | +0.848 |
riches | +0.834 |
turrets | +0.825 |
miles | +0.824 |
pollen | +0.821 |
Neg logit contributions | |
| -0.226 |
" | -0.169 |
She | -0.150 |
because | -0.149 |
: | -0.114 |
Token | looking |
Token ID | 2045 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
| +0.101 |
" | +0.089 |
because | +0.087 |
. | +0.077 |
and | +0.076 |
Neg logit contributions | |
isher | -0.194 |
ief | -0.192 |
ocol | -0.189 |
ounces | -0.186 |
ubb | -0.186 |
Token | party |
Token ID | 2151 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
| +0.060 |
because | +0.059 |
" | +0.058 |
but | +0.056 |
She | +0.051 |
Neg logit contributions | |
ts | -0.087 |
ief | -0.085 |
ieve | -0.084 |
miles | -0.083 |
aches | -0.080 |
Token | with |
Token ID | 351 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ts | +0.881 |
riches | +0.867 |
seas | +0.850 |
turrets | +0.842 |
miles | +0.839 |
Neg logit contributions | |
| -0.286 |
" | -0.221 |
She | -0.218 |
because | -0.204 |
They | -0.159 |
Token | other |
Token ID | 584 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ts | +0.405 |
isher | +0.393 |
riches | +0.392 |
turrets | +0.392 |
ounces | +0.391 |
Neg logit contributions | |
| -0.239 |
" | -0.197 |
because | -0.194 |
. | -0.185 |
She | -0.184 |
Token | kings |
Token ID | 21557 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
ts | +0.432 |
isher | +0.418 |
ief | +0.417 |
plank | +0.406 |
ounces | +0.403 |
Neg logit contributions | |
| -0.614 |
. | -0.556 |
because | -0.552 |
" | -0.549 |
and | -0.531 |
Token | and |
Token ID | 290 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ts | +1.078 |
riches | +1.062 |
seas | +1.044 |
isher | +1.042 |
miles | +1.039 |
Neg logit contributions | |
| -0.258 |
" | -0.185 |
She | -0.176 |
because | -0.153 |
They | -0.113 |
Token | queens |
Token ID | 38771 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
| +0.095 |
" | +0.090 |
they | +0.087 |
because | +0.082 |
. | +0.081 |
Neg logit contributions | |
isher | -0.065 |
isel | -0.061 |
inge | -0.057 |
ocol | -0.057 |
breaths | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ts | +1.395 |
riches | +1.372 |
pollen | +1.350 |
miles | +1.349 |
turrets | +1.347 |
Neg logit contributions | |
| -0.337 |
" | -0.256 |
because | -0.229 |
She | -0.220 |
: | -0.152 |
Token | He |
Token ID | 679 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
because | +0.164 |
| +0.135 |
: | +0.129 |
. | +0.124 |
" | +0.117 |
Neg logit contributions | |
Majesty | -0.697 |
turrets | -0.675 |
riches | -0.665 |
pollen | -0.659 |
ounces | -0.653 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ts | +0.075 |
isher | +0.075 |
riches | +0.074 |
turrets | +0.073 |
ief | +0.073 |
Neg logit contributions | |
| -0.050 |
" | -0.043 |
because | -0.041 |
. | -0.039 |
She | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
ts | +0.429 |
isher | +0.423 |
ief | +0.420 |
riches | +0.419 |
ubb | +0.417 |
Neg logit contributions | |
| -0.087 |
" | -0.057 |
because | -0.052 |
. | -0.041 |
She | -0.038 |
Token | show |
Token ID | 905 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
isher | +0.210 |
ts | +0.200 |
ounces | +0.197 |
breaths | +0.195 |
ubb | +0.193 |
Neg logit contributions | |
| -0.177 |
. | -0.149 |
because | -0.147 |
" | -0.147 |
She | -0.139 |
Token | who |
Token ID | 508 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ts | +0.881 |
riches | +0.865 |
seas | +0.854 |
miles | +0.832 |
Majesty | +0.827 |
Neg logit contributions | |
| -0.357 |
She | -0.305 |
" | -0.289 |
because | -0.255 |
They | -0.228 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ts | +0.035 |
pollen | +0.034 |
riches | +0.034 |
turrets | +0.034 |
ief | +0.034 |
Neg logit contributions | |
| -0.023 |
" | -0.020 |
because | -0.019 |
. | -0.018 |
She | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ts | +0.410 |
ief | +0.404 |
isher | +0.403 |
ounces | +0.402 |
riches | +0.402 |
Neg logit contributions | |
| -0.109 |
" | -0.085 |
because | -0.079 |
. | -0.068 |
She | -0.058 |
Token | sail |
Token ID | 14936 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
isher | +0.147 |
ounces | +0.142 |
ts | +0.141 |
pollen | +0.140 |
ief | +0.140 |
Neg logit contributions | |
| -0.151 |
" | -0.132 |
. | -0.131 |
because | -0.130 |
She | -0.120 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ts | +0.794 |
riches | +0.779 |
turrets | +0.771 |
pollen | +0.768 |
miles | +0.766 |
Neg logit contributions | |
| -0.289 |
" | -0.225 |
because | -0.219 |
She | -0.199 |
. | -0.194 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ts | +0.172 |
ounces | +0.165 |
ief | +0.163 |
confidence | +0.159 |
ocol | +0.154 |
Neg logit contributions | |
| -0.426 |
. | -0.400 |
and | -0.383 |
because | -0.383 |
" | -0.379 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ts | +0.701 |
riches | +0.684 |
Majesty | +0.675 |
turrets | +0.671 |
isher | +0.668 |
Neg logit contributions | |
| -1.009 |
because | -0.901 |
" | -0.885 |
. | -0.878 |
She | -0.846 |
Token | He |
Token ID | 679 |
Feature activation | -5.08e-03 |
Pos logit contributions | |
| +0.280 |
because | +0.252 |
: | +0.238 |
" | +0.229 |
. | +0.218 |
Neg logit contributions | |
turrets | -0.749 |
riches | -0.740 |
seas | -0.731 |
ounces | -0.720 |
pollen | -0.717 |
Token | had |
Token ID | 550 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
riches | +0.011 |
ief | +0.011 |
decisions | +0.011 |
pollen | +0.011 |
turrets | +0.011 |
Neg logit contributions | |
| -0.009 |
" | -0.008 |
because | -0.008 |
. | -0.007 |
and | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
isher | +0.222 |
ocol | +0.215 |
ubb | +0.214 |
ts | +0.211 |
ieve | +0.208 |
Neg logit contributions | |
| -0.107 |
" | -0.082 |
because | -0.073 |
. | -0.069 |
She | -0.068 |
Token | big |
Token ID | 1263 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ts | +0.347 |
ief | +0.337 |
ounces | +0.328 |
isher | +0.327 |
lled | +0.322 |
Neg logit contributions | |
| -0.314 |
" | -0.278 |
because | -0.261 |
. | -0.252 |
and | -0.246 |
Token | reward |
Token ID | 6721 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
ts | +0.623 |
ief | +0.578 |
miles | +0.575 |
riches | +0.574 |
turrets | +0.572 |
Neg logit contributions | |
| -0.714 |
" | -0.650 |
because | -0.638 |
. | -0.627 |
She | -0.609 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
ts | +0.803 |
riches | +0.796 |
pollen | +0.777 |
miles | +0.770 |
seas | +0.765 |
Neg logit contributions | |
| -0.257 |
" | -0.194 |
She | -0.185 |
because | -0.177 |
They | -0.142 |
Token | It |
Token ID | 632 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
because | +0.163 |
| +0.152 |
. | +0.125 |
" | +0.124 |
: | +0.124 |
Neg logit contributions | |
turrets | -0.585 |
Majesty | -0.582 |
riches | -0.578 |
ounces | -0.574 |
pollen | -0.566 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ts | +0.429 |
riches | +0.420 |
turrets | +0.417 |
isher | +0.415 |
miles | +0.412 |
Neg logit contributions | |
| -0.198 |
" | -0.165 |
because | -0.154 |
She | -0.149 |
. | -0.142 |
Token | ch |
Token ID | 442 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ts | +0.275 |
riches | +0.265 |
isher | +0.263 |
turrets | +0.262 |
miles | +0.261 |
Neg logit contributions | |
| -0.168 |
" | -0.147 |
because | -0.142 |
She | -0.132 |
. | -0.129 |
Token | ocol |
Token ID | 4668 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ts | +0.330 |
riches | +0.317 |
Majesty | +0.306 |
turrets | +0.298 |
plank | +0.292 |
Neg logit contributions | |
| -0.534 |
because | -0.504 |
She | -0.494 |
. | -0.480 |
" | -0.478 |
Token | ates |
Token ID | 689 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
ts | +0.439 |
riches | +0.432 |
miles | +0.414 |
turrets | +0.412 |
pollen | +0.407 |
Neg logit contributions | |
| -1.224 |
" | -1.114 |
because | -1.106 |
. | -1.080 |
She | -1.073 |
Token | and |
Token ID | 290 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
ts | +0.780 |
riches | +0.763 |
pollen | +0.763 |
turrets | +0.758 |
miles | +0.757 |
Neg logit contributions | |
| -0.247 |
" | -0.180 |
She | -0.160 |
because | -0.148 |
They | -0.130 |
Token | sweets |
Token ID | 42402 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
| +0.106 |
" | +0.098 |
because | +0.094 |
. | +0.088 |
She | +0.088 |
Neg logit contributions | |
isher | -0.131 |
ts | -0.129 |
ief | -0.129 |
riches | -0.127 |
turrets | -0.126 |
Token | ! |
Token ID | 0 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ts | +0.889 |
riches | +0.864 |
pollen | +0.860 |
miles | +0.860 |
seas | +0.845 |
Neg logit contributions | |
| -0.272 |
" | -0.192 |
She | -0.175 |
because | -0.155 |
They | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
because | +0.193 |
| +0.193 |
" | +0.167 |
: | +0.156 |
. | +0.155 |
Neg logit contributions | |
turrets | -0.566 |
riches | -0.565 |
pollen | -0.564 |
ounces | -0.564 |
miles | -0.559 |
Token | place |
Token ID | 1295 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
ts | +0.357 |
ief | +0.327 |
isher | +0.318 |
lled | +0.314 |
miles | +0.308 |
Neg logit contributions | |
| -0.404 |
" | -0.380 |
because | -0.361 |
. | -0.350 |
: | -0.329 |
Token | that |
Token ID | 326 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
ts | +0.619 |
riches | +0.609 |
miles | +0.605 |
turrets | +0.604 |
pollen | +0.599 |
Neg logit contributions | |
| -0.236 |
" | -0.175 |
She | -0.167 |
because | -0.157 |
They | -0.133 |
Token | has |
Token ID | 468 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ts | +0.027 |
isher | +0.026 |
riches | +0.026 |
turrets | +0.026 |
ief | +0.025 |
Neg logit contributions | |
| -0.017 |
" | -0.015 |
because | -0.014 |
She | -0.013 |
. | -0.013 |
Token | lots |
Token ID | 6041 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
isher | +0.280 |
ts | +0.273 |
ief | +0.268 |
ubb | +0.267 |
Majesty | +0.262 |
Neg logit contributions | |
| -0.186 |
" | -0.166 |
because | -0.164 |
. | -0.156 |
She | -0.148 |
Token | of |
Token ID | 286 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ts | +0.561 |
riches | +0.541 |
turrets | +0.534 |
isher | +0.533 |
ief | +0.531 |
Neg logit contributions | |
| -0.366 |
" | -0.315 |
because | -0.314 |
She | -0.295 |
. | -0.290 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
isher | +0.295 |
ief | +0.280 |
ubb | +0.269 |
Majesty | +0.269 |
ts | +0.267 |
Neg logit contributions | |
| -0.439 |
because | -0.408 |
. | -0.407 |
" | -0.404 |
and | -0.386 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
ts | +0.648 |
riches | +0.628 |
isher | +0.625 |
turrets | +0.613 |
miles | +0.606 |
Neg logit contributions | |
| -1.049 |
because | -0.940 |
" | -0.938 |
. | -0.915 |
She | -0.902 |
Token | s |
Token ID | 82 |
Feature activation | -8.82e-02 |
Pos logit contributions | |
ts | +0.474 |
pollen | +0.463 |
riches | +0.463 |
miles | +0.456 |
turrets | +0.456 |
Neg logit contributions | |
| -0.255 |
" | -0.214 |
because | -0.198 |
She | -0.192 |
: | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ts | +0.231 |
riches | +0.230 |
pollen | +0.226 |
turrets | +0.225 |
miles | +0.224 |
Neg logit contributions | |
| -0.110 |
" | -0.091 |
She | -0.085 |
because | -0.084 |
They | -0.070 |
Token | right |
Token ID | 826 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
| +0.186 |
" | +0.156 |
because | +0.153 |
She | +0.139 |
. | +0.130 |
Neg logit contributions | |
ts | -0.417 |
riches | -0.405 |
isher | -0.399 |
turrets | -0.399 |
miles | -0.398 |
Token | near |
Token ID | 1474 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ts | +0.413 |
riches | +0.400 |
turrets | +0.396 |
miles | +0.394 |
pollen | +0.394 |
Neg logit contributions | |
| -0.279 |
" | -0.236 |
because | -0.227 |
She | -0.226 |
. | -0.202 |
Token | 's |
Token ID | 338 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ts | +0.261 |
turrets | +0.259 |
riches | +0.257 |
Majesty | +0.255 |
isher | +0.254 |
Neg logit contributions | |
| -0.116 |
because | -0.095 |
" | -0.094 |
. | -0.084 |
She | -0.084 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ts | +0.359 |
miles | +0.338 |
riches | +0.338 |
turrets | +0.337 |
ief | +0.337 |
Neg logit contributions | |
| -0.359 |
" | -0.321 |
because | -0.317 |
She | -0.299 |
. | -0.299 |
Token | was |
Token ID | 373 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ts | +0.563 |
Majesty | +0.538 |
riches | +0.538 |
pollen | +0.531 |
turrets | +0.530 |
Neg logit contributions | |
| -0.363 |
" | -0.312 |
because | -0.298 |
She | -0.294 |
They | -0.263 |
Token | even |
Token ID | 772 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ts | +0.252 |
riches | +0.245 |
turrets | +0.240 |
miles | +0.240 |
pollen | +0.239 |
Neg logit contributions | |
| -0.204 |
" | -0.178 |
because | -0.175 |
She | -0.171 |
. | -0.158 |
Token | ang |
Token ID | 3550 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
riches | +0.489 |
ts | +0.481 |
plank | +0.480 |
ief | +0.477 |
turrets | +0.477 |
Neg logit contributions | |
| -0.484 |
" | -0.442 |
because | -0.435 |
. | -0.431 |
and | -0.398 |
Token | rier |
Token ID | 5277 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ts | +0.053 |
riches | +0.031 |
isher | +0.030 |
ounces | +0.029 |
ubb | +0.025 |
Neg logit contributions | |
| -0.869 |
" | -0.805 |
because | -0.798 |
She | -0.784 |
: | -0.754 |
Token | and |
Token ID | 290 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
ounces | +1.079 |
decisions | +1.074 |
ts | +1.070 |
isher | +1.052 |
angles | +1.048 |
Neg logit contributions | |
| -0.408 |
She | -0.317 |
" | -0.279 |
One | -0.269 |
On | -0.263 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
| +0.088 |
" | +0.080 |
because | +0.075 |
She | +0.074 |
. | +0.071 |
Neg logit contributions | |
riches | -0.115 |
turrets | -0.114 |
ts | -0.114 |
seas | -0.111 |
ounces | -0.111 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ts | +0.455 |
riches | +0.432 |
pollen | +0.427 |
turrets | +0.425 |
miles | +0.425 |
Neg logit contributions | |
| -0.330 |
" | -0.289 |
because | -0.281 |
She | -0.270 |
They | -0.244 |
Token | even |
Token ID | 772 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ts | +0.414 |
turrets | +0.403 |
riches | +0.401 |
isher | +0.400 |
seas | +0.394 |
Neg logit contributions | |
| -0.362 |
" | -0.318 |
because | -0.315 |
She | -0.301 |
. | -0.294 |
Token | sad |
Token ID | 6507 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
riches | +0.476 |
turrets | +0.473 |
seas | +0.472 |
plank | +0.468 |
Majesty | +0.461 |
Neg logit contributions | |
| -0.411 |
. | -0.366 |
" | -0.362 |
because | -0.361 |
and | -0.325 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
riches | +0.618 |
ts | +0.617 |
ounces | +0.596 |
pollen | +0.593 |
ief | +0.590 |
Neg logit contributions | |
| -0.839 |
" | -0.757 |
because | -0.754 |
. | -0.723 |
She | -0.717 |
Token | les |
Token ID | 829 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ts | +0.159 |
riches | +0.136 |
miles | +0.129 |
pollen | +0.127 |
turrets | +0.127 |
Neg logit contributions | |
| -0.874 |
" | -0.818 |
because | -0.808 |
She | -0.797 |
. | -0.769 |
Token | and |
Token ID | 290 |
Feature activation | +7.08e-02 |
Pos logit contributions | |
ts | +0.867 |
pollen | +0.846 |
miles | +0.844 |
turrets | +0.841 |
riches | +0.838 |
Neg logit contributions | |
| -0.198 |
" | -0.132 |
because | -0.116 |
She | -0.111 |
They | -0.073 |
Token | collect |
Token ID | 2824 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
| +0.126 |
" | +0.112 |
because | +0.109 |
She | +0.105 |
and | +0.103 |
Neg logit contributions | |
isher | -0.168 |
ief | -0.160 |
riches | -0.160 |
ieve | -0.157 |
ocol | -0.156 |
Token | pretty |
Token ID | 2495 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
confidence | +0.372 |
Majesty | +0.358 |
ounces | +0.341 |
ief | +0.332 |
ubb | +0.324 |
Neg logit contributions | |
| -0.790 |
. | -0.767 |
and | -0.730 |
because | -0.701 |
" | -0.691 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ief | +0.308 |
confidence | +0.289 |
ounces | +0.271 |
ubb | +0.267 |
ts | +0.264 |
Neg logit contributions | |
| -0.887 |
. | -0.846 |
and | -0.817 |
" | -0.803 |
because | -0.798 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ts | +0.536 |
riches | +0.512 |
turrets | +0.495 |
pollen | +0.493 |
miles | +0.492 |
Neg logit contributions | |
| -1.148 |
" | -1.052 |
because | -1.038 |
She | -1.014 |
. | -0.989 |
Token | s |
Token ID | 82 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
ts | +0.519 |
pollen | +0.511 |
seas | +0.508 |
riches | +0.504 |
miles | +0.500 |
Neg logit contributions | |
| -0.236 |
" | -0.199 |
because | -0.179 |
She | -0.176 |
: | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
ts | +0.289 |
riches | +0.286 |
pollen | +0.284 |
turrets | +0.284 |
seas | +0.283 |
Neg logit contributions | |
| -0.059 |
" | -0.040 |
She | -0.037 |
because | -0.032 |
They | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | +7.42e-02 |
Pos logit contributions | |
because | +0.156 |
| +0.126 |
: | +0.125 |
. | +0.114 |
" | +0.112 |
Neg logit contributions | |
Majesty | -0.816 |
pollen | -0.801 |
turrets | -0.796 |
miles | -0.778 |
riches | -0.774 |
Token | day |
Token ID | 1110 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
| +0.135 |
because | +0.119 |
" | +0.114 |
. | +0.112 |
and | +0.105 |
Neg logit contributions | |
ts | -0.175 |
ief | -0.170 |
riches | -0.166 |
Majesty | -0.166 |
ounces | -0.163 |
Token | there |
Token ID | 612 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
miles | +0.188 |
ts | +0.187 |
seas | +0.181 |
Majesty | +0.176 |
turrets | +0.172 |
Neg logit contributions | |
| -0.088 |
She | -0.083 |
They | -0.081 |
because | -0.077 |
" | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
ts | +0.273 |
miles | +0.264 |
turrets | +0.253 |
seas | +0.253 |
riches | +0.252 |
Neg logit contributions | |
| -0.172 |
because | -0.172 |
" | -0.170 |
She | -0.162 |
They | -0.146 |
Token | a |
Token ID | 257 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ts | +0.231 |
riches | +0.226 |
turrets | +0.222 |
pollen | +0.222 |
miles | +0.222 |
Neg logit contributions | |
| -0.126 |
" | -0.106 |
because | -0.103 |
She | -0.098 |
. | -0.092 |
Token | yellow |
Token ID | 7872 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ts | +0.336 |
riches | +0.327 |
turrets | +0.321 |
miles | +0.319 |
pollen | +0.319 |
Neg logit contributions | |
| -0.365 |
" | -0.327 |
because | -0.318 |
She | -0.307 |
. | -0.298 |
Token | pol |
Token ID | 755 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ts | +0.405 |
riches | +0.389 |
turrets | +0.379 |
miles | +0.378 |
pollen | +0.377 |
Neg logit contributions | |
| -0.623 |
" | -0.566 |
because | -0.557 |
She | -0.543 |
. | -0.526 |
Token | isher |
Token ID | 4828 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
miles | +0.406 |
ounces | +0.391 |
riches | +0.379 |
decisions | +0.378 |
turrets | +0.369 |
Neg logit contributions | |
| -0.531 |
. | -0.519 |
because | -0.498 |
and | -0.483 |
She | -0.459 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ts | +1.223 |
isher | +1.182 |
riches | +1.179 |
turrets | +1.168 |
miles | +1.161 |
Neg logit contributions | |
| -0.365 |
She | -0.273 |
" | -0.243 |
They | -0.201 |
because | -0.199 |
Token | It |
Token ID | 632 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
| +0.353 |
because | +0.298 |
: | +0.294 |
" | +0.285 |
. | +0.283 |
Neg logit contributions | |
turrets | -0.663 |
pollen | -0.658 |
riches | -0.647 |
miles | -0.641 |
ounces | -0.639 |
Token | was |
Token ID | 373 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
ts | +0.285 |
pollen | +0.279 |
riches | +0.275 |
turrets | +0.274 |
miles | +0.272 |
Neg logit contributions | |
| -0.164 |
" | -0.144 |
because | -0.140 |
She | -0.133 |
: | -0.122 |
Token | very |
Token ID | 845 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ts | +0.170 |
riches | +0.165 |
turrets | +0.162 |
pollen | +0.161 |
miles | +0.161 |
Neg logit contributions | |
| -0.135 |
" | -0.118 |
because | -0.116 |
She | -0.111 |
. | -0.106 |
Token | special |
Token ID | 2041 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ts | +0.254 |
ief | +0.243 |
riches | +0.242 |
miles | +0.242 |
isher | +0.237 |
Neg logit contributions | |
| -0.309 |
" | -0.279 |
because | -0.274 |
She | -0.265 |
. | -0.259 |
Token | So |
Token ID | 2396 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
| +0.299 |
" | +0.252 |
because | +0.243 |
She | +0.233 |
. | +0.217 |
Neg logit contributions | |
ts | -0.553 |
riches | -0.540 |
turrets | -0.533 |
miles | -0.531 |
pollen | -0.530 |
Token | she |
Token ID | 673 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
| +0.012 |
" | +0.010 |
because | +0.009 |
She | +0.009 |
. | +0.007 |
Neg logit contributions | |
ts | -0.036 |
riches | -0.036 |
miles | -0.035 |
turrets | -0.035 |
pollen | -0.035 |
Token | put |
Token ID | 1234 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ts | +0.334 |
riches | +0.333 |
miles | +0.324 |
isher | +0.324 |
turrets | +0.323 |
Neg logit contributions | |
| -0.226 |
" | -0.197 |
because | -0.186 |
She | -0.183 |
. | -0.183 |
Token | on |
Token ID | 319 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Majesty | +0.755 |
riches | +0.750 |
ts | +0.748 |
turrets | +0.743 |
confidence | +0.736 |
Neg logit contributions | |
| -0.373 |
" | -0.310 |
because | -0.291 |
. | -0.285 |
She | -0.280 |
Token | her |
Token ID | 607 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
isher | +0.531 |
ts | +0.526 |
Majesty | +0.522 |
ief | +0.521 |
riches | +0.521 |
Neg logit contributions | |
| -0.216 |
" | -0.170 |
. | -0.160 |
She | -0.156 |
because | -0.155 |
Token | brav |
Token ID | 49025 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
ts | +0.406 |
ief | +0.389 |
riches | +0.380 |
miles | +0.379 |
turrets | +0.378 |
Neg logit contributions | |
| -0.586 |
" | -0.534 |
because | -0.523 |
. | -0.513 |
She | -0.498 |
Token | est |
Token ID | 395 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ts | +0.584 |
riches | +0.525 |
pollen | +0.522 |
miles | +0.517 |
ubb | +0.515 |
Neg logit contributions | |
| -1.159 |
because | -1.067 |
" | -1.042 |
. | -1.038 |
and | -1.015 |
Token | face |
Token ID | 1986 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ts | +0.583 |
ief | +0.566 |
riches | +0.539 |
confidence | +0.535 |
miles | +0.534 |
Neg logit contributions | |
| -0.664 |
. | -0.615 |
because | -0.610 |
" | -0.607 |
and | -0.592 |
Token | and |
Token ID | 290 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
ts | +0.736 |
pollen | +0.719 |
riches | +0.717 |
turrets | +0.715 |
miles | +0.713 |
Neg logit contributions | |
| -0.268 |
" | -0.204 |
because | -0.191 |
She | -0.186 |
They | -0.155 |
Token | set |
Token ID | 900 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
| +0.103 |
" | +0.093 |
because | +0.089 |
. | +0.088 |
and | +0.086 |
Neg logit contributions | |
isher | -0.119 |
ief | -0.117 |
ts | -0.115 |
ubb | -0.112 |
ocol | -0.111 |
Token | off |
Token ID | 572 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ts | +0.559 |
riches | +0.554 |
isher | +0.553 |
ounces | +0.543 |
ief | +0.538 |
Neg logit contributions | |
| -0.389 |
" | -0.340 |
. | -0.332 |
because | -0.312 |
She | -0.303 |
Token | the |
Token ID | 262 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
isher | +0.572 |
confidence | +0.555 |
ounces | +0.552 |
ief | +0.543 |
ubb | +0.538 |
Neg logit contributions | |
| -0.238 |
" | -0.197 |
because | -0.193 |
. | -0.182 |
and | -0.174 |
Token | shore |
Token ID | 15191 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ts | +0.327 |
ief | +0.308 |
ounces | +0.306 |
isel | +0.299 |
isher | +0.295 |
Neg logit contributions | |
| -0.359 |
. | -0.328 |
and | -0.320 |
because | -0.319 |
" | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ts | +0.851 |
riches | +0.835 |
turrets | +0.829 |
pollen | +0.828 |
miles | +0.827 |
Neg logit contributions | |
| -0.186 |
" | -0.126 |
She | -0.108 |
because | -0.106 |
: | -0.071 |
Token | They |
Token ID | 1119 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
| +0.259 |
because | +0.258 |
. | +0.238 |
" | +0.230 |
: | +0.225 |
Neg logit contributions | |
turrets | -0.692 |
pollen | -0.686 |
miles | -0.678 |
riches | -0.678 |
Majesty | -0.674 |
Token | collected |
Token ID | 7723 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
| +0.029 |
" | +0.024 |
because | +0.024 |
She | +0.022 |
. | +0.022 |
Neg logit contributions | |
riches | -0.050 |
ts | -0.050 |
isher | -0.049 |
ounces | -0.049 |
decisions | -0.049 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Majesty | +0.555 |
ounces | +0.551 |
ief | +0.540 |
confidence | +0.538 |
fters | +0.523 |
Neg logit contributions | |
| -0.558 |
and | -0.505 |
. | -0.499 |
because | -0.469 |
" | -0.468 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
ts | +0.648 |
riches | +0.639 |
isher | +0.630 |
ief | +0.628 |
Majesty | +0.622 |
Neg logit contributions | |
| -1.044 |
because | -0.921 |
" | -0.920 |
. | -0.895 |
She | -0.879 |
Token | s |
Token ID | 82 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
ts | +0.578 |
riches | +0.567 |
turrets | +0.560 |
pollen | +0.559 |
miles | +0.558 |
Neg logit contributions | |
| -0.172 |
" | -0.130 |
because | -0.123 |
She | -0.113 |
. | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
ts | +0.261 |
riches | +0.256 |
pollen | +0.253 |
turrets | +0.253 |
miles | +0.252 |
Neg logit contributions | |
| -0.079 |
" | -0.060 |
because | -0.057 |
She | -0.053 |
. | -0.045 |
Token | built |
Token ID | 3170 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
| +0.144 |
and | +0.130 |
because | +0.128 |
they | +0.128 |
. | +0.123 |
Neg logit contributions | |
ief | -0.210 |
rier | -0.201 |
ieve | -0.200 |
isher | -0.198 |
Majesty | -0.197 |
Token | sand |
Token ID | 6450 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
isher | +0.464 |
ounces | +0.454 |
confidence | +0.451 |
ief | +0.448 |
chie | +0.432 |
Neg logit contributions | |
| -0.428 |
. | -0.392 |
and | -0.373 |
" | -0.367 |
because | -0.344 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ts | +0.970 |
riches | +0.945 |
pollen | +0.938 |
turrets | +0.934 |
miles | +0.932 |
Neg logit contributions | |
| -0.438 |
" | -0.361 |
because | -0.359 |
She | -0.337 |
They | -0.284 |
Token | She |
Token ID | 1375 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
because | +0.115 |
| +0.094 |
. | +0.078 |
: | +0.069 |
" | +0.068 |
Neg logit contributions | |
Majesty | -0.553 |
turrets | -0.529 |
pollen | -0.518 |
riches | -0.514 |
angles | -0.512 |
Token | was |
Token ID | 373 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ts | +0.096 |
riches | +0.094 |
turrets | +0.092 |
miles | +0.092 |
pollen | +0.092 |
Neg logit contributions | |
| -0.063 |
" | -0.054 |
because | -0.053 |
She | -0.051 |
. | -0.048 |
Token | three |
Token ID | 1115 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
isher | +0.322 |
ts | +0.321 |
riches | +0.316 |
seas | +0.313 |
fortune | +0.313 |
Neg logit contributions | |
| -0.159 |
" | -0.143 |
because | -0.132 |
She | -0.123 |
. | -0.117 |
Token | - |
Token ID | 12 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
isher | +0.702 |
ts | +0.695 |
riches | +0.693 |
turrets | +0.691 |
ief | +0.688 |
Neg logit contributions | |
| -0.745 |
because | -0.692 |
. | -0.683 |
" | -0.662 |
and | -0.648 |
Token | years |
Token ID | 19002 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
riches | +0.443 |
Majesty | +0.429 |
seas | +0.425 |
ts | +0.420 |
plank | +0.416 |
Neg logit contributions | |
| -0.588 |
She | -0.522 |
" | -0.516 |
. | -0.501 |
because | -0.497 |
Token | - |
Token ID | 12 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ts | +0.862 |
miles | +0.837 |
turrets | +0.826 |
ief | +0.823 |
pollen | +0.821 |
Neg logit contributions | |
| -0.804 |
because | -0.758 |
. | -0.748 |
" | -0.723 |
and | -0.705 |
Token | old |
Token ID | 727 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
ts | +0.407 |
pollen | +0.390 |
riches | +0.383 |
seas | +0.377 |
plank | +0.376 |
Neg logit contributions | |
| -0.635 |
" | -0.568 |
She | -0.561 |
because | -0.556 |
. | -0.543 |
Token | and |
Token ID | 290 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
ts | +1.008 |
riches | +0.992 |
turrets | +0.978 |
pollen | +0.978 |
miles | +0.977 |
Neg logit contributions | |
| -0.210 |
" | -0.135 |
because | -0.124 |
She | -0.110 |
: | -0.079 |
Token | she |
Token ID | 673 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
| +0.081 |
" | +0.070 |
because | +0.066 |
She | +0.064 |
. | +0.060 |
Neg logit contributions | |
ts | -0.135 |
riches | -0.132 |
turrets | -0.130 |
isher | -0.130 |
pollen | -0.130 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ts | +0.252 |
riches | +0.246 |
turrets | +0.243 |
pollen | +0.242 |
miles | +0.242 |
Neg logit contributions | |
| -0.135 |
" | -0.114 |
because | -0.110 |
She | -0.105 |
. | -0.098 |
Token | she |
Token ID | 673 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
| +0.178 |
" | +0.146 |
because | +0.139 |
She | +0.134 |
: | +0.127 |
Neg logit contributions | |
ts | -0.389 |
riches | -0.378 |
miles | -0.377 |
turrets | -0.374 |
pollen | -0.373 |
Token | found |
Token ID | 1043 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ts | +0.193 |
pollen | +0.189 |
ounces | +0.188 |
riches | +0.187 |
ief | +0.187 |
Neg logit contributions | |
| -0.136 |
" | -0.113 |
because | -0.110 |
She | -0.107 |
. | -0.106 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ts | +0.691 |
ounces | +0.682 |
Majesty | +0.670 |
riches | +0.667 |
turrets | +0.667 |
Neg logit contributions | |
| -0.273 |
" | -0.211 |
because | -0.194 |
She | -0.188 |
. | -0.186 |
Token | very |
Token ID | 845 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ts | +0.357 |
ief | +0.344 |
isher | +0.330 |
ounces | +0.328 |
breaths | +0.328 |
Neg logit contributions | |
| -0.342 |
" | -0.317 |
because | -0.299 |
. | -0.287 |
but | -0.281 |
Token | delicate |
Token ID | 19217 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ts | +0.337 |
ief | +0.334 |
ieve | +0.316 |
isher | +0.316 |
miles | +0.313 |
Neg logit contributions | |
| -0.251 |
" | -0.230 |
. | -0.221 |
because | -0.218 |
: | -0.203 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
ts | +0.450 |
ief | +0.431 |
ieve | +0.404 |
ounces | +0.394 |
lled | +0.393 |
Neg logit contributions | |
| -0.686 |
because | -0.667 |
. | -0.659 |
" | -0.655 |
and | -0.646 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ts | +0.424 |
riches | +0.404 |
miles | +0.389 |
pollen | +0.385 |
seas | +0.381 |
Neg logit contributions | |
| -1.195 |
" | -1.135 |
She | -1.092 |
because | -1.078 |
They | -1.044 |
Token | on |
Token ID | 319 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
seas | +0.449 |
ts | +0.448 |
stones | +0.445 |
pollen | +0.443 |
miles | +0.435 |
Neg logit contributions | |
| -0.275 |
" | -0.230 |
And | -0.214 |
She | -0.209 |
They | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ts | +0.274 |
pollen | +0.266 |
miles | +0.266 |
riches | +0.265 |
seas | +0.259 |
Neg logit contributions | |
| -0.208 |
" | -0.186 |
because | -0.177 |
She | -0.170 |
: | -0.160 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
isher | +0.221 |
ief | +0.219 |
ts | +0.218 |
ocol | +0.216 |
ubb | +0.215 |
Neg logit contributions | |
| -0.376 |
because | -0.335 |
" | -0.333 |
. | -0.332 |
and | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ts | +0.882 |
seas | +0.865 |
riches | +0.862 |
miles | +0.854 |
pollen | +0.853 |
Neg logit contributions | |
| -0.181 |
" | -0.111 |
She | -0.103 |
because | -0.082 |
And | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
pollen | +0.523 |
riches | +0.521 |
Majesty | +0.512 |
ren | +0.510 |
treasures | +0.510 |
Neg logit contributions | |
| -0.151 |
She | -0.110 |
" | -0.107 |
Because | -0.104 |
On | -0.092 |
Token | she |
Token ID | 673 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
| +0.040 |
" | +0.034 |
because | +0.034 |
She | +0.031 |
. | +0.029 |
Neg logit contributions | |
ts | -0.072 |
riches | -0.071 |
pollen | -0.069 |
turrets | -0.069 |
miles | -0.069 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ts | +0.273 |
riches | +0.268 |
turrets | +0.264 |
pollen | +0.263 |
miles | +0.262 |
Neg logit contributions | |
| -0.160 |
" | -0.137 |
because | -0.134 |
She | -0.127 |
. | -0.117 |
Token | three |
Token ID | 1115 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ts | +0.277 |
riches | +0.269 |
isher | +0.266 |
turrets | +0.264 |
miles | +0.263 |
Neg logit contributions | |
| -0.162 |
" | -0.138 |
because | -0.133 |
She | -0.127 |
. | -0.120 |
Token | - |
Token ID | 12 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ts | +0.681 |
turrets | +0.671 |
isher | +0.670 |
ief | +0.662 |
riches | +0.661 |
Neg logit contributions | |
| -0.720 |
because | -0.648 |
. | -0.646 |
" | -0.632 |
and | -0.600 |
Token | years |
Token ID | 19002 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
riches | +0.400 |
plank | +0.398 |
ts | +0.398 |
Majesty | +0.397 |
decisions | +0.388 |
Neg logit contributions | |
| -0.585 |
She | -0.510 |
" | -0.507 |
. | -0.500 |
because | -0.490 |
Token | - |
Token ID | 12 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ts | +0.848 |
miles | +0.819 |
turrets | +0.813 |
ief | +0.806 |
pollen | +0.803 |
Neg logit contributions | |
| -0.809 |
. | -0.762 |
because | -0.760 |
" | -0.721 |
: | -0.710 |
Token | old |
Token ID | 727 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ts | +0.393 |
pollen | +0.372 |
plank | +0.365 |
riches | +0.362 |
miles | +0.358 |
Neg logit contributions | |
| -0.619 |
" | -0.549 |
She | -0.541 |
because | -0.540 |
. | -0.530 |
Token | . |
Token ID | 13 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
ts | +0.977 |
riches | +0.969 |
pollen | +0.947 |
turrets | +0.946 |
miles | +0.944 |
Neg logit contributions | |
| -0.204 |
" | -0.132 |
because | -0.119 |
She | -0.109 |
: | -0.077 |
Token | She |
Token ID | 1375 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
because | +0.213 |
: | +0.184 |
. | +0.173 |
? | +0.147 |
and | +0.147 |
Neg logit contributions | |
riches | -0.618 |
Majesty | -0.612 |
turrets | -0.603 |
adventurer | -0.580 |
adventurers | -0.578 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ts | +0.032 |
riches | +0.031 |
turrets | +0.031 |
pollen | +0.031 |
miles | +0.031 |
Neg logit contributions | |
| -0.019 |
" | -0.016 |
because | -0.015 |
She | -0.015 |
. | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
ts | +0.747 |
riches | +0.735 |
turrets | +0.726 |
pollen | +0.725 |
miles | +0.722 |
Neg logit contributions | |
| -0.167 |
" | -0.118 |
because | -0.109 |
She | -0.095 |
. | -0.082 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
| +0.166 |
" | +0.135 |
because | +0.130 |
She | +0.115 |
. | +0.111 |
Neg logit contributions | |
ts | -0.414 |
riches | -0.412 |
isher | -0.408 |
ief | -0.406 |
pollen | -0.406 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ts | +0.423 |
riches | +0.415 |
pollen | +0.406 |
turrets | +0.406 |
miles | +0.404 |
Neg logit contributions | |
| -0.299 |
" | -0.258 |
because | -0.252 |
She | -0.240 |
. | -0.231 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ounces | +0.414 |
riches | +0.411 |
ts | +0.411 |
isher | +0.409 |
ief | +0.404 |
Neg logit contributions | |
| -0.186 |
" | -0.151 |
because | -0.141 |
She | -0.138 |
. | -0.133 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ts | +0.344 |
ief | +0.335 |
isher | +0.332 |
ounces | +0.327 |
riches | +0.324 |
Neg logit contributions | |
| -0.346 |
" | -0.320 |
because | -0.293 |
. | -0.285 |
and | -0.275 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
ts | +0.448 |
ounces | +0.433 |
ief | +0.429 |
confidence | +0.409 |
ieve | +0.400 |
Neg logit contributions | |
| -0.627 |
" | -0.585 |
because | -0.570 |
. | -0.567 |
and | -0.556 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ts | +0.477 |
riches | +0.445 |
miles | +0.440 |
turrets | +0.432 |
pollen | +0.424 |
Neg logit contributions | |
| -1.153 |
" | -1.086 |
She | -1.048 |
because | -1.042 |
They | -0.987 |
Token | in |
Token ID | 287 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ts | +0.456 |
miles | +0.447 |
seas | +0.441 |
pollen | +0.439 |
stones | +0.436 |
Neg logit contributions | |
| -0.255 |
" | -0.214 |
She | -0.198 |
And | -0.186 |
because | -0.183 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ts | +0.305 |
riches | +0.297 |
turrets | +0.293 |
pollen | +0.292 |
miles | +0.291 |
Neg logit contributions | |
| -0.194 |
" | -0.166 |
because | -0.162 |
She | -0.155 |
. | -0.146 |
Token | water |
Token ID | 1660 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ts | +0.298 |
ief | +0.278 |
ounces | +0.278 |
ieve | +0.272 |
ubb | +0.269 |
Neg logit contributions | |
| -0.334 |
. | -0.278 |
" | -0.271 |
because | -0.271 |
and | -0.260 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
seas | +0.692 |
ts | +0.677 |
pollen | +0.674 |
miles | +0.669 |
stones | +0.666 |
Neg logit contributions | |
| -0.171 |
" | -0.125 |
She | -0.113 |
And | -0.111 |
because | -0.099 |
Token | sand |
Token ID | 6450 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
isher | +0.556 |
confidence | +0.544 |
riches | +0.530 |
Majesty | +0.529 |
ief | +0.528 |
Neg logit contributions | |
| -0.584 |
. | -0.560 |
" | -0.546 |
because | -0.540 |
and | -0.535 |
Token | cast |
Token ID | 2701 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ts | +0.899 |
riches | +0.889 |
pollen | +0.869 |
turrets | +0.868 |
miles | +0.867 |
Neg logit contributions | |
| -0.502 |
" | -0.426 |
because | -0.418 |
She | -0.392 |
. | -0.381 |
Token | les |
Token ID | 829 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
ts | +0.153 |
riches | +0.136 |
turrets | +0.126 |
pollen | +0.126 |
miles | +0.126 |
Neg logit contributions | |
| -0.830 |
" | -0.776 |
because | -0.766 |
She | -0.754 |
. | -0.733 |
Token | and |
Token ID | 290 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ts | +0.826 |
pollen | +0.801 |
riches | +0.801 |
miles | +0.801 |
turrets | +0.799 |
Neg logit contributions | |
| -0.192 |
" | -0.131 |
because | -0.118 |
She | -0.111 |
: | -0.077 |
Token | collecting |
Token ID | 13157 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
| +0.148 |
" | +0.140 |
because | +0.136 |
and | +0.134 |
they | +0.127 |
Neg logit contributions | |
isher | -0.191 |
ief | -0.186 |
riches | -0.182 |
an | -0.179 |
chie | -0.179 |
Token | seas |
Token ID | 21547 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
confidence | +0.362 |
Majesty | +0.327 |
ief | +0.323 |
ubb | +0.313 |
ounces | +0.310 |
Neg logit contributions | |
. | -0.643 |
| -0.632 |
and | -0.610 |
" | -0.576 |
, | -0.564 |
Token | hell |
Token ID | 12758 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
ts | +0.558 |
riches | +0.546 |
turrets | +0.527 |
isher | +0.526 |
miles | +0.521 |
Neg logit contributions | |
| -1.096 |
" | -0.986 |
because | -0.980 |
. | -0.952 |
She | -0.946 |
Token | s |
Token ID | 82 |
Feature activation | -8.05e-02 |
Pos logit contributions | |
ts | +0.519 |
pollen | +0.505 |
riches | +0.501 |
seas | +0.499 |
miles | +0.497 |
Neg logit contributions | |
| -0.205 |
" | -0.171 |
because | -0.152 |
She | -0.151 |
: | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
ts | +0.267 |
riches | +0.263 |
turrets | +0.261 |
pollen | +0.261 |
miles | +0.259 |
Neg logit contributions | |
| -0.048 |
" | -0.031 |
She | -0.026 |
because | -0.025 |
: | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
because | +0.168 |
: | +0.141 |
| +0.125 |
. | +0.121 |
" | +0.119 |
Neg logit contributions | |
pollen | -0.830 |
Majesty | -0.819 |
turrets | -0.807 |
miles | -0.792 |
ounces | -0.787 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
because | +0.044 |
but | +0.017 |
" | +0.013 |
; | +0.009 |
: | +0.008 |
Neg logit contributions | |
ts | -0.301 |
pollen | -0.291 |
aches | -0.291 |
turrets | -0.288 |
riches | -0.288 |
Token | called |
Token ID | 1444 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
ts | +0.635 |
turrets | +0.596 |
riches | +0.589 |
Majesty | +0.589 |
aches | +0.584 |
Neg logit contributions | |
| -0.325 |
" | -0.272 |
because | -0.265 |
She | -0.258 |
They | -0.225 |
Token | out |
Token ID | 503 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ts | +0.126 |
riches | +0.123 |
pollen | +0.120 |
turrets | +0.120 |
miles | +0.120 |
Neg logit contributions | |
| -0.082 |
" | -0.070 |
because | -0.068 |
She | -0.066 |
. | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
ts | +0.861 |
riches | +0.855 |
miles | +0.847 |
pollen | +0.839 |
turrets | +0.835 |
Neg logit contributions | |
| -0.297 |
" | -0.218 |
because | -0.214 |
She | -0.211 |
They | -0.163 |
Token | " |
Token ID | 366 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
| +0.061 |
because | +0.045 |
She | +0.040 |
: | +0.031 |
And | +0.031 |
Neg logit contributions | |
ts | -0.272 |
miles | -0.270 |
pollen | -0.269 |
turrets | -0.267 |
riches | -0.263 |
Token | D |
Token ID | 35 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
| +0.028 |
" | +0.024 |
because | +0.024 |
She | +0.023 |
. | +0.022 |
Neg logit contributions | |
ts | -0.042 |
riches | -0.041 |
turrets | -0.040 |
miles | -0.040 |
pollen | -0.040 |
Token | inner |
Token ID | 5083 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ts | +0.179 |
riches | +0.172 |
pollen | +0.169 |
turrets | +0.168 |
isher | +0.168 |
Neg logit contributions | |
| -0.270 |
" | -0.245 |
because | -0.241 |
She | -0.233 |
. | -0.224 |
Token | 's |
Token ID | 338 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ts | +1.088 |
riches | +1.053 |
miles | +1.048 |
pollen | +1.039 |
turrets | +1.038 |
Neg logit contributions | |
| -0.518 |
" | -0.419 |
because | -0.404 |
She | -0.399 |
. | -0.334 |
Token | ready |
Token ID | 3492 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ts | +0.313 |
riches | +0.305 |
turrets | +0.300 |
pollen | +0.299 |
miles | +0.299 |
Neg logit contributions | |
| -0.263 |
" | -0.231 |
because | -0.225 |
She | -0.219 |
. | -0.207 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ts | +0.654 |
seas | +0.649 |
miles | +0.647 |
riches | +0.640 |
turrets | +0.637 |
Neg logit contributions | |
| -0.274 |
She | -0.215 |
" | -0.212 |
because | -0.185 |
They | -0.173 |
Token | Jim |
Token ID | 5395 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
| +0.097 |
because | +0.095 |
: | +0.088 |
" | +0.083 |
? | +0.071 |
Neg logit contributions | |
pollen | -0.435 |
turrets | -0.427 |
riches | -0.426 |
Majesty | -0.417 |
seas | -0.416 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ts | +0.440 |
riches | +0.427 |
turrets | +0.421 |
pollen | +0.420 |
miles | +0.417 |
Neg logit contributions | |
| -0.344 |
" | -0.301 |
because | -0.294 |
She | -0.284 |
. | -0.266 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ts | +0.570 |
riches | +0.562 |
miles | +0.561 |
seas | +0.548 |
pollen | +0.547 |
Neg logit contributions | |
| -0.169 |
" | -0.133 |
because | -0.120 |
She | -0.119 |
They | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
| +0.130 |
" | +0.108 |
because | +0.104 |
She | +0.099 |
. | +0.092 |
Neg logit contributions | |
ts | -0.275 |
riches | -0.269 |
turrets | -0.265 |
pollen | -0.264 |
miles | -0.264 |
Token | group |
Token ID | 1448 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
ts | +0.437 |
ief | +0.413 |
isher | +0.408 |
turrets | +0.401 |
lled | +0.400 |
Neg logit contributions | |
| -0.412 |
" | -0.380 |
because | -0.345 |
. | -0.332 |
She | -0.324 |
Token | of |
Token ID | 286 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ts | +0.517 |
miles | +0.511 |
riches | +0.490 |
turrets | +0.488 |
seas | +0.486 |
Neg logit contributions | |
| -0.501 |
" | -0.433 |
She | -0.422 |
because | -0.420 |
They | -0.381 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ounces | +0.377 |
isher | +0.376 |
asis | +0.373 |
Majesty | +0.369 |
ts | +0.366 |
Neg logit contributions | |
| -0.439 |
" | -0.405 |
. | -0.386 |
and | -0.371 |
because | -0.368 |
Token | chie |
Token ID | 3043 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
pollen | +0.231 |
Majesty | +0.220 |
ts | +0.210 |
pearl | +0.206 |
riches | +0.206 |
Neg logit contributions | |
| -0.613 |
because | -0.553 |
She | -0.544 |
. | -0.539 |
" | -0.534 |
Token | vous |
Token ID | 31222 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
ts | +0.557 |
riches | +0.536 |
pollen | +0.524 |
turrets | +0.514 |
Majesty | +0.506 |
Neg logit contributions | |
| -1.101 |
" | -0.993 |
because | -0.989 |
She | -0.954 |
. | -0.950 |
Token | mice |
Token ID | 10693 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ts | +0.556 |
riches | +0.524 |
pollen | +0.522 |
isher | +0.518 |
turrets | +0.514 |
Neg logit contributions | |
| -0.684 |
" | -0.633 |
because | -0.621 |
. | -0.601 |
She | -0.597 |
Token | came |
Token ID | 1625 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ts | +0.777 |
riches | +0.745 |
miles | +0.745 |
pollen | +0.734 |
turrets | +0.717 |
Neg logit contributions | |
| -0.423 |
" | -0.352 |
She | -0.339 |
because | -0.330 |
They | -0.285 |
Token | by |
Token ID | 416 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ts | +0.445 |
miles | +0.442 |
riches | +0.440 |
pollen | +0.436 |
turrets | +0.429 |
Neg logit contributions | |
| -0.203 |
" | -0.162 |
She | -0.156 |
because | -0.153 |
And | -0.129 |
Token | and |
Token ID | 290 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
ts | +0.454 |
riches | +0.441 |
miles | +0.440 |
pollen | +0.434 |
turrets | +0.427 |
Neg logit contributions | |
| -0.197 |
" | -0.160 |
She | -0.159 |
because | -0.150 |
: | -0.125 |
Token | her |
Token ID | 607 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ts | +0.212 |
riches | +0.211 |
turrets | +0.207 |
miles | +0.203 |
ief | +0.201 |
Neg logit contributions | |
| -0.348 |
" | -0.325 |
because | -0.315 |
. | -0.304 |
She | -0.303 |
Token | bricks |
Token ID | 28902 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ts | +0.573 |
riches | +0.554 |
turrets | +0.546 |
miles | +0.544 |
pollen | +0.543 |
Neg logit contributions | |
| -0.514 |
" | -0.455 |
because | -0.445 |
She | -0.428 |
. | -0.415 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
ts | +0.973 |
turrets | +0.958 |
riches | +0.952 |
isher | +0.950 |
seas | +0.939 |
Neg logit contributions | |
| -0.288 |
" | -0.224 |
She | -0.195 |
because | -0.181 |
They | -0.151 |
Token | build |
Token ID | 1382 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
| +0.036 |
" | +0.034 |
because | +0.033 |
She | +0.032 |
. | +0.031 |
Neg logit contributions | |
isher | -0.047 |
ief | -0.047 |
ubb | -0.047 |
riches | -0.046 |
ts | -0.046 |
Token | tall |
Token ID | 7331 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
isher | +0.719 |
confidence | +0.715 |
riches | +0.714 |
ubb | +0.709 |
ounces | +0.708 |
Neg logit contributions | |
| -0.469 |
" | -0.410 |
. | -0.405 |
because | -0.388 |
She | -0.372 |
Token | towers |
Token ID | 18028 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ts | +0.375 |
riches | +0.371 |
isher | +0.363 |
ief | +0.359 |
pollen | +0.357 |
Neg logit contributions | |
| -0.898 |
" | -0.837 |
because | -0.834 |
. | -0.825 |
She | -0.799 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ts | +1.294 |
turrets | +1.275 |
miles | +1.264 |
riches | +1.237 |
seas | +1.228 |
Neg logit contributions | |
| -0.291 |
" | -0.204 |
She | -0.170 |
because | -0.168 |
: | -0.114 |
Token | One |
Token ID | 1881 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
because | +0.169 |
| +0.140 |
: | +0.136 |
. | +0.130 |
? | +0.114 |
Neg logit contributions | |
Majesty | -0.676 |
turrets | -0.674 |
ounces | -0.654 |
pollen | -0.653 |
miles | -0.645 |
Token | day |
Token ID | 1110 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
| +0.097 |
" | +0.086 |
because | +0.086 |
She | +0.081 |
. | +0.080 |
Neg logit contributions | |
ts | -0.105 |
riches | -0.103 |
pollen | -0.101 |
ief | -0.101 |
Majesty | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ts | +0.488 |
miles | +0.478 |
riches | +0.475 |
turrets | +0.473 |
pollen | +0.473 |
Neg logit contributions | |
| -0.137 |
" | -0.100 |
because | -0.100 |
She | -0.088 |
: | -0.072 |
Token | she |
Token ID | 673 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
| +0.161 |
" | +0.131 |
because | +0.126 |
She | +0.119 |
: | +0.110 |
Neg logit contributions | |
ts | -0.370 |
riches | -0.361 |
miles | -0.358 |
turrets | -0.357 |
pollen | -0.356 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ts | +0.338 |
miles | +0.329 |
riches | +0.324 |
stones | +0.322 |
treasures | +0.322 |
Neg logit contributions | |
| -0.096 |
She | -0.072 |
" | -0.071 |
They | -0.055 |
: | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
because | +0.251 |
? | +0.229 |
: | +0.209 |
; | +0.206 |
. | +0.172 |
Neg logit contributions | |
directions | -0.853 |
Majesty | -0.849 |
riches | -0.829 |
seas | -0.819 |
turrets | -0.818 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
because | +0.194 |
She | +0.158 |
" | +0.155 |
� | +0.103 |
They | +0.087 |
Neg logit contributions | |
ts | -0.914 |
miles | -0.884 |
seas | -0.861 |
directions | -0.857 |
riches | -0.857 |
Token | That |
Token ID | 2504 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
| +0.536 |
She | +0.530 |
" | +0.521 |
because | +0.510 |
: | +0.483 |
Neg logit contributions | |
ts | -0.648 |
ounces | -0.606 |
miles | -0.601 |
aches | -0.595 |
an | -0.594 |
Token | night |
Token ID | 1755 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
| +0.062 |
" | +0.054 |
because | +0.054 |
She | +0.052 |
. | +0.051 |
Neg logit contributions | |
ts | -0.055 |
riches | -0.052 |
pollen | -0.051 |
miles | -0.051 |
turrets | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ts | +0.193 |
riches | +0.192 |
miles | +0.190 |
seas | +0.190 |
fortune | +0.187 |
Neg logit contributions | |
| -0.063 |
She | -0.052 |
" | -0.047 |
because | -0.042 |
They | -0.037 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
| +0.298 |
She | +0.258 |
: | +0.244 |
" | +0.238 |
. | +0.209 |
Neg logit contributions | |
ts | -0.594 |
miles | -0.587 |
seas | -0.581 |
riches | -0.570 |
turrets | -0.568 |
Token | my |
Token ID | 1820 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
ts | +0.115 |
riches | +0.112 |
turrets | +0.111 |
pollen | +0.110 |
miles | +0.110 |
Neg logit contributions | |
| -0.060 |
" | -0.051 |
because | -0.049 |
She | -0.047 |
. | -0.043 |
Token | went |
Token ID | 1816 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
ts | +0.177 |
riches | +0.172 |
turrets | +0.170 |
pollen | +0.169 |
miles | +0.169 |
Neg logit contributions | |
| -0.110 |
" | -0.094 |
because | -0.091 |
She | -0.088 |
. | -0.082 |
Token | to |
Token ID | 284 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
ts | +0.129 |
miles | +0.127 |
riches | +0.125 |
pollen | +0.124 |
seas | +0.123 |
Neg logit contributions | |
| -0.062 |
" | -0.053 |
because | -0.049 |
She | -0.048 |
They | -0.043 |
Token | bed |
Token ID | 3996 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
| +0.050 |
" | +0.047 |
because | +0.046 |
She | +0.046 |
: | +0.044 |
Neg logit contributions | |
ts | -0.036 |
riches | -0.034 |
miles | -0.034 |
pollen | -0.032 |
turrets | -0.032 |
Token | as |
Token ID | 355 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
| +0.021 |
" | +0.016 |
because | +0.014 |
She | +0.013 |
: | +0.010 |
Neg logit contributions | |
ts | -0.085 |
riches | -0.084 |
pollen | -0.083 |
turrets | -0.083 |
miles | -0.083 |
Token | he |
Token ID | 339 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
| +0.098 |
" | +0.081 |
because | +0.077 |
She | +0.072 |
. | +0.070 |
Neg logit contributions | |
ts | -0.202 |
riches | -0.199 |
turrets | -0.196 |
pollen | -0.196 |
isher | -0.196 |
Token | closed |
Token ID | 4838 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
| +0.072 |
because | +0.060 |
" | +0.059 |
. | +0.057 |
She | +0.056 |
Neg logit contributions | |
riches | -0.108 |
ts | -0.108 |
ief | -0.107 |
isher | -0.106 |
turrets | -0.106 |
Token | his |
Token ID | 465 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
ts | +0.111 |
pollen | +0.106 |
miles | +0.105 |
riches | +0.105 |
seas | +0.105 |
Neg logit contributions | |
| -0.096 |
" | -0.084 |
She | -0.081 |
because | -0.080 |
They | -0.073 |
Token | eyes |
Token ID | 2951 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ts | +0.132 |
riches | +0.127 |
turrets | +0.125 |
miles | +0.125 |
pollen | +0.123 |
Neg logit contributions | |
| -0.169 |
" | -0.153 |
because | -0.150 |
She | -0.145 |
. | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
pollen | +0.305 |
miles | +0.303 |
turrets | +0.302 |
seas | +0.301 |
riches | +0.298 |
Neg logit contributions | |
| -0.093 |
" | -0.068 |
She | -0.061 |
They | -0.057 |
Why | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
because | +0.330 |
| +0.293 |
? | +0.275 |
: | +0.272 |
. | +0.269 |
Neg logit contributions | |
pollen | -1.089 |
riches | -1.080 |
Majesty | -1.052 |
seas | -1.052 |
ts | -1.051 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
because | +0.142 |
" | +0.104 |
She | +0.081 |
but | +0.030 |
| +0.008 |
Neg logit contributions | |
ts | -1.214 |
miles | -1.213 |
riches | -1.179 |
pollen | -1.169 |
seas | -1.160 |
Token | As |
Token ID | 1722 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
| +0.582 |
" | +0.507 |
because | +0.498 |
She | +0.476 |
. | +0.450 |
Neg logit contributions | |
ts | -0.931 |
riches | -0.900 |
miles | -0.895 |
pollen | -0.889 |
turrets | -0.881 |
Token | he |
Token ID | 339 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
| +0.146 |
" | +0.134 |
She | +0.130 |
because | +0.128 |
: | +0.118 |
Neg logit contributions | |
ts | -0.238 |
miles | -0.236 |
seas | -0.231 |
riches | -0.230 |
pollen | -0.229 |
Token | lay |
Token ID | 3830 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
| +0.084 |
because | +0.069 |
" | +0.066 |
. | +0.065 |
and | +0.063 |
Neg logit contributions | |
Majesty | -0.112 |
riches | -0.112 |
ief | -0.111 |
decisions | -0.111 |
isher | -0.110 |
Token | No |
Token ID | 2949 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
| +0.246 |
" | +0.207 |
because | +0.201 |
She | +0.197 |
. | +0.182 |
Neg logit contributions | |
ts | -0.387 |
riches | -0.379 |
turrets | -0.371 |
pollen | -0.369 |
miles | -0.367 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ts | +0.314 |
riches | +0.308 |
miles | +0.305 |
turrets | +0.303 |
Majesty | +0.303 |
Neg logit contributions | |
| -0.087 |
" | -0.061 |
She | -0.055 |
because | -0.055 |
: | -0.042 |
Token | no |
Token ID | 645 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
| +0.340 |
" | +0.289 |
because | +0.280 |
She | +0.266 |
. | +0.249 |
Neg logit contributions | |
ts | -0.611 |
riches | -0.598 |
turrets | -0.589 |
pollen | -0.586 |
miles | -0.586 |
Token | , |
Token ID | 11 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ts | +0.153 |
riches | +0.150 |
miles | +0.149 |
turrets | +0.149 |
pollen | +0.148 |
Neg logit contributions | |
| -0.045 |
" | -0.033 |
because | -0.030 |
She | -0.029 |
: | -0.024 |
Token | no |
Token ID | 645 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
| +0.335 |
" | +0.298 |
because | +0.296 |
She | +0.267 |
. | +0.254 |
Neg logit contributions | |
ts | -0.624 |
riches | -0.618 |
turrets | -0.604 |
pollen | -0.599 |
isher | -0.598 |
Token | ! |
Token ID | 0 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ts | +0.138 |
riches | +0.135 |
turrets | +0.134 |
pollen | +0.133 |
miles | +0.133 |
Neg logit contributions | |
| -0.057 |
" | -0.047 |
because | -0.045 |
She | -0.042 |
. | -0.039 |
Token | I |
Token ID | 314 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
| +0.450 |
because | +0.382 |
" | +0.371 |
: | +0.358 |
. | +0.357 |
Neg logit contributions | |
ounces | -0.768 |
Majesty | -0.762 |
pollen | -0.755 |
turrets | -0.745 |
isher | -0.739 |
Token | want |
Token ID | 765 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
| +0.039 |
" | +0.034 |
because | +0.033 |
She | +0.032 |
. | +0.030 |
Neg logit contributions | |
ts | -0.046 |
riches | -0.045 |
turrets | -0.044 |
pollen | -0.044 |
miles | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ts | +0.178 |
riches | +0.177 |
pollen | +0.175 |
miles | +0.174 |
turrets | +0.173 |
Neg logit contributions | |
| -0.077 |
" | -0.063 |
because | -0.059 |
She | -0.058 |
: | -0.050 |
Token | play |
Token ID | 711 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
| +0.051 |
because | +0.045 |
" | +0.044 |
She | +0.043 |
. | +0.043 |
Neg logit contributions | |
ts | -0.054 |
riches | -0.053 |
isher | -0.052 |
turrets | -0.052 |
pollen | -0.051 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ts | +0.339 |
riches | +0.326 |
miles | +0.324 |
pollen | +0.322 |
turrets | +0.322 |
Neg logit contributions | |
| -0.148 |
" | -0.121 |
because | -0.116 |
She | -0.114 |
: | -0.101 |
Token | play |
Token ID | 711 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
| +0.022 |
" | +0.019 |
because | +0.019 |
She | +0.018 |
. | +0.018 |
Neg logit contributions | |
ts | -0.027 |
riches | -0.026 |
isher | -0.026 |
pollen | -0.026 |
ounces | -0.026 |
Token | together |
Token ID | 1978 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ts | +0.343 |
riches | +0.321 |
seas | +0.321 |
miles | +0.320 |
pollen | +0.319 |
Neg logit contributions | |
| -0.204 |
" | -0.175 |
She | -0.173 |
because | -0.170 |
: | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
ts | +0.094 |
pollen | +0.090 |
miles | +0.089 |
riches | +0.089 |
seas | +0.088 |
Neg logit contributions | |
| -0.029 |
She | -0.023 |
" | -0.022 |
because | -0.019 |
They | -0.015 |
Token | One |
Token ID | 1881 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
because | +0.373 |
| +0.331 |
" | +0.313 |
; | +0.305 |
: | +0.303 |
Neg logit contributions | |
turrets | -0.827 |
seas | -0.822 |
fishes | -0.795 |
ounces | -0.792 |
pollen | -0.788 |
Token | day |
Token ID | 1110 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
| +0.315 |
" | +0.281 |
because | +0.276 |
She | +0.267 |
. | +0.257 |
Neg logit contributions | |
ts | -0.296 |
riches | -0.287 |
turrets | -0.282 |
pollen | -0.281 |
miles | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
seas | +0.153 |
ts | +0.150 |
miles | +0.147 |
coins | +0.145 |
riches | +0.145 |
Neg logit contributions | |
| -0.052 |
She | -0.048 |
because | -0.047 |
" | -0.044 |
Why | -0.034 |
Token | they |
Token ID | 484 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
| +0.269 |
She | +0.230 |
because | +0.222 |
" | +0.221 |
: | +0.208 |
Neg logit contributions | |
seas | -0.597 |
ts | -0.589 |
miles | -0.576 |
turrets | -0.563 |
riches | -0.563 |
Token | go |
Token ID | 467 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
| +0.024 |
" | +0.021 |
because | +0.021 |
She | +0.020 |
. | +0.019 |
Neg logit contributions | |
ts | -0.025 |
riches | -0.024 |
pollen | -0.024 |
ounces | -0.024 |
turrets | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ts | +0.308 |
riches | +0.301 |
miles | +0.300 |
pollen | +0.298 |
turrets | +0.298 |
Neg logit contributions | |
| -0.092 |
" | -0.071 |
because | -0.066 |
She | -0.063 |
: | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
| +0.028 |
" | +0.024 |
because | +0.023 |
She | +0.022 |
. | +0.021 |
Neg logit contributions | |
ts | -0.046 |
riches | -0.045 |
turrets | -0.045 |
pollen | -0.045 |
isher | -0.044 |
Token | park |
Token ID | 3952 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ts | +0.119 |
riches | +0.115 |
pollen | +0.112 |
turrets | +0.112 |
miles | +0.112 |
Neg logit contributions | |
| -0.136 |
" | -0.122 |
because | -0.119 |
She | -0.116 |
. | -0.112 |
Token | replace |
Token ID | 6330 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
isher | +0.040 |
ts | +0.039 |
ounces | +0.038 |
seas | +0.038 |
ief | +0.037 |
Neg logit contributions | |
| -0.034 |
. | -0.029 |
" | -0.028 |
because | -0.028 |
She | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
ts | +0.409 |
ounces | +0.407 |
ief | +0.406 |
turrets | +0.403 |
Majesty | +0.402 |
Neg logit contributions | |
| -0.227 |
because | -0.189 |
" | -0.185 |
. | -0.180 |
and | -0.161 |
Token | strong |
Token ID | 1913 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ts | +0.187 |
ief | +0.173 |
isher | +0.173 |
ounces | +0.168 |
ieve | +0.165 |
Neg logit contributions | |
| -0.234 |
" | -0.213 |
because | -0.206 |
. | -0.204 |
She | -0.198 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ts | +0.398 |
ief | +0.375 |
isher | +0.367 |
riches | +0.366 |
ieve | +0.366 |
Neg logit contributions | |
| -0.407 |
" | -0.375 |
because | -0.367 |
. | -0.356 |
She | -0.351 |
Token | flower |
Token ID | 25547 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
pollen | +0.469 |
ts | +0.465 |
turrets | +0.464 |
riches | +0.462 |
miles | +0.455 |
Neg logit contributions | |
| -0.211 |
" | -0.172 |
She | -0.159 |
because | -0.154 |
: | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
pollen | +0.499 |
riches | +0.498 |
ts | +0.496 |
turrets | +0.485 |
miles | +0.485 |
Neg logit contributions | |
| -0.146 |
" | -0.111 |
She | -0.098 |
because | -0.091 |
They | -0.079 |
Token | He |
Token ID | 679 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
| +0.331 |
because | +0.252 |
" | +0.225 |
: | +0.213 |
. | +0.211 |
Neg logit contributions | |
ts | -0.957 |
riches | -0.950 |
turrets | -0.948 |
ounces | -0.936 |
isher | -0.934 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
| +0.073 |
" | +0.063 |
because | +0.060 |
She | +0.056 |
. | +0.055 |
Neg logit contributions | |
riches | -0.115 |
ts | -0.114 |
ief | -0.113 |
turrets | -0.113 |
miles | -0.113 |
Token | something |
Token ID | 1223 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ts | +0.164 |
Majesty | +0.160 |
isher | +0.160 |
ief | +0.160 |
riches | +0.158 |
Neg logit contributions | |
| -0.031 |
" | -0.021 |
because | -0.019 |
. | -0.014 |
She | -0.013 |
Token | more |
Token ID | 517 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
riches | +0.206 |
pollen | +0.200 |
treasures | +0.199 |
ts | +0.196 |
seas | +0.194 |
Neg logit contributions | |
| -0.209 |
" | -0.187 |
She | -0.186 |
They | -0.172 |
because | -0.169 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
riches | +0.297 |
ts | +0.290 |
pollen | +0.283 |
miles | +0.281 |
seas | +0.277 |
Neg logit contributions | |
| -0.276 |
" | -0.252 |
She | -0.246 |
because | -0.224 |
They | -0.219 |
Token | became |
Token ID | 2627 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ts | +0.080 |
riches | +0.078 |
turrets | +0.077 |
pollen | +0.076 |
miles | +0.076 |
Neg logit contributions | |
| -0.053 |
" | -0.046 |
because | -0.045 |
She | -0.043 |
. | -0.040 |
Token | best |
Token ID | 1266 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
ts | +0.225 |
isher | +0.224 |
turrets | +0.223 |
ounces | +0.222 |
riches | +0.218 |
Neg logit contributions | |
| -0.209 |
" | -0.186 |
because | -0.178 |
. | -0.170 |
She | -0.168 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ts | +0.257 |
riches | +0.248 |
ief | +0.246 |
turrets | +0.245 |
isher | +0.242 |
Neg logit contributions | |
| -0.411 |
" | -0.375 |
because | -0.368 |
. | -0.359 |
She | -0.350 |
Token | and |
Token ID | 290 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ts | +0.417 |
miles | +0.415 |
riches | +0.402 |
pollen | +0.392 |
treasures | +0.390 |
Neg logit contributions | |
| -0.136 |
" | -0.117 |
She | -0.117 |
� | -0.084 |
On | -0.083 |
Token | always |
Token ID | 1464 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
| +0.169 |
" | +0.148 |
because | +0.140 |
She | +0.128 |
They | +0.122 |
Neg logit contributions | |
isher | -0.348 |
ief | -0.343 |
ounces | -0.341 |
ieve | -0.338 |
ts | -0.337 |
Token | helped |
Token ID | 4193 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
ts | +0.132 |
riches | +0.128 |
turrets | +0.127 |
pollen | +0.126 |
miles | +0.126 |
Neg logit contributions | |
| -0.116 |
" | -0.103 |
because | -0.101 |
She | -0.097 |
. | -0.094 |
Token | each |
Token ID | 1123 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
turrets | +0.080 |
isher | +0.078 |
Majesty | +0.078 |
riches | +0.078 |
ts | +0.077 |
Neg logit contributions | |
| -0.035 |
" | -0.028 |
because | -0.027 |
. | -0.026 |
She | -0.024 |
Token | other |
Token ID | 584 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Majesty | +0.232 |
ts | +0.229 |
turrets | +0.225 |
riches | +0.222 |
ief | +0.213 |
Neg logit contributions | |
| -0.278 |
" | -0.250 |
because | -0.246 |
. | -0.243 |
and | -0.230 |
Token | when |
Token ID | 618 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
ts | +0.471 |
turrets | +0.467 |
riches | +0.465 |
isher | +0.464 |
pollen | +0.459 |
Neg logit contributions | |
| -0.141 |
" | -0.107 |
because | -0.106 |
. | -0.096 |
She | -0.086 |
Token | they |
Token ID | 484 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
| +0.032 |
" | +0.024 |
because | +0.021 |
. | +0.018 |
She | +0.018 |
Neg logit contributions | |
isher | -0.125 |
ts | -0.124 |
riches | -0.123 |
turrets | -0.122 |
pollen | -0.122 |
Token | needed |
Token ID | 2622 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
ts | +0.050 |
riches | +0.049 |
turrets | +0.048 |
pollen | +0.048 |
miles | +0.048 |
Neg logit contributions | |
| -0.039 |
" | -0.034 |
because | -0.033 |
She | -0.032 |
. | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
isher | +0.187 |
ounces | +0.187 |
ubb | +0.186 |
plank | +0.185 |
chie | +0.183 |
Neg logit contributions | |
| -0.089 |
. | -0.071 |
" | -0.069 |
because | -0.062 |
She | -0.060 |
Token | model |
Token ID | 2746 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ts | +0.145 |
ief | +0.135 |
ounces | +0.134 |
isher | +0.134 |
pollen | +0.131 |
Neg logit contributions | |
| -0.132 |
" | -0.116 |
because | -0.112 |
. | -0.109 |
She | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
ts | +0.432 |
riches | +0.417 |
pollen | +0.415 |
ounces | +0.406 |
miles | +0.406 |
Neg logit contributions | |
| -0.382 |
" | -0.338 |
because | -0.334 |
. | -0.318 |
She | -0.317 |
Token | a |
Token ID | 257 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
ts | +0.192 |
isher | +0.188 |
ounces | +0.187 |
riches | +0.186 |
turrets | +0.185 |
Neg logit contributions | |
| -0.125 |
" | -0.109 |
because | -0.103 |
She | -0.099 |
. | -0.098 |
Token | castle |
Token ID | 16669 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ts | +0.122 |
ief | +0.112 |
isher | +0.111 |
pollen | +0.111 |
riches | +0.110 |
Neg logit contributions | |
| -0.144 |
" | -0.130 |
because | -0.125 |
. | -0.122 |
She | -0.118 |
Token | with |
Token ID | 351 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ts | +0.618 |
riches | +0.605 |
miles | +0.600 |
turrets | +0.600 |
pollen | +0.594 |
Neg logit contributions | |
| -0.198 |
" | -0.152 |
because | -0.137 |
She | -0.137 |
: | -0.111 |
Token | her |
Token ID | 607 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
| +0.023 |
" | +0.020 |
. | +0.019 |
because | +0.019 |
She | +0.019 |
Neg logit contributions | |
ts | -0.041 |
isher | -0.041 |
ief | -0.040 |
Majesty | -0.040 |
ounces | -0.040 |
Token | building |
Token ID | 2615 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ts | +0.168 |
riches | +0.164 |
turrets | +0.160 |
pollen | +0.158 |
miles | +0.158 |
Neg logit contributions | |
| -0.191 |
" | -0.171 |
because | -0.167 |
She | -0.165 |
. | -0.154 |
Token | blocks |
Token ID | 7021 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ts | +0.550 |
riches | +0.540 |
pollen | +0.534 |
turrets | +0.532 |
miles | +0.532 |
Neg logit contributions | |
| -0.134 |
" | -0.097 |
because | -0.091 |
She | -0.079 |
. | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
ts | +0.638 |
turrets | +0.627 |
miles | +0.624 |
riches | +0.624 |
seas | +0.621 |
Neg logit contributions | |
| -0.154 |
" | -0.116 |
She | -0.097 |
because | -0.082 |
They | -0.067 |
Token | She |
Token ID | 1375 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
because | +0.242 |
: | +0.209 |
? | +0.207 |
; | +0.194 |
. | +0.187 |
Neg logit contributions | |
Majesty | -0.948 |
riches | -0.911 |
majesty | -0.889 |
energy | -0.884 |
pollen | -0.882 |
Token | to |
Token ID | 284 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
miles | +0.537 |
turrets | +0.526 |
seas | +0.520 |
pollen | +0.518 |
ts | +0.518 |
Neg logit contributions | |
| -0.153 |
" | -0.126 |
And | -0.104 |
She | -0.104 |
because | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
| +0.026 |
" | +0.022 |
because | +0.022 |
She | +0.021 |
. | +0.020 |
Neg logit contributions | |
ts | -0.029 |
isher | -0.029 |
riches | -0.028 |
ounces | -0.028 |
pollen | -0.028 |
Token | sky |
Token ID | 6766 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
ts | +0.130 |
riches | +0.123 |
ief | +0.121 |
isher | +0.121 |
ounces | +0.120 |
Neg logit contributions | |
| -0.173 |
" | -0.154 |
because | -0.151 |
. | -0.147 |
She | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
miles | +0.275 |
turrets | +0.273 |
ts | +0.273 |
pollen | +0.270 |
reflections | +0.267 |
Neg logit contributions | |
| -0.067 |
" | -0.047 |
And | -0.042 |
She | -0.039 |
because | -0.035 |
Token | Something |
Token ID | 13742 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
| +0.397 |
because | +0.368 |
. | +0.322 |
" | +0.314 |
? | +0.294 |
Neg logit contributions | |
pollen | -0.933 |
riches | -0.894 |
miles | -0.882 |
turrets | -0.878 |
ts | -0.873 |
Token | was |
Token ID | 373 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
ts | +0.067 |
miles | +0.067 |
pollen | +0.065 |
stones | +0.065 |
seas | +0.065 |
Neg logit contributions | |
| -0.063 |
She | -0.055 |
" | -0.054 |
because | -0.052 |
And | -0.052 |
Token | z |
Token ID | 1976 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
| +0.014 |
She | +0.012 |
" | +0.012 |
because | +0.012 |
And | +0.012 |
Neg logit contributions | |
ts | -0.015 |
miles | -0.015 |
turrets | -0.015 |
riches | -0.014 |
pollen | -0.014 |
Token | ooming |
Token ID | 30602 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ts | +0.196 |
riches | +0.185 |
turrets | +0.182 |
miles | +0.181 |
pollen | +0.179 |
Neg logit contributions | |
| -0.361 |
" | -0.331 |
because | -0.324 |
She | -0.319 |
. | -0.305 |
Token | quickly |
Token ID | 2952 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
ts | +0.412 |
miles | +0.404 |
turrets | +0.398 |
seas | +0.394 |
riches | +0.393 |
Neg logit contributions | |
| -0.187 |
" | -0.152 |
She | -0.138 |
because | -0.132 |
: | -0.119 |
Token | over |
Token ID | 625 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
miles | +0.224 |
ts | +0.221 |
turrets | +0.218 |
stones | +0.217 |
pollen | +0.215 |
Neg logit contributions | |
| -0.061 |
She | -0.041 |
" | -0.039 |
because | -0.032 |
And | -0.028 |
Token | her |
Token ID | 607 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
miles | +0.286 |
ts | +0.281 |
turrets | +0.275 |
pollen | +0.273 |
stones | +0.271 |
Neg logit contributions | |
| -0.189 |
" | -0.168 |
because | -0.161 |
She | -0.153 |
And | -0.143 |
Token | more |
Token ID | 517 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
| +0.265 |
" | +0.217 |
because | +0.209 |
She | +0.197 |
. | +0.182 |
Neg logit contributions | |
ts | -0.602 |
riches | -0.589 |
turrets | -0.581 |
pollen | -0.580 |
miles | -0.579 |
Token | passengers |
Token ID | 10405 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ts | +0.315 |
riches | +0.306 |
turrets | +0.302 |
pollen | +0.302 |
miles | +0.300 |
Neg logit contributions | |
| -0.236 |
" | -0.206 |
because | -0.202 |
She | -0.193 |
. | -0.186 |
Token | would |
Token ID | 561 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ts | +0.571 |
riches | +0.559 |
miles | +0.548 |
turrets | +0.548 |
pollen | +0.547 |
Neg logit contributions | |
| -0.234 |
" | -0.188 |
because | -0.178 |
She | -0.172 |
. | -0.149 |
Token | come |
Token ID | 1282 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
| +0.027 |
" | +0.024 |
because | +0.023 |
She | +0.023 |
. | +0.021 |
Neg logit contributions | |
ts | -0.027 |
riches | -0.026 |
miles | -0.026 |
pollen | -0.026 |
turrets | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
riches | +0.212 |
miles | +0.210 |
ts | +0.209 |
turrets | +0.206 |
fortune | +0.201 |
Neg logit contributions | |
| -0.163 |
" | -0.146 |
She | -0.137 |
because | -0.137 |
: | -0.126 |
Token | he |
Token ID | 339 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
| +0.294 |
" | +0.249 |
because | +0.245 |
She | +0.231 |
. | +0.230 |
Neg logit contributions | |
ts | -0.352 |
isher | -0.351 |
ounces | -0.339 |
ubb | -0.336 |
pollen | -0.335 |
Token | would |
Token ID | 561 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ts | +0.012 |
riches | +0.012 |
turrets | +0.012 |
pollen | +0.012 |
miles | +0.012 |
Neg logit contributions | |
| -0.007 |
" | -0.006 |
because | -0.006 |
She | -0.005 |
. | -0.005 |
Token | never |
Token ID | 1239 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
| +0.031 |
" | +0.028 |
because | +0.027 |
She | +0.026 |
. | +0.025 |
Neg logit contributions | |
ts | -0.032 |
riches | -0.032 |
miles | -0.031 |
pollen | -0.031 |
turrets | -0.031 |
Token | have |
Token ID | 423 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ts | +0.095 |
turrets | +0.091 |
riches | +0.091 |
isher | +0.091 |
pollen | +0.090 |
Neg logit contributions | |
| -0.095 |
because | -0.083 |
" | -0.083 |
. | -0.080 |
She | -0.079 |
Token | to |
Token ID | 284 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
ts | +0.184 |
turrets | +0.179 |
isher | +0.178 |
riches | +0.178 |
pollen | +0.177 |
Neg logit contributions | |
| -0.078 |
" | -0.062 |
because | -0.061 |
. | -0.056 |
She | -0.054 |
Token | quit |
Token ID | 11238 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
| +0.012 |
because | +0.011 |
" | +0.010 |
. | +0.010 |
She | +0.010 |
Neg logit contributions | |
ts | -0.013 |
isher | -0.013 |
pollen | -0.013 |
turrets | -0.012 |
riches | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ts | +0.734 |
pollen | +0.718 |
riches | +0.712 |
stones | +0.709 |
miles | +0.708 |
Neg logit contributions | |
| -0.226 |
" | -0.176 |
She | -0.170 |
because | -0.151 |
And | -0.127 |
Token | berries |
Token ID | 36322 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
| +0.213 |
" | +0.188 |
because | +0.184 |
and | +0.179 |
. | +0.178 |
Neg logit contributions | |
ief | -0.226 |
isher | -0.220 |
ieve | -0.219 |
ubb | -0.218 |
ymes | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ts | +0.562 |
pollen | +0.549 |
stones | +0.535 |
miles | +0.532 |
riches | +0.528 |
Neg logit contributions | |
| -0.147 |
" | -0.113 |
She | -0.109 |
because | -0.097 |
And | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
because | +0.288 |
: | +0.272 |
| +0.260 |
? | +0.257 |
. | +0.250 |
Neg logit contributions | |
pollen | -0.754 |
riches | -0.737 |
ts | -0.733 |
stones | -0.725 |
fishes | -0.722 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
because | +0.114 |
" | +0.065 |
She | +0.063 |
. | +0.026 |
: | +0.021 |
Neg logit contributions | |
ts | -0.870 |
miles | -0.862 |
seas | -0.837 |
pollen | -0.833 |
riches | -0.828 |
Token | As |
Token ID | 1722 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
| +0.430 |
because | +0.392 |
" | +0.390 |
She | +0.372 |
. | +0.356 |
Neg logit contributions | |
ts | -0.626 |
miles | -0.605 |
riches | -0.598 |
pollen | -0.595 |
turrets | -0.592 |
Token | they |
Token ID | 484 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
ts | +0.013 |
riches | +0.013 |
miles | +0.013 |
pollen | +0.013 |
turrets | +0.013 |
Neg logit contributions | |
| -0.006 |
" | -0.005 |
because | -0.005 |
She | -0.005 |
. | -0.004 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
Majesty | +0.122 |
riches | +0.120 |
ts | +0.119 |
decisions | +0.118 |
turrets | +0.118 |
Neg logit contributions | |
| -0.071 |
because | -0.058 |
" | -0.058 |
She | -0.053 |
. | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
ts | +0.529 |
riches | +0.510 |
miles | +0.510 |
pollen | +0.500 |
seas | +0.498 |
Neg logit contributions | |
| -0.154 |
" | -0.112 |
She | -0.108 |
because | -0.100 |
. | -0.075 |
Token | Benny |
Token ID | 44275 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
| +0.227 |
" | +0.186 |
because | +0.182 |
She | +0.166 |
. | +0.159 |
Neg logit contributions | |
ts | -0.482 |
riches | -0.475 |
turrets | -0.470 |
isher | -0.467 |
ounces | -0.466 |
Token | noticed |
Token ID | 6810 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ts | +0.243 |
riches | +0.237 |
turrets | +0.233 |
pollen | +0.233 |
miles | +0.232 |
Neg logit contributions | |
| -0.180 |
" | -0.156 |
because | -0.153 |
She | -0.147 |
. | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
ts | +0.628 |
pollen | +0.595 |
isher | +0.593 |
riches | +0.588 |
miles | +0.586 |
Neg logit contributions | |
| -0.163 |
She | -0.111 |
" | -0.110 |
because | -0.095 |
Her | -0.073 |
Token | Don |
Token ID | 2094 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
| +0.355 |
because | +0.323 |
" | +0.318 |
. | +0.311 |
: | +0.308 |
Neg logit contributions | |
ounces | -0.736 |
pollen | -0.728 |
Majesty | -0.727 |
riches | -0.722 |
ts | -0.721 |
Token | 't |
Token ID | 470 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
| +0.023 |
because | +0.020 |
" | +0.020 |
She | +0.019 |
. | +0.017 |
Neg logit contributions | |
ts | -0.055 |
miles | -0.053 |
ief | -0.052 |
riches | -0.051 |
pollen | -0.051 |
Token | break |
Token ID | 2270 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
ts | +0.110 |
riches | +0.107 |
turrets | +0.105 |
pollen | +0.105 |
miles | +0.104 |
Neg logit contributions | |
| -0.099 |
" | -0.087 |
because | -0.086 |
She | -0.082 |
. | -0.079 |
Token | our |
Token ID | 674 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
riches | +0.398 |
ts | +0.393 |
turrets | +0.390 |
pollen | +0.384 |
miles | +0.383 |
Neg logit contributions | |
| -0.322 |
" | -0.282 |
because | -0.279 |
. | -0.263 |
She | -0.259 |
Token | house |
Token ID | 2156 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ief | +0.339 |
ubb | +0.327 |
confidence | +0.327 |
ounces | +0.323 |
ts | +0.323 |
Neg logit contributions | |
| -0.382 |
. | -0.360 |
because | -0.358 |
" | -0.355 |
and | -0.331 |
Token | again |
Token ID | 757 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
ts | +0.559 |
riches | +0.528 |
miles | +0.527 |
isher | +0.526 |
turrets | +0.523 |
Neg logit contributions | |
| -0.214 |
" | -0.171 |
She | -0.164 |
because | -0.151 |
: | -0.129 |
Token | ." |
Token ID | 526 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
ts | +0.224 |
miles | +0.211 |
pollen | +0.211 |
riches | +0.210 |
decisions | +0.207 |
Neg logit contributions | |
| -0.111 |
She | -0.103 |
" | -0.100 |
because | -0.087 |
� | -0.082 |
Token | Rex |
Token ID | 17853 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
because | +0.162 |
; | +0.143 |
? | +0.122 |
: | +0.118 |
– | +0.113 |
Neg logit contributions | |
pollen | -0.652 |
ts | -0.649 |
nests | -0.642 |
lands | -0.637 |
miles | -0.630 |
Token | w |
Token ID | 266 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ts | +0.231 |
pollen | +0.218 |
riches | +0.212 |
turrets | +0.210 |
miles | +0.209 |
Neg logit contributions | |
| -0.213 |
" | -0.187 |
because | -0.187 |
She | -0.179 |
. | -0.168 |
Token | ags |
Token ID | 3775 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
riches | +0.135 |
turrets | +0.132 |
seas | +0.128 |
miles | +0.128 |
pollen | +0.128 |
Neg logit contributions | |
| -0.265 |
" | -0.238 |
: | -0.235 |
because | -0.234 |
. | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ts | +0.662 |
pollen | +0.657 |
miles | +0.646 |
riches | +0.646 |
turrets | +0.642 |
Neg logit contributions | |
| -0.146 |
" | -0.101 |
She | -0.079 |
because | -0.078 |
They | -0.060 |
Token | She |
Token ID | 1375 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
because | +0.344 |
. | +0.269 |
: | +0.269 |
; | +0.261 |
| +0.248 |
Neg logit contributions | |
pollen | -0.740 |
ocol | -0.706 |
ounces | -0.691 |
turrets | -0.687 |
tad | -0.675 |
Token | was |
Token ID | 373 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
| +0.084 |
" | +0.071 |
because | +0.069 |
She | +0.065 |
. | +0.063 |
Neg logit contributions | |
ts | -0.141 |
riches | -0.140 |
isher | -0.137 |
turrets | -0.137 |
ief | -0.137 |
Token | proud |
Token ID | 6613 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
ts | +0.067 |
riches | +0.066 |
isher | +0.066 |
turrets | +0.064 |
ounces | +0.064 |
Neg logit contributions | |
| -0.050 |
" | -0.044 |
because | -0.043 |
She | -0.040 |
. | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
pollen | +0.145 |
treasures | +0.139 |
stones | +0.137 |
turrets | +0.136 |
riches | +0.136 |
Neg logit contributions | |
| -0.142 |
" | -0.126 |
She | -0.124 |
They | -0.120 |
because | -0.118 |
Token | her |
Token ID | 607 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ts | +0.298 |
miles | +0.284 |
riches | +0.284 |
pollen | +0.284 |
turrets | +0.278 |
Neg logit contributions | |
| -0.187 |
" | -0.161 |
because | -0.157 |
She | -0.146 |
. | -0.136 |
Token | angel |
Token ID | 18304 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ts | +0.339 |
riches | +0.332 |
turrets | +0.326 |
pollen | +0.325 |
miles | +0.322 |
Neg logit contributions | |
| -0.217 |
" | -0.184 |
because | -0.178 |
She | -0.176 |
. | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ts | +0.707 |
riches | +0.697 |
pollen | +0.691 |
turrets | +0.688 |
miles | +0.686 |
Neg logit contributions | |
| -0.111 |
" | -0.065 |
because | -0.053 |
She | -0.047 |
: | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
because | +0.232 |
; | +0.150 |
. | +0.149 |
: | +0.141 |
and | +0.129 |
Neg logit contributions | |
pollen | -0.840 |
Majesty | -0.800 |
tad | -0.798 |
majesty | -0.790 |
angles | -0.786 |
Token |
|
Token ID | 198 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
because | +0.203 |
" | +0.142 |
but | +0.115 |
She | +0.111 |
| +0.109 |
Neg logit contributions | |
ts | -0.931 |
miles | -0.906 |
pollen | -0.885 |
riches | -0.864 |
turrets | -0.856 |
Token | She |
Token ID | 3347 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
| +0.366 |
because | +0.333 |
" | +0.324 |
She | +0.276 |
. | +0.274 |
Neg logit contributions | |
ts | -0.823 |
miles | -0.795 |
pollen | -0.780 |
ief | -0.775 |
turrets | -0.771 |
Token | some |
Token ID | 617 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ts | +0.269 |
riches | +0.261 |
turrets | +0.258 |
pollen | +0.256 |
isher | +0.255 |
Neg logit contributions | |
| -0.199 |
" | -0.171 |
because | -0.169 |
She | -0.159 |
. | -0.155 |
Token | sugar |
Token ID | 7543 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ts | +0.352 |
riches | +0.343 |
pollen | +0.335 |
turrets | +0.333 |
miles | +0.331 |
Neg logit contributions | |
| -0.448 |
" | -0.405 |
because | -0.394 |
She | -0.388 |
. | -0.366 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
isher | +0.640 |
ts | +0.636 |
seas | +0.633 |
riches | +0.622 |
pollen | +0.621 |
Neg logit contributions | |
| -0.298 |
" | -0.243 |
She | -0.232 |
They | -0.203 |
And | -0.197 |
Token | The |
Token ID | 383 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
because | +0.209 |
| +0.182 |
" | +0.177 |
: | +0.159 |
? | +0.155 |
Neg logit contributions | |
turrets | -0.466 |
riches | -0.458 |
ounces | -0.446 |
miles | -0.441 |
pollen | -0.440 |
Token | man |
Token ID | 582 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
| +0.050 |
" | +0.045 |
. | +0.040 |
because | +0.040 |
She | +0.040 |
Neg logit contributions | |
ts | -0.053 |
pollen | -0.053 |
isher | -0.052 |
turrets | -0.052 |
miles | -0.052 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ts | +0.366 |
riches | +0.354 |
turrets | +0.348 |
pollen | +0.346 |
miles | +0.343 |
Neg logit contributions | |
| -0.311 |
" | -0.271 |
because | -0.267 |
She | -0.261 |
. | -0.243 |
Token | and |
Token ID | 290 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
pearl | +0.308 |
riches | +0.308 |
rier | +0.307 |
turrets | +0.303 |
seas | +0.302 |
Neg logit contributions | |
| -0.114 |
She | -0.081 |
because | -0.077 |
" | -0.076 |
They | -0.072 |
Token | said |
Token ID | 531 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
| +0.140 |
" | +0.115 |
because | +0.111 |
She | +0.105 |
. | +0.097 |
Neg logit contributions | |
ts | -0.309 |
riches | -0.302 |
turrets | -0.298 |
pollen | -0.298 |
miles | -0.297 |
Token | , |
Token ID | 11 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
| +0.011 |
because | +0.008 |
She | +0.008 |
" | +0.007 |
They | +0.006 |
Neg logit contributions | |
ts | -0.034 |
riches | -0.033 |
pollen | -0.033 |
Majesty | -0.033 |
ounces | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
? | +0.123 |
| +0.118 |
because | +0.113 |
She | +0.101 |
They | +0.086 |
Neg logit contributions | |
rier | -0.452 |
Majesty | -0.450 |
ts | -0.433 |
pollen | -0.432 |
ounces | -0.428 |
Token | Sure |
Token ID | 19457 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
| +0.168 |
" | +0.148 |
because | +0.146 |
She | +0.138 |
. | +0.133 |
Neg logit contributions | |
ts | -0.223 |
riches | -0.218 |
pollen | -0.216 |
miles | -0.215 |
turrets | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ts | +0.470 |
miles | +0.458 |
riches | +0.449 |
pollen | +0.447 |
turrets | +0.443 |
Neg logit contributions | |
| -0.117 |
" | -0.080 |
She | -0.070 |
because | -0.061 |
: | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
because | +0.160 |
: | +0.104 |
? | +0.104 |
" | +0.103 |
. | +0.103 |
Neg logit contributions | |
miles | -0.951 |
ts | -0.951 |
turrets | -0.942 |
riches | -0.937 |
pollen | -0.937 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
because | +0.169 |
She | +0.093 |
" | +0.090 |
but | +0.043 |
. | +0.042 |
Neg logit contributions | |
ts | -0.940 |
miles | -0.927 |
riches | -0.866 |
ounces | -0.865 |
pollen | -0.857 |
Token | Finally |
Token ID | 11158 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
| +0.452 |
" | +0.394 |
because | +0.388 |
She | +0.369 |
. | +0.349 |
Neg logit contributions | |
ts | -0.744 |
miles | -0.715 |
riches | -0.713 |
turrets | -0.707 |
pollen | -0.703 |
Token | , |
Token ID | 11 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
| +0.015 |
" | +0.011 |
because | +0.010 |
She | +0.010 |
. | +0.007 |
Neg logit contributions | |
ts | -0.064 |
riches | -0.063 |
miles | -0.063 |
turrets | -0.062 |
pollen | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
| +0.255 |
" | +0.212 |
because | +0.206 |
. | +0.181 |
She | +0.181 |
Neg logit contributions | |
ts | -0.541 |
riches | -0.534 |
isher | -0.529 |
ounces | -0.526 |
ief | -0.524 |
Token | war |
Token ID | 1175 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
isher | +0.181 |
ocol | +0.170 |
ounces | +0.170 |
ts | +0.167 |
pollen | +0.167 |
Neg logit contributions | |
| -0.229 |
" | -0.223 |
. | -0.215 |
because | -0.209 |
and | -0.199 |
Token | was |
Token ID | 373 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
ts | +0.408 |
riches | +0.398 |
pollen | +0.395 |
turrets | +0.394 |
isher | +0.390 |
Neg logit contributions | |
| -0.257 |
" | -0.221 |
because | -0.214 |
She | -0.200 |
. | -0.199 |
Token | over |
Token ID | 625 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ts | +0.059 |
riches | +0.058 |
turrets | +0.057 |
pollen | +0.057 |
miles | +0.056 |
Neg logit contributions | |
| -0.041 |
" | -0.035 |
because | -0.034 |
She | -0.032 |
. | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ts | +0.457 |
miles | +0.454 |
riches | +0.451 |
seas | +0.446 |
turrets | +0.434 |
Neg logit contributions | |
| -0.113 |
She | -0.110 |
" | -0.096 |
because | -0.080 |
Her | -0.066 |
Token | The |
Token ID | 383 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
| +0.385 |
because | +0.319 |
" | +0.309 |
She | +0.288 |
. | +0.285 |
Neg logit contributions | |
ts | -0.875 |
riches | -0.869 |
turrets | -0.868 |
pollen | -0.855 |
miles | -0.851 |
Token | the |
Token ID | 262 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
ts | +0.032 |
riches | +0.032 |
isher | +0.031 |
pollen | +0.031 |
ounces | +0.031 |
Neg logit contributions | |
| -0.021 |
" | -0.018 |
because | -0.017 |
. | -0.016 |
She | -0.016 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ts | +0.183 |
isher | +0.178 |
ocol | +0.167 |
riches | +0.165 |
ief | +0.163 |
Neg logit contributions | |
| -0.226 |
" | -0.211 |
. | -0.199 |
because | -0.197 |
She | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ts | +0.397 |
riches | +0.388 |
miles | +0.387 |
turrets | +0.387 |
pollen | +0.386 |
Neg logit contributions | |
| -0.132 |
" | -0.101 |
because | -0.095 |
She | -0.093 |
: | -0.077 |
Token | peek |
Token ID | 27185 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
| +0.257 |
" | +0.226 |
because | +0.217 |
She | +0.211 |
. | +0.202 |
Neg logit contributions | |
isher | -0.309 |
ts | -0.308 |
riches | -0.304 |
seas | -0.297 |
ubb | -0.296 |
Token | behind |
Token ID | 2157 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
ts | +0.455 |
riches | +0.445 |
ounces | +0.429 |
ief | +0.428 |
isher | +0.428 |
Neg logit contributions | |
| -0.302 |
" | -0.265 |
because | -0.256 |
. | -0.249 |
She | -0.238 |
Token | it |
Token ID | 340 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ts | +0.188 |
riches | +0.183 |
turrets | +0.180 |
pollen | +0.180 |
miles | +0.179 |
Neg logit contributions | |
| -0.138 |
" | -0.120 |
because | -0.117 |
She | -0.112 |
. | -0.107 |
Token | to |
Token ID | 284 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
pollen | +0.341 |
ts | +0.341 |
miles | +0.336 |
turrets | +0.335 |
riches | +0.332 |
Neg logit contributions | |
| -0.169 |
because | -0.144 |
" | -0.141 |
She | -0.134 |
: | -0.119 |
Token | find |
Token ID | 1064 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
isher | +0.017 |
riches | +0.016 |
ts | +0.016 |
pollen | +0.016 |
ubb | +0.016 |
Neg logit contributions | |
| -0.016 |
" | -0.014 |
. | -0.013 |
because | -0.013 |
She | -0.013 |
Token | out |
Token ID | 503 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ts | +0.420 |
riches | +0.409 |
turrets | +0.403 |
isher | +0.403 |
pollen | +0.401 |
Neg logit contributions | |
| -0.240 |
" | -0.201 |
because | -0.192 |
. | -0.189 |
She | -0.178 |
Token | what |
Token ID | 644 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ts | +0.483 |
riches | +0.473 |
miles | +0.467 |
turrets | +0.466 |
pollen | +0.465 |
Neg logit contributions | |
| -0.213 |
" | -0.174 |
because | -0.168 |
She | -0.161 |
. | -0.143 |
Token | 's |
Token ID | 338 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
isher | +0.056 |
ts | +0.056 |
riches | +0.055 |
turrets | +0.055 |
pollen | +0.055 |
Neg logit contributions | |
| -0.032 |
" | -0.027 |
because | -0.024 |
. | -0.024 |
She | -0.024 |
Token | work |
Token ID | 670 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ts | +0.459 |
riches | +0.450 |
turrets | +0.446 |
pollen | +0.442 |
isher | +0.441 |
Neg logit contributions | |
| -0.366 |
" | -0.320 |
because | -0.312 |
She | -0.297 |
. | -0.291 |
Token | and |
Token ID | 290 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ts | +1.001 |
riches | +0.979 |
miles | +0.960 |
seas | +0.955 |
isher | +0.952 |
Neg logit contributions | |
| -0.273 |
" | -0.203 |
She | -0.197 |
because | -0.162 |
They | -0.137 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
| +0.045 |
" | +0.041 |
because | +0.040 |
. | +0.038 |
She | +0.038 |
Neg logit contributions | |
pollen | -0.054 |
ts | -0.054 |
isher | -0.053 |
riches | -0.053 |
ubb | -0.053 |
Token | putting |
Token ID | 5137 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
ts | +0.258 |
riches | +0.251 |
pollen | +0.248 |
seas | +0.247 |
isher | +0.247 |
Neg logit contributions | |
| -0.188 |
" | -0.167 |
because | -0.162 |
. | -0.150 |
She | -0.149 |
Token | her |
Token ID | 607 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Majesty | +0.519 |
confidence | +0.508 |
ts | +0.506 |
ounces | +0.503 |
riches | +0.503 |
Neg logit contributions | |
| -0.402 |
because | -0.355 |
. | -0.351 |
" | -0.350 |
and | -0.323 |
Token | purple |
Token ID | 14032 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ts | +0.393 |
ief | +0.383 |
miles | +0.373 |
turrets | +0.371 |
ounces | +0.367 |
Neg logit contributions | |
| -0.522 |
because | -0.481 |
. | -0.473 |
" | -0.464 |
and | -0.446 |
Token | tie |
Token ID | 9839 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ts | +0.491 |
riches | +0.465 |
miles | +0.457 |
ief | +0.455 |
turrets | +0.453 |
Neg logit contributions | |
| -0.676 |
" | -0.615 |
because | -0.608 |
She | -0.582 |
. | -0.582 |
Token | on |
Token ID | 319 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ts | +0.845 |
riches | +0.829 |
turrets | +0.819 |
pollen | +0.818 |
miles | +0.817 |
Neg logit contributions | |
| -0.252 |
" | -0.191 |
because | -0.178 |
She | -0.166 |
. | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ts | +0.388 |
riches | +0.379 |
turrets | +0.373 |
pollen | +0.372 |
miles | +0.371 |
Neg logit contributions | |
| -0.235 |
" | -0.201 |
because | -0.195 |
She | -0.187 |
. | -0.175 |
Token | Molly |
Token ID | 30236 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
because | +0.183 |
| +0.157 |
: | +0.152 |
. | +0.145 |
" | +0.128 |
Neg logit contributions | |
Majesty | -0.710 |
turrets | -0.686 |
pollen | -0.684 |
ounces | -0.676 |
riches | -0.667 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ts | +0.497 |
riches | +0.487 |
turrets | +0.478 |
pollen | +0.478 |
miles | +0.477 |
Neg logit contributions | |
| -0.307 |
" | -0.263 |
because | -0.255 |
She | -0.244 |
. | -0.231 |
Token | surprise |
Token ID | 5975 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ts | +0.540 |
ief | +0.503 |
riches | +0.503 |
turrets | +0.497 |
confidence | +0.497 |
Neg logit contributions | |
| -0.431 |
" | -0.397 |
because | -0.389 |
. | -0.362 |
She | -0.357 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
riches | +0.757 |
seas | +0.744 |
turrets | +0.744 |
pearl | +0.743 |
miles | +0.743 |
Neg logit contributions | |
| -0.283 |
She | -0.223 |
" | -0.211 |
because | -0.195 |
They | -0.182 |
Token | It |
Token ID | 632 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
because | +0.257 |
| +0.231 |
. | +0.221 |
: | +0.201 |
" | +0.193 |
Neg logit contributions | |
turrets | -0.657 |
riches | -0.656 |
ounces | -0.647 |
pollen | -0.633 |
Majesty | -0.629 |
Token | was |
Token ID | 373 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
ts | +0.354 |
riches | +0.346 |
turrets | +0.341 |
pollen | +0.340 |
miles | +0.340 |
Neg logit contributions | |
| -0.164 |
" | -0.135 |
because | -0.131 |
She | -0.124 |
. | -0.114 |
Token | a |
Token ID | 257 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ts | +0.209 |
riches | +0.205 |
turrets | +0.202 |
miles | +0.201 |
pollen | +0.201 |
Neg logit contributions | |
| -0.128 |
" | -0.108 |
because | -0.105 |
She | -0.102 |
. | -0.095 |
Token | bright |
Token ID | 6016 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ts | +0.310 |
ief | +0.286 |
riches | +0.283 |
isher | +0.282 |
pollen | +0.280 |
Neg logit contributions | |
| -0.404 |
" | -0.371 |
because | -0.360 |
She | -0.341 |
. | -0.340 |
Token | shiny |
Token ID | 22441 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
ts | +0.742 |
ief | +0.696 |
riches | +0.696 |
pollen | +0.695 |
miles | +0.695 |
Neg logit contributions | |
| -0.360 |
" | -0.308 |
because | -0.308 |
. | -0.280 |
She | -0.278 |
Token | new |
Token ID | 649 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ts | +0.680 |
riches | +0.640 |
pollen | +0.635 |
miles | +0.634 |
ief | +0.632 |
Neg logit contributions | |
| -0.604 |
" | -0.547 |
because | -0.545 |
. | -0.513 |
She | -0.509 |
Token | bike |
Token ID | 7161 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
riches | +0.401 |
ts | +0.400 |
turrets | +0.390 |
miles | +0.388 |
pollen | +0.387 |
Neg logit contributions | |
| -0.462 |
" | -0.412 |
because | -0.400 |
She | -0.397 |
. | -0.368 |
Token | ! |
Token ID | 0 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
miles | +0.731 |
ts | +0.728 |
seas | +0.719 |
riches | +0.714 |
turrets | +0.710 |
Neg logit contributions | |
| -0.280 |
" | -0.220 |
She | -0.205 |
They | -0.180 |
because | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
because | +0.207 |
| +0.202 |
" | +0.180 |
. | +0.170 |
: | +0.167 |
Neg logit contributions | |
turrets | -0.623 |
riches | -0.623 |
ounces | -0.619 |
miles | -0.615 |
seas | -0.611 |
Token | park |
Token ID | 3952 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ts | +0.359 |
ounces | +0.339 |
ief | +0.335 |
breaths | +0.329 |
ubb | +0.328 |
Neg logit contributions | |
| -0.361 |
" | -0.328 |
because | -0.309 |
She | -0.299 |
. | -0.298 |
Token | and |
Token ID | 290 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
seas | +0.605 |
miles | +0.601 |
ts | +0.590 |
turrets | +0.589 |
riches | +0.584 |
Neg logit contributions | |
| -0.179 |
" | -0.133 |
She | -0.120 |
And | -0.096 |
: | -0.095 |
Token | play |
Token ID | 711 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
| +0.110 |
" | +0.096 |
because | +0.092 |
She | +0.090 |
. | +0.082 |
Neg logit contributions | |
ts | -0.159 |
ief | -0.156 |
isher | -0.156 |
ounces | -0.155 |
riches | -0.155 |
Token | on |
Token ID | 319 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ts | +0.633 |
riches | +0.610 |
miles | +0.609 |
pollen | +0.607 |
turrets | +0.603 |
Neg logit contributions | |
| -0.316 |
" | -0.265 |
because | -0.256 |
She | -0.248 |
: | -0.222 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ts | +0.332 |
riches | +0.322 |
miles | +0.320 |
pollen | +0.318 |
turrets | +0.317 |
Neg logit contributions | |
| -0.237 |
" | -0.207 |
because | -0.201 |
She | -0.193 |
. | -0.181 |
Token | swings |
Token ID | 26728 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ubb | +0.279 |
riches | +0.277 |
ocol | +0.275 |
ts | +0.275 |
isher | +0.275 |
Neg logit contributions | |
| -0.371 |
" | -0.344 |
because | -0.327 |
. | -0.325 |
and | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
seas | +0.826 |
miles | +0.823 |
ts | +0.814 |
stones | +0.809 |
pollen | +0.794 |
Neg logit contributions | |
| -0.220 |
" | -0.174 |
She | -0.149 |
because | -0.131 |
Why | -0.116 |
Token | When |
Token ID | 1649 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
: | +0.191 |
? | +0.189 |
| +0.187 |
. | +0.179 |
because | +0.172 |
Neg logit contributions | |
Majesty | -0.734 |
turrets | -0.709 |
pollen | -0.704 |
stones | -0.683 |
weeds | -0.683 |
Token | they |
Token ID | 484 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
| +0.032 |
" | +0.025 |
because | +0.024 |
She | +0.021 |
: | +0.019 |
Neg logit contributions | |
ts | -0.092 |
miles | -0.091 |
riches | -0.090 |
turrets | -0.090 |
pollen | -0.090 |
Token | got |
Token ID | 1392 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ts | +0.157 |
miles | +0.151 |
riches | +0.150 |
turrets | +0.150 |
seas | +0.148 |
Neg logit contributions | |
| -0.148 |
" | -0.135 |
because | -0.130 |
She | -0.128 |
. | -0.120 |
Token | there |
Token ID | 612 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ts | +0.615 |
riches | +0.599 |
ounces | +0.597 |
Majesty | +0.591 |
pollen | +0.590 |
Neg logit contributions | |
| -0.218 |
" | -0.165 |
because | -0.161 |
She | -0.150 |
. | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
isher | +0.247 |
riches | +0.243 |
pollen | +0.243 |
confidence | +0.241 |
Majesty | +0.240 |
Neg logit contributions | |
| -0.172 |
" | -0.154 |
because | -0.149 |
. | -0.140 |
She | -0.133 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ts | +0.267 |
pollen | +0.253 |
ief | +0.251 |
riches | +0.248 |
isher | +0.244 |
Neg logit contributions | |
| -0.350 |
" | -0.325 |
because | -0.313 |
. | -0.310 |
She | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ts | +0.687 |
turrets | +0.680 |
miles | +0.674 |
stones | +0.670 |
pollen | +0.669 |
Neg logit contributions | |
| -0.194 |
" | -0.132 |
She | -0.120 |
because | -0.109 |
And | -0.094 |
Token | four |
Token ID | 1440 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
| +0.117 |
" | +0.081 |
because | +0.075 |
She | +0.068 |
. | +0.056 |
Neg logit contributions | |
ts | -0.498 |
riches | -0.488 |
turrets | -0.484 |
pollen | -0.483 |
miles | -0.482 |
Token | long |
Token ID | 890 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ts | +0.640 |
riches | +0.634 |
pollen | +0.630 |
isher | +0.620 |
turrets | +0.619 |
Neg logit contributions | |
| -0.424 |
" | -0.372 |
because | -0.359 |
. | -0.342 |
She | -0.332 |
Token | gears |
Token ID | 28713 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ts | +0.424 |
riches | +0.415 |
pollen | +0.410 |
turrets | +0.406 |
miles | +0.406 |
Neg logit contributions | |
| -0.312 |
" | -0.275 |
because | -0.265 |
She | -0.252 |
. | -0.251 |
Token | for |
Token ID | 329 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
ts | +0.932 |
riches | +0.891 |
turrets | +0.889 |
miles | +0.888 |
isher | +0.887 |
Neg logit contributions | |
| -0.219 |
" | -0.143 |
She | -0.130 |
because | -0.119 |
And | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
isher | +0.212 |
riches | +0.211 |
pollen | +0.211 |
ts | +0.208 |
turrets | +0.208 |
Neg logit contributions | |
| -0.159 |
" | -0.142 |
because | -0.138 |
. | -0.129 |
She | -0.126 |
Token | arms |
Token ID | 5101 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ts | +0.247 |
pollen | +0.235 |
riches | +0.230 |
ief | +0.229 |
miles | +0.226 |
Neg logit contributions | |
| -0.329 |
" | -0.304 |
because | -0.294 |
. | -0.289 |
She | -0.278 |
Token | and |
Token ID | 290 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
ts | +0.720 |
turrets | +0.707 |
riches | +0.699 |
pollen | +0.697 |
stones | +0.695 |
Neg logit contributions | |
| -0.191 |
" | -0.135 |
She | -0.111 |
because | -0.107 |
And | -0.088 |
Token | legs |
Token ID | 7405 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
| +0.223 |
" | +0.210 |
because | +0.201 |
She | +0.193 |
. | +0.191 |
Neg logit contributions | |
ts | -0.152 |
riches | -0.150 |
isher | -0.149 |
ief | -0.145 |
miles | -0.144 |
Token | play |
Token ID | 711 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
ts | +0.182 |
riches | +0.177 |
turrets | +0.174 |
pollen | +0.174 |
miles | +0.173 |
Neg logit contributions | |
| -0.171 |
" | -0.151 |
because | -0.149 |
She | -0.144 |
. | -0.138 |
Token | with |
Token ID | 351 |
Feature activation | -9.83e-02 |
Pos logit contributions | |
ts | +0.616 |
miles | +0.576 |
riches | +0.573 |
seas | +0.572 |
turrets | +0.568 |
Neg logit contributions | |
| -0.331 |
" | -0.279 |
She | -0.270 |
because | -0.266 |
: | -0.245 |
Token | water |
Token ID | 1660 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ts | +0.224 |
riches | +0.217 |
turrets | +0.214 |
miles | +0.213 |
pollen | +0.213 |
Neg logit contributions | |
| -0.167 |
" | -0.146 |
because | -0.142 |
She | -0.137 |
. | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
ts | +0.717 |
pollen | +0.706 |
seas | +0.697 |
stones | +0.692 |
riches | +0.682 |
Neg logit contributions | |
| -0.226 |
" | -0.172 |
She | -0.156 |
because | -0.136 |
: | -0.118 |
Token | One |
Token ID | 1881 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
: | +0.304 |
because | +0.269 |
; | +0.259 |
| +0.248 |
. | +0.245 |
Neg logit contributions | |
turrets | -0.578 |
stones | -0.574 |
seas | -0.555 |
miles | -0.553 |
ounces | -0.550 |
Token | sunny |
Token ID | 27737 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
| +0.151 |
" | +0.138 |
She | +0.134 |
because | +0.131 |
: | +0.124 |
Neg logit contributions | |
ts | -0.109 |
pollen | -0.107 |
riches | -0.106 |
seas | -0.104 |
miles | -0.104 |
Token | day |
Token ID | 1110 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ts | +0.527 |
riches | +0.511 |
turrets | +0.501 |
pollen | +0.498 |
miles | +0.497 |
Neg logit contributions | |
| -0.551 |
" | -0.489 |
because | -0.480 |
She | -0.465 |
. | -0.448 |
Token | , |
Token ID | 11 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
seas | +0.310 |
miles | +0.309 |
ts | +0.301 |
stones | +0.298 |
coins | +0.291 |
Neg logit contributions | |
| -0.167 |
She | -0.151 |
Why | -0.140 |
Maybe | -0.138 |
" | -0.137 |
Token | he |
Token ID | 339 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
| +0.199 |
: | +0.185 |
She | +0.170 |
" | +0.167 |
And | +0.161 |
Neg logit contributions | |
ts | -0.364 |
miles | -0.364 |
seas | -0.361 |
stones | -0.355 |
turrets | -0.345 |
Token | found |
Token ID | 1043 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ts | +0.166 |
riches | +0.162 |
turrets | +0.159 |
pollen | +0.158 |
miles | +0.158 |
Neg logit contributions | |
| -0.133 |
" | -0.117 |
because | -0.114 |
She | -0.110 |
. | -0.105 |
Token | a |
Token ID | 257 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ts | +0.610 |
riches | +0.596 |
Majesty | +0.589 |
ief | +0.589 |
turrets | +0.588 |
Neg logit contributions | |
| -0.292 |
" | -0.236 |
because | -0.223 |
She | -0.211 |
. | -0.204 |