Token | the |
Token ID | 262 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
ling | +0.019 |
led | +0.016 |
ie | +0.015 |
shining | +0.015 |
around | +0.015 |
Neg logit contributions | |
roller | -0.012 |
salon | -0.010 |
ara | -0.010 |
post | -0.010 |
atters | -0.009 |
Token | handle |
Token ID | 5412 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
roller | +0.112 |
salon | +0.106 |
ara | +0.099 |
pitcher | +0.096 |
heaven | +0.096 |
Neg logit contributions | |
ling | -0.119 |
around | -0.106 |
shining | -0.103 |
led | -0.102 |
up | -0.096 |
Token | of |
Token ID | 286 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
roller | +0.117 |
salon | +0.111 |
ara | +0.107 |
heaven | +0.107 |
clinic | +0.105 |
Neg logit contributions | |
ling | -0.078 |
around | -0.070 |
shining | -0.066 |
led | -0.062 |
up | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
roller | +0.124 |
salon | +0.119 |
ara | +0.113 |
heaven | +0.111 |
pitcher | +0.111 |
Neg logit contributions | |
ling | -0.067 |
around | -0.055 |
shining | -0.053 |
led | -0.051 |
up | -0.047 |
Token | st |
Token ID | 336 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
roller | +0.005 |
salon | +0.005 |
ara | +0.005 |
heaven | +0.005 |
pitcher | +0.005 |
Neg logit contributions | |
ling | -0.007 |
around | -0.006 |
shining | -0.006 |
led | -0.006 |
up | -0.005 |
Token | roller |
Token ID | 10646 |
Feature activation | +9.08e+00 |
Pos logit contributions | |
heaven | +0.036 |
salon | +0.033 |
ara | +0.032 |
S | +0.030 |
Anna | +0.030 |
Neg logit contributions | |
ling | -0.076 |
around | -0.069 |
up | -0.065 |
led | -0.063 |
shining | -0.063 |
Token | so |
Token ID | 523 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
roller | +0.547 |
salon | +0.520 |
ara | +0.503 |
heaven | +0.490 |
atters | +0.487 |
Neg logit contributions | |
ling | -0.355 |
around | -0.309 |
shining | -0.295 |
led | -0.276 |
up | -0.272 |
Token | we |
Token ID | 356 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ling | +0.021 |
around | +0.018 |
shining | +0.017 |
led | +0.016 |
up | +0.015 |
Neg logit contributions | |
roller | -0.034 |
salon | -0.033 |
ara | -0.031 |
heaven | -0.030 |
pitcher | -0.030 |
Token | won |
Token ID | 1839 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
roller | +0.090 |
salon | +0.086 |
ara | +0.081 |
atters | +0.079 |
heaven | +0.079 |
Neg logit contributions | |
ling | -0.083 |
shining | -0.071 |
around | -0.070 |
led | -0.069 |
up | -0.065 |
Token | 't |
Token ID | 470 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
roller | +0.128 |
salon | +0.121 |
ara | +0.115 |
heaven | +0.111 |
atters | +0.111 |
Neg logit contributions | |
ling | -0.113 |
around | -0.099 |
shining | -0.097 |
led | -0.093 |
up | -0.090 |
Token | get |
Token ID | 651 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
roller | +0.049 |
salon | +0.046 |
ara | +0.044 |
post | +0.042 |
heaven | +0.042 |
Neg logit contributions | |
ling | -0.046 |
around | -0.041 |
shining | -0.040 |
up | -0.037 |
him | -0.037 |
Token | down |
Token ID | 866 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ling | +0.087 |
shining | +0.066 |
bee | +0.066 |
mattered | +0.062 |
itive | +0.061 |
Neg logit contributions | |
roller | -0.184 |
salon | -0.181 |
ara | -0.175 |
ress | -0.170 |
post | -0.166 |
Token | next |
Token ID | 1306 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ling | +0.127 |
around | +0.105 |
shining | +0.105 |
led | +0.100 |
ie | +0.096 |
Neg logit contributions | |
roller | -0.193 |
salon | -0.184 |
ara | -0.176 |
heaven | -0.171 |
post | -0.171 |
Token | to |
Token ID | 284 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
ling | +0.009 |
around | +0.009 |
shining | +0.008 |
up | +0.008 |
in | +0.007 |
Neg logit contributions | |
roller | -0.015 |
atters | -0.015 |
salon | -0.014 |
pitcher | -0.014 |
ara | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
heaven | +0.029 |
ara | +0.026 |
salon | +0.026 |
clinic | +0.026 |
vet | +0.026 |
Neg logit contributions | |
ling | -0.021 |
led | -0.019 |
shining | -0.016 |
itive | -0.016 |
b | -0.015 |
Token | st |
Token ID | 336 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
roller | +0.000 |
salon | +0.000 |
ara | +0.000 |
heaven | +0.000 |
clinic | +0.000 |
Neg logit contributions | |
ling | -0.000 |
around | -0.000 |
shining | -0.000 |
led | -0.000 |
up | -0.000 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.92e+00 |
Pos logit contributions | |
Ble | +0.019 |
Y | +0.018 |
pitcher | +0.016 |
Uh | +0.016 |
pic | +0.016 |
Neg logit contributions | |
ling | -0.049 |
up | -0.046 |
around | -0.045 |
curiously | -0.044 |
ing | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
roller | +0.559 |
salon | +0.524 |
ara | +0.514 |
atters | +0.506 |
pitcher | +0.501 |
Neg logit contributions | |
ling | -0.331 |
around | -0.294 |
shining | -0.269 |
up | -0.258 |
in | -0.245 |
Token | They |
Token ID | 1119 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
salon | +0.007 |
roller | +0.006 |
lor | +0.006 |
ird | +0.006 |
ress | +0.006 |
Neg logit contributions | |
around | -0.007 |
up | -0.006 |
him | -0.006 |
ling | -0.006 |
curiously | -0.006 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
roller | +0.166 |
salon | +0.161 |
ara | +0.151 |
heaven | +0.149 |
clinic | +0.147 |
Neg logit contributions | |
ling | -0.131 |
shining | -0.110 |
around | -0.110 |
led | -0.104 |
up | -0.100 |
Token | Leo |
Token ID | 19632 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ling | +0.027 |
shining | +0.022 |
ie | +0.022 |
itive | +0.022 |
led | +0.021 |
Neg logit contributions | |
salon | -0.025 |
heaven | -0.025 |
vet | -0.024 |
clinic | -0.023 |
ara | -0.023 |
Token | 's |
Token ID | 338 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ling | +0.132 |
led | +0.120 |
around | +0.112 |
itive | +0.110 |
shining | +0.108 |
Neg logit contributions | |
salon | -0.160 |
roller | -0.158 |
heaven | -0.155 |
clinic | -0.155 |
ara | -0.149 |
Token | until |
Token ID | 1566 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
roller | +0.079 |
salon | +0.077 |
post | +0.072 |
heaven | +0.071 |
clinic | +0.071 |
Neg logit contributions | |
ling | -0.054 |
shining | -0.045 |
around | -0.044 |
led | -0.044 |
ie | -0.042 |
Token | she |
Token ID | 673 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ling | +0.003 |
around | +0.002 |
shining | +0.002 |
led | +0.002 |
ie | +0.002 |
Neg logit contributions | |
roller | -0.007 |
salon | -0.007 |
ara | -0.006 |
heaven | -0.006 |
clinic | -0.006 |
Token | got |
Token ID | 1392 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ling | +0.006 |
around | +0.005 |
shining | +0.004 |
led | +0.004 |
up | +0.004 |
Neg logit contributions | |
roller | -0.009 |
salon | -0.009 |
atters | -0.008 |
ara | -0.008 |
heaven | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
roller | +0.030 |
salon | +0.029 |
heaven | +0.028 |
pitcher | +0.028 |
clinic | +0.026 |
Neg logit contributions | |
ling | -0.023 |
bee | -0.019 |
itive | -0.018 |
led | -0.018 |
shining | -0.017 |
Token | st |
Token ID | 336 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
roller | +0.010 |
salon | +0.010 |
pitcher | +0.009 |
clinic | +0.009 |
heaven | +0.009 |
Neg logit contributions | |
ling | -0.010 |
led | -0.009 |
around | -0.008 |
shining | -0.008 |
ie | -0.008 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
heaven | +0.018 |
salon | +0.017 |
ara | +0.016 |
bidder | +0.015 |
Anna | +0.014 |
Neg logit contributions | |
ling | -0.043 |
around | -0.039 |
up | -0.039 |
led | -0.037 |
shining | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
roller | +0.598 |
salon | +0.573 |
ara | +0.550 |
heaven | +0.538 |
atters | +0.536 |
Neg logit contributions | |
ling | -0.282 |
around | -0.233 |
shining | -0.225 |
led | -0.208 |
up | -0.199 |
Token | was |
Token ID | 373 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
ling | +0.028 |
around | +0.024 |
shining | +0.023 |
led | +0.022 |
up | +0.021 |
Neg logit contributions | |
roller | -0.042 |
salon | -0.040 |
ara | -0.038 |
atters | -0.037 |
heaven | -0.037 |
Token | ready |
Token ID | 3492 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
roller | +0.005 |
salon | +0.004 |
ara | +0.004 |
heaven | +0.004 |
atters | +0.004 |
Neg logit contributions | |
ling | -0.003 |
around | -0.002 |
shining | -0.002 |
led | -0.002 |
up | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
roller | +0.019 |
salon | +0.019 |
ara | +0.018 |
heaven | +0.017 |
atters | +0.017 |
Neg logit contributions | |
ling | -0.011 |
around | -0.009 |
shining | -0.009 |
led | -0.008 |
up | -0.008 |
Token | start |
Token ID | 923 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
roller | +0.014 |
salon | +0.013 |
ara | +0.013 |
post | +0.013 |
atters | +0.012 |
Neg logit contributions | |
ling | -0.010 |
around | -0.009 |
shining | -0.009 |
up | -0.009 |
him | -0.008 |
Token | happily |
Token ID | 18177 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ling | +0.139 |
around | +0.118 |
shining | +0.114 |
led | +0.109 |
up | +0.104 |
Neg logit contributions | |
roller | -0.222 |
salon | -0.212 |
ara | -0.201 |
heaven | -0.197 |
atters | -0.197 |
Token | hopped |
Token ID | 45230 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
roller | +0.083 |
salon | +0.078 |
heaven | +0.075 |
ara | +0.074 |
clinic | +0.073 |
Neg logit contributions | |
ling | -0.057 |
around | -0.051 |
shining | -0.047 |
led | -0.046 |
up | -0.044 |
Token | off |
Token ID | 572 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ling | +0.062 |
around | +0.052 |
shining | +0.048 |
led | +0.044 |
up | +0.043 |
Neg logit contributions | |
roller | -0.151 |
salon | -0.145 |
ara | -0.139 |
heaven | -0.137 |
atters | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
roller | +0.198 |
salon | +0.190 |
ara | +0.182 |
atters | +0.178 |
heaven | +0.178 |
Neg logit contributions | |
ling | -0.085 |
around | -0.070 |
shining | -0.067 |
led | -0.061 |
up | -0.059 |
Token | st |
Token ID | 336 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
ling | +0.031 |
around | +0.028 |
shining | +0.028 |
up | +0.026 |
led | +0.026 |
Neg logit contributions | |
roller | -0.021 |
salon | -0.019 |
heaven | -0.018 |
ara | -0.018 |
atters | -0.018 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.86e+00 |
Pos logit contributions | |
heaven | +0.018 |
Ble | +0.016 |
prise | +0.016 |
Uh | +0.015 |
Gu | +0.015 |
Neg logit contributions | |
ling | -0.040 |
around | -0.039 |
up | -0.038 |
bles | -0.035 |
ing | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
roller | +0.547 |
ara | +0.520 |
salon | +0.519 |
atters | +0.500 |
heaven | +0.499 |
Neg logit contributions | |
ling | -0.329 |
around | -0.299 |
shining | -0.271 |
up | -0.260 |
in | -0.245 |
Token | ran |
Token ID | 4966 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
ling | +0.013 |
around | +0.011 |
shining | +0.011 |
led | +0.010 |
up | +0.010 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.018 |
ara | -0.017 |
heaven | -0.017 |
atters | -0.017 |
Token | towards |
Token ID | 3371 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
roller | +0.062 |
salon | +0.061 |
ara | +0.058 |
clinic | +0.057 |
heaven | +0.057 |
Neg logit contributions | |
ling | -0.024 |
around | -0.023 |
up | -0.019 |
shining | -0.018 |
in | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ling | +0.028 |
shining | +0.022 |
led | +0.021 |
around | +0.021 |
ie | +0.018 |
Neg logit contributions | |
roller | -0.057 |
salon | -0.055 |
heaven | -0.053 |
ara | -0.052 |
clinic | -0.051 |
Token | playground |
Token ID | 24817 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ling | +0.022 |
around | +0.021 |
shining | +0.020 |
up | +0.019 |
in | +0.018 |
Neg logit contributions | |
roller | -0.018 |
heaven | -0.016 |
lor | -0.016 |
atters | -0.016 |
ara | -0.016 |
Token | pushing |
Token ID | 7796 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
roller | +0.001 |
salon | +0.001 |
ara | +0.001 |
atters | +0.001 |
heaven | +0.001 |
Neg logit contributions | |
ling | -0.001 |
around | -0.001 |
shining | -0.001 |
led | -0.000 |
up | -0.000 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
ling | +0.096 |
shining | +0.084 |
itive | +0.081 |
led | +0.079 |
atop | +0.075 |
Neg logit contributions | |
roller | -0.125 |
ara | -0.122 |
S | -0.121 |
heaven | -0.118 |
jail | -0.116 |
Token | in |
Token ID | 287 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ling | +0.244 |
led | +0.230 |
itive | +0.214 |
ie | +0.207 |
shining | +0.205 |
Neg logit contributions | |
roller | -0.391 |
salon | -0.375 |
stand | -0.330 |
clinic | -0.328 |
pitcher | -0.328 |
Token | the |
Token ID | 262 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ling | +0.044 |
around | +0.038 |
shining | +0.035 |
him | +0.031 |
up | +0.031 |
Neg logit contributions | |
roller | -0.145 |
salon | -0.139 |
ara | -0.135 |
atters | -0.133 |
pitcher | -0.130 |
Token | st |
Token ID | 336 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
ling | +0.034 |
around | +0.033 |
up | +0.032 |
shining | +0.032 |
in | +0.029 |
Neg logit contributions | |
roller | -0.025 |
ress | -0.024 |
lor | -0.024 |
post | -0.023 |
salon | -0.023 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
heaven | +0.016 |
jar | +0.014 |
Ble | +0.014 |
anniversary | +0.013 |
Y | +0.013 |
Neg logit contributions | |
ling | -0.043 |
around | -0.042 |
all | -0.040 |
up | -0.040 |
uses | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
roller | +0.561 |
ara | +0.534 |
salon | +0.532 |
pitcher | +0.515 |
atters | +0.513 |
Neg logit contributions | |
ling | -0.308 |
around | -0.280 |
shining | -0.240 |
up | -0.240 |
ie | -0.228 |
Token | and |
Token ID | 290 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
ling | +0.012 |
led | +0.010 |
ie | +0.010 |
around | +0.009 |
shining | +0.009 |
Neg logit contributions | |
roller | -0.016 |
salon | -0.016 |
ara | -0.015 |
post | -0.015 |
pitcher | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ling | +0.021 |
led | +0.017 |
itive | +0.016 |
around | +0.016 |
shining | +0.016 |
Neg logit contributions | |
roller | -0.026 |
ara | -0.025 |
pitcher | -0.025 |
salon | -0.025 |
S | -0.024 |
Token | were |
Token ID | 547 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
salon | +0.024 |
roller | +0.023 |
ird | +0.021 |
ara | +0.020 |
post | +0.020 |
Neg logit contributions | |
ling | -0.023 |
led | -0.019 |
shining | -0.019 |
spear | -0.018 |
itive | -0.018 |
Token | having |
Token ID | 1719 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
ling | +0.036 |
led | +0.028 |
ie | +0.027 |
shining | +0.026 |
around | +0.026 |
Neg logit contributions | |
roller | -0.071 |
salon | -0.068 |
heaven | -0.064 |
clinic | -0.064 |
atters | -0.063 |
Token | her |
Token ID | 607 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ling | +0.026 |
led | +0.021 |
shining | +0.019 |
ie | +0.018 |
bee | +0.018 |
Neg logit contributions | |
salon | -0.037 |
roller | -0.035 |
vet | -0.034 |
heaven | -0.034 |
jail | -0.034 |
Token | standing |
Token ID | 5055 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
roller | +0.016 |
salon | +0.016 |
clinic | +0.014 |
pitcher | +0.014 |
ara | +0.014 |
Neg logit contributions | |
ling | -0.014 |
led | -0.012 |
shining | -0.011 |
around | -0.011 |
ie | -0.011 |
Token | near |
Token ID | 1474 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ling | +0.152 |
shining | +0.120 |
around | +0.118 |
led | +0.114 |
ie | +0.109 |
Neg logit contributions | |
roller | -0.350 |
salon | -0.343 |
ara | -0.327 |
pitcher | -0.318 |
post | -0.313 |
Token | the |
Token ID | 262 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ling | +0.047 |
around | +0.038 |
shining | +0.037 |
led | +0.035 |
up | +0.032 |
Neg logit contributions | |
roller | -0.103 |
salon | -0.099 |
ara | -0.095 |
heaven | -0.093 |
clinic | -0.092 |
Token | st |
Token ID | 336 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
ling | +0.019 |
around | +0.018 |
shining | +0.018 |
up | +0.017 |
in | +0.017 |
Neg logit contributions | |
roller | -0.016 |
lor | -0.015 |
ress | -0.015 |
heaven | -0.015 |
ara | -0.014 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
heaven | +0.018 |
prise | +0.016 |
anniversary | +0.016 |
des | +0.014 |
Ble | +0.014 |
Neg logit contributions | |
ling | -0.040 |
around | -0.040 |
up | -0.039 |
all | -0.037 |
through | -0.036 |
Token | waving |
Token ID | 25849 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
roller | +0.532 |
salon | +0.500 |
ara | +0.500 |
heaven | +0.489 |
atters | +0.488 |
Neg logit contributions | |
ling | -0.334 |
around | -0.300 |
shining | -0.278 |
up | -0.264 |
ie | -0.251 |
Token | at |
Token ID | 379 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ling | +0.111 |
shining | +0.091 |
around | +0.089 |
led | +0.085 |
ie | +0.082 |
Neg logit contributions | |
roller | -0.195 |
salon | -0.185 |
ara | -0.178 |
post | -0.173 |
pitcher | -0.173 |
Token | him |
Token ID | 683 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
ling | +0.073 |
led | +0.061 |
shining | +0.057 |
around | +0.052 |
uses | +0.052 |
Neg logit contributions | |
heaven | -0.088 |
roller | -0.086 |
salon | -0.085 |
ara | -0.083 |
vet | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ling | +0.203 |
led | +0.177 |
shining | +0.174 |
around | +0.166 |
ie | +0.161 |
Neg logit contributions | |
roller | -0.239 |
salon | -0.226 |
heaven | -0.209 |
clinic | -0.207 |
ara | -0.207 |
Token | He |
Token ID | 679 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
ling | +0.007 |
around | +0.007 |
shining | +0.006 |
led | +0.006 |
ie | +0.006 |
Neg logit contributions | |
roller | -0.007 |
salon | -0.006 |
ara | -0.006 |
heaven | -0.006 |
clinic | -0.005 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ling | +0.195 |
around | +0.166 |
shining | +0.162 |
led | +0.156 |
up | +0.147 |
Neg logit contributions | |
roller | -0.275 |
salon | -0.264 |
ara | -0.250 |
clinic | -0.242 |
heaven | -0.241 |
Token | out |
Token ID | 503 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
roller | +0.194 |
salon | +0.184 |
ara | +0.175 |
post | +0.174 |
atters | +0.173 |
Neg logit contributions | |
ling | -0.076 |
around | -0.055 |
shining | -0.055 |
led | -0.054 |
ie | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ling | +0.018 |
around | +0.016 |
shining | +0.015 |
led | +0.014 |
up | +0.014 |
Neg logit contributions | |
roller | -0.026 |
salon | -0.025 |
ara | -0.024 |
clinic | -0.023 |
pitcher | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
roller | +0.120 |
salon | +0.115 |
atters | +0.112 |
lor | +0.112 |
ara | +0.111 |
Neg logit contributions | |
shining | -0.034 |
around | -0.032 |
him | -0.031 |
ling | -0.031 |
all | -0.029 |
Token | st |
Token ID | 336 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
roller | +0.010 |
ara | +0.010 |
salon | +0.010 |
atters | +0.010 |
post | +0.010 |
Neg logit contributions | |
ling | -0.012 |
around | -0.012 |
shining | -0.011 |
up | -0.011 |
in | -0.011 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.74e+00 |
Pos logit contributions | |
salon | +0.015 |
heaven | +0.014 |
Anna | +0.013 |
inconvenience | +0.012 |
anniversary | +0.012 |
Neg logit contributions | |
ling | -0.041 |
around | -0.040 |
up | -0.038 |
ully | -0.038 |
ie | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ara | +0.610 |
Ble | +0.604 |
bidder | +0.595 |
clinic | +0.594 |
salon | +0.593 |
Neg logit contributions | |
around | -0.243 |
ling | -0.227 |
up | -0.203 |
in | -0.193 |
through | -0.169 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ling | +0.007 |
around | +0.007 |
shining | +0.006 |
up | +0.006 |
him | +0.006 |
Neg logit contributions | |
roller | -0.009 |
salon | -0.009 |
heaven | -0.008 |
clinic | -0.008 |
atters | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
roller | +0.007 |
salon | +0.006 |
ara | +0.006 |
atters | +0.006 |
heaven | +0.006 |
Neg logit contributions | |
ling | -0.008 |
shining | -0.007 |
around | -0.007 |
led | -0.007 |
up | -0.007 |
Token | When |
Token ID | 2215 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
roller | +0.007 |
salon | +0.006 |
clinic | +0.006 |
pitcher | +0.006 |
heaven | +0.006 |
Neg logit contributions | |
ling | -0.007 |
around | -0.007 |
up | -0.006 |
in | -0.006 |
shining | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
roller | +0.245 |
lor | +0.230 |
atters | +0.226 |
salon | +0.226 |
clinic | +0.225 |
Neg logit contributions | |
ling | -0.118 |
around | -0.118 |
shining | -0.115 |
up | -0.108 |
in | -0.107 |
Token | She |
Token ID | 1375 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
roller | +0.017 |
salon | +0.016 |
atters | +0.015 |
lor | +0.014 |
pitcher | +0.014 |
Neg logit contributions | |
around | -0.018 |
ling | -0.017 |
him | -0.017 |
shining | -0.017 |
up | -0.016 |
Token | puts |
Token ID | 7584 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
roller | +0.125 |
salon | +0.115 |
ara | +0.107 |
post | +0.106 |
pitcher | +0.105 |
Neg logit contributions | |
ling | -0.131 |
around | -0.118 |
shining | -0.114 |
led | -0.111 |
up | -0.109 |
Token | on |
Token ID | 319 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
roller | +0.036 |
salon | +0.036 |
heaven | +0.035 |
post | +0.034 |
ara | +0.034 |
Neg logit contributions | |
ling | -0.026 |
shining | -0.020 |
itive | -0.020 |
led | -0.019 |
around | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
ling | +0.073 |
around | +0.062 |
shining | +0.058 |
up | +0.054 |
led | +0.052 |
Neg logit contributions | |
roller | -0.177 |
salon | -0.169 |
ara | -0.162 |
atters | -0.160 |
clinic | -0.159 |
Token | p |
Token ID | 279 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
roller | +0.035 |
salon | +0.033 |
heaven | +0.030 |
clinic | +0.030 |
ara | +0.029 |
Neg logit contributions | |
ling | -0.054 |
led | -0.046 |
around | -0.046 |
shining | -0.045 |
ie | -0.045 |
Token | aj |
Token ID | 1228 |
Feature activation | +8.72e+00 |
Pos logit contributions | |
heaven | +0.169 |
salon | +0.166 |
vet | +0.162 |
bidder | +0.162 |
roller | +0.162 |
Neg logit contributions | |
ling | -0.263 |
around | -0.236 |
ie | -0.230 |
led | -0.227 |
up | -0.226 |
Token | amas |
Token ID | 17485 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
salon | +0.357 |
roller | +0.344 |
heaven | +0.326 |
atters | +0.319 |
ara | +0.318 |
Neg logit contributions | |
ling | -0.494 |
shining | -0.448 |
around | -0.442 |
led | -0.422 |
up | -0.420 |
Token | . |
Token ID | 13 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
roller | +0.135 |
salon | +0.130 |
ara | +0.126 |
pitcher | +0.125 |
atters | +0.124 |
Neg logit contributions | |
ling | -0.070 |
around | -0.066 |
shining | -0.059 |
up | -0.057 |
in | -0.056 |
Token | She |
Token ID | 1375 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
around | +0.003 |
ling | +0.003 |
shining | +0.003 |
him | +0.003 |
up | +0.003 |
Neg logit contributions | |
roller | -0.002 |
salon | -0.002 |
atters | -0.002 |
pitcher | -0.002 |
ara | -0.002 |
Token | hugs |
Token ID | 40657 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
roller | +0.127 |
salon | +0.114 |
post | +0.108 |
ress | +0.106 |
pitcher | +0.106 |
Neg logit contributions | |
ling | -0.138 |
around | -0.125 |
shining | -0.120 |
led | -0.118 |
up | -0.117 |
Token | her |
Token ID | 607 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
roller | +0.163 |
salon | +0.159 |
ara | +0.153 |
heaven | +0.151 |
post | +0.149 |
Neg logit contributions | |
ling | -0.115 |
led | -0.093 |
shining | -0.091 |
around | -0.090 |
atop | -0.083 |
Token | pushing |
Token ID | 7796 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
roller | +0.006 |
salon | +0.006 |
ara | +0.006 |
atters | +0.006 |
heaven | +0.006 |
Neg logit contributions | |
ling | -0.003 |
around | -0.003 |
shining | -0.002 |
led | -0.002 |
up | -0.002 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ling | +0.083 |
shining | +0.072 |
itive | +0.069 |
led | +0.064 |
bee | +0.061 |
Neg logit contributions | |
roller | -0.137 |
heaven | -0.135 |
ara | -0.134 |
jail | -0.130 |
post | -0.129 |
Token | in |
Token ID | 287 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ling | +0.026 |
led | +0.026 |
itive | +0.024 |
ie | +0.022 |
agles | +0.021 |
Neg logit contributions | |
roller | -0.052 |
salon | -0.051 |
stand | -0.045 |
rack | -0.044 |
ress | -0.044 |
Token | his |
Token ID | 465 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ling | +0.050 |
around | +0.043 |
shining | +0.040 |
up | +0.035 |
him | +0.035 |
Neg logit contributions | |
roller | -0.127 |
salon | -0.122 |
ara | -0.117 |
atters | -0.116 |
clinic | -0.114 |
Token | st |
Token ID | 336 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
ling | +0.103 |
around | +0.094 |
shining | +0.091 |
led | +0.088 |
up | +0.087 |
Neg logit contributions | |
roller | -0.074 |
salon | -0.069 |
ara | -0.065 |
atters | -0.062 |
heaven | -0.062 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.67e+00 |
Pos logit contributions | |
heaven | +0.012 |
Ble | +0.012 |
jar | +0.011 |
S | +0.010 |
Anna | +0.010 |
Neg logit contributions | |
ling | -0.041 |
around | -0.040 |
up | -0.039 |
all | -0.038 |
upon | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
roller | +0.533 |
salon | +0.506 |
ara | +0.499 |
atters | +0.485 |
pitcher | +0.481 |
Neg logit contributions | |
ling | -0.328 |
around | -0.291 |
shining | -0.266 |
up | -0.254 |
led | -0.246 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ling | +0.013 |
around | +0.013 |
shining | +0.012 |
him | +0.012 |
up | +0.012 |
Neg logit contributions | |
roller | -0.014 |
salon | -0.014 |
atters | -0.013 |
heaven | -0.013 |
clinic | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
roller | +0.103 |
salon | +0.098 |
ara | +0.095 |
post | +0.088 |
heaven | +0.088 |
Neg logit contributions | |
ling | -0.088 |
around | -0.073 |
shining | -0.071 |
led | -0.071 |
ie | -0.066 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
ling | +0.009 |
around | +0.008 |
led | +0.007 |
shining | +0.007 |
ie | +0.007 |
Neg logit contributions | |
roller | -0.012 |
salon | -0.012 |
ara | -0.011 |
heaven | -0.011 |
pitcher | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
ling | +0.039 |
minerals | +0.034 |
nam | +0.034 |
led | +0.034 |
shining | +0.034 |
Neg logit contributions | |
roller | -0.042 |
ara | -0.037 |
salon | -0.037 |
pitcher | -0.033 |
stand | -0.032 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ling | +0.011 |
around | +0.010 |
up | +0.009 |
him | +0.009 |
led | +0.008 |
Neg logit contributions | |
roller | -0.027 |
salon | -0.027 |
ara | -0.025 |
clinic | -0.025 |
pitcher | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
roller | +0.094 |
salon | +0.089 |
ara | +0.084 |
heaven | +0.084 |
atters | +0.083 |
Neg logit contributions | |
ling | -0.072 |
shining | -0.063 |
around | -0.062 |
led | -0.060 |
ie | -0.056 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
up | +0.002 |
him | +0.002 |
Neg logit contributions | |
roller | -0.002 |
salon | -0.002 |
ara | -0.002 |
post | -0.002 |
lor | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
roller | +0.254 |
salon | +0.240 |
heaven | +0.229 |
atters | +0.225 |
ara | +0.224 |
Neg logit contributions | |
ling | -0.176 |
shining | -0.150 |
led | -0.144 |
around | -0.143 |
ie | -0.132 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
roller | +0.046 |
salon | +0.044 |
ara | +0.042 |
atters | +0.041 |
pitcher | +0.041 |
Neg logit contributions | |
ling | -0.017 |
around | -0.014 |
shining | -0.013 |
him | -0.013 |
up | -0.012 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
ling | +0.005 |
around | +0.005 |
shining | +0.005 |
up | +0.004 |
in | +0.004 |
Neg logit contributions | |
roller | -0.005 |
ress | -0.005 |
atters | -0.005 |
salon | -0.005 |
lor | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
roller | +0.551 |
salon | +0.523 |
ara | +0.515 |
pitcher | +0.497 |
atters | +0.488 |
Neg logit contributions | |
ling | -0.312 |
around | -0.279 |
shining | -0.255 |
up | -0.246 |
led | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
salon | +0.004 |
roller | +0.004 |
lor | +0.003 |
ress | +0.003 |
ction | +0.003 |
Neg logit contributions | |
around | -0.002 |
him | -0.002 |
ling | -0.002 |
his | -0.002 |
in | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
roller | +0.021 |
salon | +0.020 |
ara | +0.018 |
pitcher | +0.018 |
heaven | +0.018 |
Neg logit contributions | |
ling | -0.019 |
around | -0.017 |
shining | -0.016 |
him | -0.015 |
up | -0.015 |
Token | Ben |
Token ID | 11696 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
roller | +0.022 |
salon | +0.021 |
ress | +0.019 |
bidder | +0.019 |
lor | +0.018 |
Neg logit contributions | |
ling | -0.019 |
around | -0.017 |
him | -0.016 |
his | -0.015 |
in | -0.015 |
Token | has |
Token ID | 468 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
roller | +0.165 |
salon | +0.159 |
ress | +0.149 |
ction | +0.149 |
post | +0.149 |
Neg logit contributions | |
ling | -0.078 |
around | -0.070 |
up | -0.061 |
led | -0.058 |
in | -0.058 |
Token | have |
Token ID | 423 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
roller | +0.174 |
salon | +0.160 |
ara | +0.155 |
ress | +0.154 |
lor | +0.148 |
Neg logit contributions | |
ling | -0.138 |
around | -0.127 |
shining | -0.117 |
him | -0.115 |
up | -0.112 |
Token | to |
Token ID | 284 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
roller | +0.126 |
salon | +0.121 |
ara | +0.117 |
atters | +0.113 |
ress | +0.112 |
Neg logit contributions | |
ling | -0.061 |
around | -0.057 |
shining | -0.054 |
him | -0.053 |
in | -0.050 |
Token | go |
Token ID | 467 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
roller | +0.038 |
lor | +0.036 |
salon | +0.035 |
ase | +0.035 |
ress | +0.035 |
Neg logit contributions | |
him | -0.020 |
ling | -0.019 |
all | -0.019 |
up | -0.019 |
in | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
roller | +0.173 |
ara | +0.168 |
lor | +0.165 |
Ble | +0.164 |
salon | +0.163 |
Neg logit contributions | |
around | -0.075 |
ling | -0.070 |
in | -0.065 |
up | -0.064 |
him | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
roller | +0.040 |
lor | +0.038 |
salon | +0.037 |
ara | +0.037 |
pitcher | +0.036 |
Neg logit contributions | |
him | -0.018 |
up | -0.016 |
around | -0.016 |
ling | -0.016 |
his | -0.015 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
roller | +0.008 |
atters | +0.008 |
lor | +0.008 |
ress | +0.007 |
ird | +0.007 |
Neg logit contributions | |
up | -0.011 |
shining | -0.011 |
around | -0.010 |
in | -0.010 |
ling | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
roller | +0.571 |
ara | +0.533 |
salon | +0.530 |
pitcher | +0.522 |
atters | +0.510 |
Neg logit contributions | |
ling | -0.292 |
around | -0.269 |
up | -0.235 |
shining | -0.231 |
in | -0.230 |
Token | Mom |
Token ID | 11254 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
salon | +0.006 |
roller | +0.006 |
lor | +0.006 |
pitcher | +0.006 |
ress | +0.006 |
Neg logit contributions | |
him | -0.003 |
around | -0.003 |
his | -0.003 |
in | -0.003 |
up | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
roller | +0.162 |
pitcher | +0.147 |
post | +0.147 |
salon | +0.146 |
lor | +0.144 |
Neg logit contributions | |
ling | -0.066 |
around | -0.059 |
up | -0.050 |
in | -0.049 |
ie | -0.044 |
Token | Dad |
Token ID | 17415 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
roller | +0.001 |
salon | +0.001 |
atters | +0.001 |
ara | +0.001 |
clinic | +0.001 |
Neg logit contributions | |
ling | -0.000 |
around | -0.000 |
shining | -0.000 |
led | -0.000 |
up | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ling | +0.047 |
around | +0.043 |
shining | +0.041 |
led | +0.039 |
up | +0.039 |
Neg logit contributions | |
roller | -0.048 |
salon | -0.045 |
ara | -0.043 |
pitcher | -0.042 |
post | -0.041 |
Token | have |
Token ID | 423 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
roller | +0.099 |
salon | +0.094 |
ara | +0.089 |
pitcher | +0.087 |
heaven | +0.087 |
Neg logit contributions | |
ling | -0.073 |
around | -0.064 |
shining | -0.061 |
led | -0.058 |
up | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
roller | +0.090 |
salon | +0.084 |
ara | +0.081 |
atters | +0.080 |
post | +0.079 |
Neg logit contributions | |
ling | -0.049 |
around | -0.045 |
shining | -0.042 |
led | -0.039 |
him | -0.039 |
Token | go |
Token ID | 467 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
roller | +0.021 |
lor | +0.019 |
ara | +0.019 |
salon | +0.019 |
ress | +0.018 |
Neg logit contributions | |
ling | -0.011 |
him | -0.011 |
around | -0.011 |
all | -0.011 |
in | -0.011 |
Token | back |
Token ID | 736 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
roller | +0.134 |
salon | +0.127 |
ara | +0.124 |
pitcher | +0.122 |
post | +0.120 |
Neg logit contributions | |
ling | -0.069 |
around | -0.065 |
shining | -0.057 |
up | -0.057 |
in | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
roller | +0.152 |
salon | +0.144 |
pitcher | +0.138 |
ara | +0.137 |
atters | +0.135 |
Neg logit contributions | |
ling | -0.086 |
around | -0.079 |
shining | -0.071 |
up | -0.071 |
him | -0.066 |
Token | heaven |
Token ID | 9538 |
Feature activation | +8.63e+00 |
Pos logit contributions | |
roller | +0.022 |
salon | +0.020 |
ara | +0.020 |
pitcher | +0.019 |
post | +0.019 |
Neg logit contributions | |
ling | -0.012 |
around | -0.011 |
him | -0.011 |
shining | -0.010 |
up | -0.010 |
Token | ," |
Token ID | 553 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
roller | +0.496 |
salon | +0.458 |
pitcher | +0.447 |
atters | +0.435 |
ara | +0.432 |
Neg logit contributions | |
ling | -0.371 |
around | -0.353 |
up | -0.316 |
in | -0.315 |
shining | -0.299 |
Token | said |
Token ID | 531 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
salon | +0.029 |
roller | +0.028 |
ara | +0.028 |
heaven | +0.027 |
vet | +0.026 |
Neg logit contributions | |
ling | -0.030 |
around | -0.026 |
shining | -0.025 |
led | -0.025 |
up | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ling | +0.064 |
led | +0.052 |
shining | +0.050 |
around | +0.049 |
uses | +0.046 |
Neg logit contributions | |
salon | -0.069 |
roller | -0.069 |
heaven | -0.066 |
ara | -0.064 |
vet | -0.064 |
Token | angel |
Token ID | 18304 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
ling | +0.010 |
around | +0.009 |
shining | +0.008 |
led | +0.008 |
him | +0.008 |
Neg logit contributions | |
roller | -0.012 |
salon | -0.012 |
ara | -0.011 |
heaven | -0.011 |
clinic | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
ling | +0.086 |
shining | +0.077 |
led | +0.073 |
around | +0.072 |
him | +0.069 |
Neg logit contributions | |
roller | -0.092 |
salon | -0.091 |
heaven | -0.086 |
ress | -0.085 |
clinic | -0.085 |
Token | Sara |
Token ID | 24799 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
salon | +0.011 |
lor | +0.011 |
ction | +0.010 |
roller | +0.010 |
ress | +0.010 |
Neg logit contributions | |
around | -0.007 |
in | -0.007 |
him | -0.007 |
his | -0.007 |
ling | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
roller | +0.256 |
salon | +0.244 |
ara | +0.234 |
heaven | +0.227 |
atters | +0.226 |
Neg logit contributions | |
ling | -0.166 |
around | -0.142 |
shining | -0.140 |
led | -0.130 |
up | -0.125 |
Token | taken |
Token ID | 2077 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
roller | +0.028 |
salon | +0.026 |
heaven | +0.026 |
clinic | +0.025 |
atters | +0.025 |
Neg logit contributions | |
ling | -0.018 |
shining | -0.015 |
around | -0.015 |
led | -0.015 |
ie | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
roller | +0.047 |
salon | +0.045 |
pitcher | +0.042 |
ara | +0.042 |
atters | +0.042 |
Neg logit contributions | |
ling | -0.014 |
around | -0.013 |
up | -0.011 |
him | -0.011 |
in | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
roller | +0.041 |
lor | +0.038 |
salon | +0.038 |
atters | +0.038 |
pitcher | +0.037 |
Neg logit contributions | |
him | -0.008 |
up | -0.008 |
around | -0.007 |
ling | -0.007 |
all | -0.006 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.61e+00 |
Pos logit contributions | |
ling | +0.004 |
shining | +0.004 |
around | +0.004 |
up | +0.004 |
in | +0.003 |
Neg logit contributions | |
roller | -0.003 |
lor | -0.003 |
atters | -0.003 |
ress | -0.003 |
post | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
roller | +0.539 |
salon | +0.511 |
ara | +0.496 |
pitcher | +0.482 |
atters | +0.480 |
Neg logit contributions | |
ling | -0.320 |
around | -0.282 |
shining | -0.264 |
up | -0.248 |
led | -0.246 |
Token | She |
Token ID | 1375 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
salon | +0.008 |
ction | +0.008 |
roller | +0.008 |
lor | +0.008 |
ress | +0.008 |
Neg logit contributions | |
him | -0.005 |
around | -0.005 |
in | -0.005 |
his | -0.004 |
up | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
roller | +0.164 |
salon | +0.154 |
pitcher | +0.146 |
atters | +0.145 |
ara | +0.145 |
Neg logit contributions | |
ling | -0.088 |
around | -0.076 |
shining | -0.071 |
led | -0.071 |
him | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ling | +0.021 |
around | +0.019 |
shining | +0.019 |
him | +0.017 |
led | +0.016 |
Neg logit contributions | |
roller | -0.049 |
salon | -0.047 |
ara | -0.045 |
atters | -0.044 |
ress | -0.043 |
Token | bad |
Token ID | 2089 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
roller | +0.013 |
salon | +0.013 |
atters | +0.013 |
ara | +0.013 |
ress | +0.012 |
Neg logit contributions | |
ling | -0.008 |
shining | -0.008 |
around | -0.007 |
up | -0.007 |
in | -0.006 |
Token | put |
Token ID | 1234 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ling | +0.165 |
around | +0.142 |
shining | +0.139 |
led | +0.132 |
up | +0.126 |
Neg logit contributions | |
roller | -0.231 |
salon | -0.220 |
ara | -0.209 |
heaven | -0.203 |
pitcher | -0.203 |
Token | him |
Token ID | 683 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
heaven | +0.030 |
roller | +0.029 |
pitcher | +0.029 |
post | +0.029 |
jail | +0.028 |
Neg logit contributions | |
ling | -0.021 |
itive | -0.017 |
bee | -0.016 |
ie | -0.016 |
curiously | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ling | +0.135 |
Barry | +0.094 |
itive | +0.094 |
curiously | +0.093 |
uses | +0.093 |
Neg logit contributions | |
roller | -0.286 |
heaven | -0.276 |
salon | -0.273 |
jail | -0.263 |
clinic | -0.261 |
Token | his |
Token ID | 465 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
shining | +0.028 |
him | +0.025 |
around | +0.023 |
in | +0.023 |
his | +0.023 |
Neg logit contributions | |
roller | -0.136 |
atters | -0.132 |
salon | -0.130 |
lor | -0.128 |
ara | -0.128 |
Token | st |
Token ID | 336 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ling | +0.094 |
around | +0.091 |
shining | +0.089 |
up | +0.086 |
in | +0.083 |
Neg logit contributions | |
roller | -0.066 |
salon | -0.062 |
atters | -0.061 |
ara | -0.061 |
post | -0.059 |
Token | roller |
Token ID | 10646 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
inconvenience | +0.015 |
salon | +0.014 |
Ble | +0.014 |
Uh | +0.014 |
heaven | +0.013 |
Neg logit contributions | |
around | -0.038 |
ling | -0.038 |
up | -0.037 |
all | -0.037 |
upon | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
roller | +0.552 |
ara | +0.540 |
salon | +0.535 |
atters | +0.530 |
bidder | +0.528 |
Neg logit contributions | |
ling | -0.286 |
around | -0.280 |
up | -0.242 |
in | -0.228 |
shining | -0.222 |
Token | they |
Token ID | 484 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ling | +0.015 |
around | +0.012 |
shining | +0.012 |
led | +0.012 |
ie | +0.011 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.018 |
ara | -0.017 |
heaven | -0.017 |
clinic | -0.017 |
Token | went |
Token ID | 1816 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
roller | +0.030 |
salon | +0.029 |
ara | +0.027 |
pitcher | +0.026 |
heaven | +0.026 |
Neg logit contributions | |
ling | -0.021 |
around | -0.017 |
shining | -0.017 |
led | -0.016 |
up | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
roller | +0.046 |
salon | +0.045 |
ara | +0.045 |
bidder | +0.043 |
pitcher | +0.043 |
Neg logit contributions | |
ling | -0.016 |
around | -0.016 |
shining | -0.014 |
up | -0.014 |
in | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
roller | +0.040 |
salon | +0.038 |
ara | +0.037 |
post | +0.036 |
atters | +0.036 |
Neg logit contributions | |
ling | -0.014 |
around | -0.013 |
shining | -0.012 |
up | -0.011 |
him | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
roller | +0.031 |
salon | +0.029 |
ara | +0.028 |
heaven | +0.027 |
clinic | +0.027 |
Neg logit contributions | |
ling | -0.023 |
around | -0.020 |
shining | -0.019 |
led | -0.018 |
up | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
roller | +0.025 |
salon | +0.024 |
ara | +0.023 |
heaven | +0.022 |
clinic | +0.022 |
Neg logit contributions | |
ling | -0.017 |
around | -0.015 |
shining | -0.014 |
led | -0.014 |
up | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
salon | +0.055 |
roller | +0.054 |
pitcher | +0.049 |
ction | +0.048 |
atters | +0.047 |
Neg logit contributions | |
around | -0.042 |
Joey | -0.041 |
ling | -0.041 |
him | -0.040 |
Peter | -0.039 |
Token | thanked |
Token ID | 26280 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
roller | +0.219 |
salon | +0.204 |
ara | +0.193 |
ress | +0.189 |
post | +0.189 |
Neg logit contributions | |
ling | -0.161 |
around | -0.145 |
shining | -0.135 |
led | -0.131 |
him | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
roller | +0.140 |
salon | +0.136 |
heaven | +0.133 |
ara | +0.132 |
clinic | +0.127 |
Neg logit contributions | |
ling | -0.089 |
led | -0.071 |
around | -0.071 |
shining | -0.070 |
atop | -0.060 |
Token | vet |
Token ID | 20202 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
roller | +0.008 |
salon | +0.008 |
ara | +0.007 |
clinic | +0.007 |
heaven | +0.007 |
Neg logit contributions | |
ling | -0.008 |
around | -0.007 |
led | -0.006 |
shining | -0.006 |
ie | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
roller | +0.496 |
salon | +0.478 |
clinic | +0.449 |
heaven | +0.449 |
ara | +0.448 |
Neg logit contributions | |
ling | -0.345 |
shining | -0.294 |
around | -0.287 |
led | -0.281 |
up | -0.252 |
Token | praised |
Token ID | 15342 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
led | +0.002 |
up | +0.002 |
Neg logit contributions | |
roller | -0.004 |
salon | -0.003 |
ara | -0.003 |
atters | -0.003 |
post | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
roller | +0.048 |
heaven | +0.047 |
salon | +0.047 |
ara | +0.046 |
post | +0.044 |
Neg logit contributions | |
ling | -0.027 |
shining | -0.022 |
led | -0.020 |
around | -0.020 |
atop | -0.018 |
Token | for |
Token ID | 329 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ling | +0.151 |
shining | +0.132 |
led | +0.125 |
around | +0.118 |
ie | +0.109 |
Neg logit contributions | |
roller | -0.245 |
salon | -0.236 |
heaven | -0.235 |
clinic | -0.230 |
ara | -0.226 |
Token | his |
Token ID | 465 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ling | +0.066 |
around | +0.054 |
shining | +0.051 |
led | +0.051 |
ie | +0.047 |
Neg logit contributions | |
roller | -0.110 |
salon | -0.106 |
heaven | -0.102 |
ara | -0.100 |
clinic | -0.100 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ling | +0.008 |
around | +0.007 |
shining | +0.007 |
led | +0.006 |
up | +0.006 |
Neg logit contributions | |
roller | -0.017 |
salon | -0.016 |
ara | -0.015 |
heaven | -0.015 |
atters | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
roller | +0.096 |
salon | +0.089 |
heaven | +0.086 |
clinic | +0.083 |
ara | +0.083 |
Neg logit contributions | |
ling | -0.073 |
shining | -0.065 |
led | -0.062 |
around | -0.059 |
ie | -0.056 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
ling | +0.011 |
around | +0.010 |
shining | +0.010 |
led | +0.010 |
up | +0.009 |
Neg logit contributions | |
roller | -0.016 |
salon | -0.015 |
ara | -0.014 |
atters | -0.014 |
post | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
roller | +0.279 |
salon | +0.266 |
heaven | +0.251 |
ara | +0.250 |
clinic | +0.248 |
Neg logit contributions | |
ling | -0.161 |
shining | -0.133 |
around | -0.129 |
led | -0.126 |
ie | -0.116 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
roller | +0.039 |
salon | +0.037 |
ara | +0.036 |
atters | +0.035 |
pitcher | +0.035 |
Neg logit contributions | |
ling | -0.017 |
around | -0.014 |
shining | -0.013 |
him | -0.012 |
up | -0.012 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
ling | +0.007 |
around | +0.007 |
shining | +0.007 |
up | +0.006 |
in | +0.006 |
Neg logit contributions | |
roller | -0.006 |
atters | -0.005 |
salon | -0.005 |
ress | -0.005 |
ara | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
roller | +0.526 |
salon | +0.501 |
ara | +0.482 |
pitcher | +0.467 |
atters | +0.465 |
Neg logit contributions | |
ling | -0.329 |
around | -0.287 |
shining | -0.274 |
led | -0.258 |
up | -0.254 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
salon | +0.000 |
roller | +0.000 |
lor | +0.000 |
ress | +0.000 |
ction | +0.000 |
Neg logit contributions | |
around | -0.000 |
him | -0.000 |
his | -0.000 |
ling | -0.000 |
all | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
roller | +0.110 |
salon | +0.106 |
atters | +0.099 |
pitcher | +0.099 |
ara | +0.097 |
Neg logit contributions | |
ling | -0.057 |
around | -0.051 |
led | -0.045 |
in | -0.043 |
shining | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
ling | +0.025 |
around | +0.023 |
shining | +0.022 |
him | +0.021 |
led | +0.020 |
Neg logit contributions | |
roller | -0.055 |
salon | -0.053 |
ara | -0.051 |
atters | -0.049 |
pitcher | -0.049 |
Token | get |
Token ID | 651 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
roller | +0.030 |
salon | +0.028 |
ara | +0.027 |
ase | +0.027 |
lor | +0.027 |
Neg logit contributions | |
him | -0.016 |
his | -0.014 |
all | -0.014 |
ling | -0.014 |
up | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
roller | +0.280 |
salon | +0.262 |
ara | +0.259 |
pitcher | +0.258 |
atters | +0.252 |
Neg logit contributions | |
ling | -0.137 |
around | -0.131 |
shining | -0.118 |
in | -0.114 |
up | -0.111 |
Token | took |
Token ID | 1718 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
led | +0.002 |
up | +0.002 |
Neg logit contributions | |
roller | -0.004 |
salon | -0.004 |
ara | -0.004 |
atters | -0.003 |
pitcher | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ling | +0.008 |
around | +0.007 |
him | +0.007 |
up | +0.006 |
shining | +0.006 |
Neg logit contributions | |
roller | -0.017 |
salon | -0.016 |
ara | -0.015 |
pitcher | -0.015 |
clinic | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
roller | +0.041 |
salon | +0.038 |
heaven | +0.037 |
clinic | +0.035 |
pitcher | +0.035 |
Neg logit contributions | |
ling | -0.031 |
led | -0.025 |
shining | -0.025 |
ie | -0.024 |
itive | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
roller | +0.048 |
lor | +0.047 |
salon | +0.046 |
ara | +0.045 |
atters | +0.045 |
Neg logit contributions | |
him | -0.008 |
up | -0.006 |
around | -0.006 |
all | -0.005 |
his | -0.005 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
roller | +0.008 |
lor | +0.008 |
ara | +0.007 |
atters | +0.007 |
ress | +0.007 |
Neg logit contributions | |
up | -0.012 |
ling | -0.011 |
around | -0.011 |
shining | -0.011 |
in | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
roller | +0.542 |
salon | +0.516 |
ara | +0.504 |
pitcher | +0.489 |
atters | +0.484 |
Neg logit contributions | |
ling | -0.312 |
around | -0.276 |
shining | -0.258 |
up | -0.244 |
led | -0.240 |
Token | They |
Token ID | 1119 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
salon | +0.015 |
lor | +0.015 |
ction | +0.015 |
ress | +0.014 |
pitcher | +0.014 |
Neg logit contributions | |
his | -0.007 |
around | -0.007 |
him | -0.007 |
in | -0.006 |
up | -0.006 |
Token | were |
Token ID | 547 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
roller | +0.194 |
salon | +0.183 |
ara | +0.175 |
pitcher | +0.171 |
atters | +0.171 |
Neg logit contributions | |
ling | -0.138 |
around | -0.121 |
shining | -0.116 |
led | -0.112 |
up | -0.106 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ling | +0.026 |
shining | +0.022 |
around | +0.022 |
led | +0.021 |
ie | +0.021 |
Neg logit contributions | |
roller | -0.037 |
salon | -0.036 |
heaven | -0.034 |
clinic | -0.034 |
atters | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
ling | +0.044 |
around | +0.038 |
shining | +0.036 |
led | +0.034 |
up | +0.034 |
Neg logit contributions | |
roller | -0.068 |
salon | -0.065 |
ara | -0.061 |
pitcher | -0.060 |
clinic | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
roller | +0.007 |
salon | +0.007 |
ara | +0.006 |
pitcher | +0.006 |
clinic | +0.006 |
Neg logit contributions | |
ling | -0.004 |
around | -0.004 |
shining | -0.004 |
up | -0.003 |
him | -0.003 |
Token | takes |
Token ID | 2753 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ling | +0.004 |
around | +0.003 |
shining | +0.003 |
led | +0.003 |
up | +0.003 |
Neg logit contributions | |
roller | -0.008 |
salon | -0.008 |
ara | -0.007 |
post | -0.007 |
pitcher | -0.007 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
ling | +0.008 |
around | +0.007 |
him | +0.006 |
shining | +0.006 |
up | +0.006 |
Neg logit contributions | |
roller | -0.025 |
salon | -0.024 |
ara | -0.023 |
clinic | -0.023 |
post | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
ling | +0.029 |
around | +0.025 |
shining | +0.024 |
led | +0.023 |
up | +0.022 |
Neg logit contributions | |
roller | -0.047 |
salon | -0.045 |
ara | -0.043 |
heaven | -0.042 |
atters | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
roller | +0.057 |
lor | +0.055 |
salon | +0.054 |
ara | +0.053 |
atters | +0.053 |
Neg logit contributions | |
him | -0.010 |
his | -0.007 |
up | -0.007 |
around | -0.006 |
ling | -0.005 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
roller | +0.005 |
atters | +0.004 |
lor | +0.004 |
post | +0.004 |
ird | +0.004 |
Neg logit contributions | |
ling | -0.007 |
up | -0.007 |
around | -0.007 |
shining | -0.007 |
all | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
roller | +0.554 |
salon | +0.526 |
ara | +0.519 |
pitcher | +0.502 |
atters | +0.493 |
Neg logit contributions | |
ling | -0.301 |
around | -0.271 |
shining | -0.244 |
up | -0.239 |
led | -0.227 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
around | +0.001 |
him | +0.001 |
ling | +0.001 |
up | +0.001 |
in | +0.001 |
Neg logit contributions | |
salon | -0.001 |
lor | -0.001 |
roller | -0.001 |
ction | -0.001 |
ara | -0.001 |
Token | has |
Token ID | 468 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ling | +0.039 |
around | +0.035 |
shining | +0.033 |
up | +0.033 |
led | +0.033 |
Neg logit contributions | |
roller | -0.038 |
salon | -0.035 |
post | -0.032 |
ara | -0.032 |
pitcher | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
roller | +0.119 |
salon | +0.114 |
ara | +0.112 |
atters | +0.108 |
ress | +0.107 |
Neg logit contributions | |
ling | -0.042 |
him | -0.041 |
around | -0.041 |
shining | -0.040 |
in | -0.037 |
Token | big |
Token ID | 1263 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
roller | +0.018 |
salon | +0.017 |
ara | +0.016 |
atters | +0.016 |
ress | +0.016 |
Neg logit contributions | |
ling | -0.013 |
shining | -0.012 |
around | -0.012 |
up | -0.011 |
in | -0.010 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ling | +0.009 |
around | +0.008 |
up | +0.007 |
shining | +0.007 |
him | +0.007 |
Neg logit contributions | |
roller | -0.020 |
salon | -0.019 |
ara | -0.018 |
clinic | -0.018 |
atters | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
roller | +0.109 |
salon | +0.104 |
ara | +0.099 |
pitcher | +0.097 |
atters | +0.096 |
Neg logit contributions | |
ling | -0.070 |
around | -0.061 |
shining | -0.057 |
up | -0.054 |
led | -0.054 |
Token | Sam |
Token ID | 3409 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
roller | +0.001 |
salon | +0.001 |
ara | +0.001 |
post | +0.001 |
lor | +0.001 |
Neg logit contributions | |
ling | -0.001 |
around | -0.001 |
shining | -0.001 |
up | -0.001 |
led | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
ling | +0.038 |
around | +0.032 |
shining | +0.032 |
led | +0.030 |
up | +0.028 |
Neg logit contributions | |
roller | -0.062 |
salon | -0.059 |
ara | -0.056 |
heaven | -0.055 |
atters | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
roller | +0.047 |
salon | +0.045 |
lor | +0.044 |
ara | +0.044 |
atters | +0.043 |
Neg logit contributions | |
him | -0.014 |
ling | -0.014 |
around | -0.013 |
up | -0.012 |
shining | -0.012 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
roller | +0.015 |
ress | +0.015 |
atters | +0.015 |
ara | +0.015 |
lor | +0.014 |
Neg logit contributions | |
around | -0.016 |
shining | -0.016 |
up | -0.016 |
ling | -0.016 |
in | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
roller | +0.556 |
salon | +0.531 |
ara | +0.523 |
pitcher | +0.503 |
atters | +0.494 |
Neg logit contributions | |
ling | -0.298 |
around | -0.270 |
shining | -0.243 |
up | -0.239 |
led | -0.229 |
Token | They |
Token ID | 1119 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
salon | +0.014 |
lor | +0.013 |
roller | +0.013 |
ress | +0.013 |
ction | +0.013 |
Neg logit contributions | |
around | -0.009 |
him | -0.009 |
his | -0.009 |
all | -0.008 |
in | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
roller | +0.193 |
salon | +0.179 |
ara | +0.175 |
pitcher | +0.170 |
atters | +0.169 |
Neg logit contributions | |
ling | -0.119 |
around | -0.109 |
shining | -0.101 |
led | -0.098 |
in | -0.097 |
Token | to |
Token ID | 284 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
ling | +0.017 |
shining | +0.017 |
around | +0.017 |
him | +0.016 |
in | +0.015 |
Neg logit contributions | |
roller | -0.039 |
salon | -0.037 |
ara | -0.036 |
atters | -0.035 |
lor | -0.035 |
Token | stay |
Token ID | 2652 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
roller | +0.040 |
lor | +0.039 |
ase | +0.038 |
salon | +0.038 |
ara | +0.037 |
Neg logit contributions | |
him | -0.020 |
up | -0.018 |
all | -0.018 |
in | -0.018 |
his | -0.017 |
Token | Tim |
Token ID | 5045 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
ling | +0.006 |
around | +0.005 |
shining | +0.005 |
up | +0.005 |
him | +0.004 |
Neg logit contributions | |
roller | -0.015 |
salon | -0.014 |
ara | -0.014 |
clinic | -0.013 |
pitcher | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
ling | +0.023 |
around | +0.020 |
up | +0.018 |
shining | +0.018 |
led | +0.017 |
Neg logit contributions | |
roller | -0.038 |
salon | -0.037 |
ara | -0.035 |
pitcher | -0.034 |
clinic | -0.034 |
Token | Kim |
Token ID | 6502 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
roller | +0.001 |
salon | +0.001 |
lor | +0.001 |
ara | +0.001 |
clinic | +0.001 |
Neg logit contributions | |
ling | -0.001 |
shining | -0.001 |
around | -0.001 |
him | -0.001 |
in | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
roller | +0.018 |
salon | +0.018 |
ara | +0.017 |
pitcher | +0.016 |
post | +0.016 |
Neg logit contributions | |
ling | -0.012 |
around | -0.010 |
shining | -0.009 |
led | -0.009 |
up | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
roller | +0.046 |
salon | +0.044 |
ara | +0.044 |
lor | +0.043 |
post | +0.042 |
Neg logit contributions | |
ling | -0.014 |
him | -0.014 |
around | -0.013 |
up | -0.012 |
shining | -0.011 |
Token | hospital |
Token ID | 4436 |
Feature activation | +8.59e+00 |
Pos logit contributions | |
roller | +0.006 |
ress | +0.006 |
lor | +0.006 |
ird | +0.005 |
ara | +0.005 |
Neg logit contributions | |
up | -0.007 |
around | -0.007 |
in | -0.007 |
ling | -0.007 |
shining | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
roller | +0.553 |
salon | +0.526 |
ara | +0.521 |
pitcher | +0.501 |
atters | +0.491 |
Neg logit contributions | |
ling | -0.302 |
around | -0.272 |
shining | -0.246 |
up | -0.242 |
led | -0.231 |
Token | They |
Token ID | 1119 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
salon | +0.018 |
lor | +0.017 |
roller | +0.016 |
ction | +0.016 |
pitcher | +0.016 |
Neg logit contributions | |
him | -0.012 |
around | -0.011 |
his | -0.010 |
Joey | -0.010 |
in | -0.010 |
Token | threw |
Token ID | 9617 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
roller | +0.199 |
salon | +0.187 |
ara | +0.181 |
pitcher | +0.175 |
atters | +0.175 |
Neg logit contributions | |
ling | -0.123 |
around | -0.111 |
shining | -0.103 |
led | -0.101 |
him | -0.098 |
Token | away |
Token ID | 1497 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
roller | +0.045 |
salon | +0.043 |
ara | +0.041 |
heaven | +0.041 |
atters | +0.041 |
Neg logit contributions | |
ling | -0.024 |
shining | -0.019 |
around | -0.019 |
led | -0.018 |
ie | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
roller | +0.321 |
salon | +0.310 |
ara | +0.292 |
atters | +0.290 |
pitcher | +0.289 |
Neg logit contributions | |
ling | -0.112 |
around | -0.097 |
shining | -0.087 |
in | -0.084 |
up | -0.083 |
Token | for |
Token ID | 329 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ling | +0.102 |
led | +0.090 |
shining | +0.086 |
around | +0.081 |
itive | +0.079 |
Neg logit contributions | |
salon | -0.114 |
ara | -0.108 |
clinic | -0.108 |
roller | -0.108 |
ress | -0.107 |
Token | some |
Token ID | 617 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ling | +0.072 |
around | +0.060 |
shining | +0.057 |
led | +0.055 |
up | +0.051 |
Neg logit contributions | |
roller | -0.120 |
salon | -0.116 |
ara | -0.110 |
heaven | -0.109 |
clinic | -0.107 |
Token | funny |
Token ID | 8258 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
roller | +0.060 |
salon | +0.059 |
heaven | +0.055 |
clinic | +0.054 |
ara | +0.054 |
Neg logit contributions | |
ling | -0.064 |
around | -0.055 |
led | -0.054 |
shining | -0.054 |
up | -0.050 |
Token | little |
Token ID | 1310 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ling | +0.016 |
shining | +0.014 |
around | +0.013 |
led | +0.013 |
atop | +0.013 |
Neg logit contributions | |
roller | -0.018 |
salon | -0.017 |
heaven | -0.016 |
ara | -0.016 |
pitcher | -0.016 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
roller | +0.065 |
salon | +0.063 |
ara | +0.059 |
heaven | +0.059 |
pitcher | +0.058 |
Neg logit contributions | |
ling | -0.052 |
around | -0.045 |
shining | -0.044 |
led | -0.043 |
up | -0.040 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
roller | +0.080 |
salon | +0.078 |
ara | +0.073 |
pitcher | +0.071 |
heaven | +0.071 |
Neg logit contributions | |
ling | -0.061 |
around | -0.050 |
shining | -0.049 |
led | -0.049 |
him | -0.045 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
ling | +0.601 |
around | +0.523 |
shining | +0.515 |
led | +0.484 |
up | +0.471 |
Neg logit contributions | |
roller | -0.706 |
salon | -0.671 |
ara | -0.635 |
pitcher | -0.620 |
atters | -0.610 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ling | +0.302 |
led | +0.251 |
shining | +0.247 |
around | +0.241 |
itive | +0.229 |
Neg logit contributions | |
roller | -0.333 |
salon | -0.325 |
pitcher | -0.305 |
heaven | -0.302 |
post | -0.299 |
Token | Her |
Token ID | 2332 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
ling | +0.026 |
around | +0.026 |
him | +0.024 |
Joey | +0.024 |
shining | +0.024 |
Neg logit contributions | |
roller | -0.036 |
salon | -0.034 |
atters | -0.034 |
post | -0.031 |
pitcher | -0.031 |
Token | m |
Token ID | 285 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
roller | +0.019 |
salon | +0.018 |
ara | +0.018 |
vet | +0.017 |
clinic | +0.017 |
Neg logit contributions | |
ling | -0.018 |
led | -0.015 |
around | -0.015 |
ging | -0.013 |
shining | -0.013 |
Token | ama |
Token ID | 1689 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ling | +0.180 |
around | +0.162 |
shining | +0.157 |
led | +0.151 |
up | +0.146 |
Neg logit contributions | |
roller | -0.174 |
salon | -0.164 |
ara | -0.154 |
ress | -0.147 |
atters | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
ling | +0.033 |
shining | +0.028 |
around | +0.026 |
led | +0.026 |
usual | +0.026 |
Neg logit contributions | |
heaven | -0.037 |
ara | -0.037 |
S | -0.034 |
salon | -0.033 |
jail | -0.033 |
Token | â |
Token ID | 22940 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
roller | +0.162 |
salon | +0.158 |
ara | +0.147 |
pitcher | +0.146 |
heaven | +0.146 |
Neg logit contributions | |
ling | -0.126 |
led | -0.106 |
around | -0.102 |
shining | -0.099 |
ie | -0.094 |
Token | € |
Token ID | 26391 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
roller | +0.181 |
salon | +0.166 |
heaven | +0.155 |
pitcher | +0.154 |
ara | +0.153 |
Neg logit contributions | |
ling | -0.199 |
around | -0.173 |
shining | -0.165 |
led | -0.160 |
ie | -0.160 |
Token | said |
Token ID | 531 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
ling | +0.100 |
around | +0.093 |
shining | +0.088 |
up | +0.084 |
in | +0.081 |
Neg logit contributions | |
roller | -0.114 |
salon | -0.114 |
heaven | -0.112 |
pitcher | -0.108 |
clinic | -0.107 |
Token | T |
Token ID | 309 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
ling | +0.039 |
shining | +0.033 |
around | +0.033 |
led | +0.032 |
ie | +0.030 |
Neg logit contributions | |
roller | -0.051 |
salon | -0.048 |
ara | -0.046 |
heaven | -0.045 |
post | -0.044 |
Token | od |
Token ID | 375 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
ling | +0.226 |
around | +0.201 |
shining | +0.198 |
led | +0.189 |
up | +0.183 |
Neg logit contributions | |
roller | -0.220 |
salon | -0.207 |
ara | -0.196 |
heaven | -0.188 |
atters | -0.188 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ling | +0.554 |
shining | +0.539 |
around | +0.501 |
up | +0.470 |
ging | +0.458 |
Neg logit contributions | |
ara | -0.662 |
roller | -0.655 |
salon | -0.654 |
ress | -0.596 |
lor | -0.595 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
around | +0.008 |
him | +0.008 |
shining | +0.008 |
ling | +0.008 |
Joey | +0.008 |
Neg logit contributions | |
salon | -0.012 |
roller | -0.012 |
atters | -0.012 |
pitcher | -0.011 |
heaven | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ling | +0.005 |
around | +0.004 |
him | +0.004 |
shining | +0.004 |
up | +0.004 |
Neg logit contributions | |
salon | -0.007 |
roller | -0.007 |
pitcher | -0.006 |
atters | -0.006 |
heaven | -0.006 |
Token | â |
Token ID | 22940 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ling | +0.006 |
around | +0.005 |
him | +0.005 |
shining | +0.005 |
Barry | +0.005 |
Neg logit contributions | |
roller | -0.007 |
atters | -0.006 |
salon | -0.006 |
heaven | -0.006 |
pitcher | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
roller | +0.119 |
salon | +0.114 |
pitcher | +0.105 |
clinic | +0.103 |
heaven | +0.102 |
Neg logit contributions | |
ling | -0.128 |
around | -0.114 |
shining | -0.107 |
led | -0.107 |
up | -0.104 |
Token | stretch |
Token ID | 7539 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
ling | +0.153 |
around | +0.135 |
shining | +0.132 |
led | +0.126 |
up | +0.122 |
Neg logit contributions | |
roller | -0.165 |
salon | -0.156 |
ara | -0.147 |
atters | -0.142 |
heaven | -0.142 |
Token | out |
Token ID | 503 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ling | +0.003 |
shining | +0.002 |
led | +0.002 |
around | +0.002 |
itive | +0.002 |
Neg logit contributions | |
roller | -0.005 |
salon | -0.004 |
post | -0.004 |
ara | -0.004 |
heaven | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
ling | +0.042 |
shining | +0.035 |
around | +0.035 |
led | +0.034 |
ie | +0.031 |
Neg logit contributions | |
roller | -0.061 |
salon | -0.057 |
heaven | -0.055 |
ara | -0.054 |
post | -0.054 |
Token | enormous |
Token ID | 9812 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
ling | +0.037 |
led | +0.032 |
shining | +0.030 |
around | +0.030 |
ie | +0.029 |
Neg logit contributions | |
roller | -0.040 |
salon | -0.039 |
heaven | -0.037 |
pitcher | -0.036 |
clinic | -0.036 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ling | +0.101 |
around | +0.088 |
shining | +0.086 |
led | +0.081 |
up | +0.078 |
Neg logit contributions | |
roller | -0.139 |
salon | -0.132 |
ara | -0.125 |
atters | -0.122 |
heaven | -0.122 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
roller | +0.104 |
salon | +0.100 |
ara | +0.096 |
post | +0.094 |
pitcher | +0.093 |
Neg logit contributions | |
ling | -0.056 |
around | -0.044 |
shining | -0.043 |
led | -0.042 |
him | -0.040 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.62e+00 |
Pos logit contributions | |
ling | +0.507 |
around | +0.432 |
shining | +0.421 |
led | +0.397 |
up | +0.381 |
Neg logit contributions | |
roller | -0.791 |
salon | -0.753 |
ara | -0.716 |
heaven | -0.698 |
atters | -0.698 |
Token | would |
Token ID | 561 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
ling | +0.239 |
shining | +0.190 |
around | +0.186 |
led | +0.186 |
him | +0.175 |
Neg logit contributions | |
roller | -0.384 |
salon | -0.372 |
post | -0.352 |
heaven | -0.351 |
ara | -0.347 |
Token | show |
Token ID | 905 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ling | +0.154 |
around | +0.138 |
shining | +0.135 |
led | +0.127 |
up | +0.125 |
Neg logit contributions | |
roller | -0.162 |
salon | -0.152 |
ara | -0.144 |
atters | -0.139 |
pitcher | -0.139 |
Token | their |
Token ID | 511 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
roller | +0.127 |
salon | +0.121 |
heaven | +0.121 |
ara | +0.118 |
post | +0.117 |
Neg logit contributions | |
ling | -0.089 |
shining | -0.074 |
led | -0.071 |
around | -0.069 |
atop | -0.064 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
roller | +0.129 |
salon | +0.124 |
ara | +0.115 |
heaven | +0.114 |
clinic | +0.114 |
Neg logit contributions | |
ling | -0.108 |
led | -0.091 |
around | -0.090 |
shining | -0.087 |
him | -0.083 |
Token | replied |
Token ID | 8712 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
around | +0.129 |
ling | +0.123 |
in | +0.115 |
couldn | +0.115 |
walking | +0.114 |
Neg logit contributions | |
salon | -0.130 |
vet | -0.123 |
roller | -0.122 |
heaven | -0.119 |
pitcher | -0.119 |
Token | his |
Token ID | 465 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ling | +0.092 |
around | +0.081 |
shining | +0.078 |
led | +0.073 |
up | +0.072 |
Neg logit contributions | |
roller | -0.140 |
salon | -0.134 |
ara | -0.127 |
atters | -0.124 |
heaven | -0.124 |
Token | mum |
Token ID | 25682 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ling | +0.082 |
around | +0.072 |
shining | +0.070 |
up | +0.065 |
led | +0.065 |
Neg logit contributions | |
roller | -0.114 |
salon | -0.109 |
ara | -0.103 |
heaven | -0.101 |
atters | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
ling | +0.077 |
shining | +0.066 |
around | +0.064 |
led | +0.063 |
up | +0.058 |
Neg logit contributions | |
roller | -0.093 |
salon | -0.089 |
ara | -0.086 |
heaven | -0.082 |
ress | -0.082 |
Token | T |
Token ID | 309 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
around | +0.030 |
Joey | +0.029 |
him | +0.028 |
Barry | +0.028 |
Bobby | +0.027 |
Neg logit contributions | |
salon | -0.037 |
roller | -0.036 |
atters | -0.035 |
heaven | -0.034 |
bidder | -0.033 |
Token | od |
Token ID | 375 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ling | +0.186 |
around | +0.158 |
shining | +0.153 |
led | +0.144 |
up | +0.137 |
Neg logit contributions | |
roller | -0.310 |
salon | -0.296 |
ara | -0.283 |
atters | -0.275 |
heaven | -0.273 |
Token | nodded |
Token ID | 14464 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
ling | +0.459 |
shining | +0.440 |
around | +0.406 |
up | +0.380 |
ging | +0.352 |
Neg logit contributions | |
ara | -0.750 |
roller | -0.749 |
salon | -0.744 |
post | -0.679 |
lor | -0.678 |
Token | and |
Token ID | 290 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
ling | +0.003 |
led | +0.003 |
around | +0.002 |
shining | +0.002 |
uses | +0.002 |
Neg logit contributions | |
roller | -0.004 |
salon | -0.003 |
ara | -0.003 |
heaven | -0.003 |
post | -0.003 |
Token | agreed |
Token ID | 4987 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
ling | +0.033 |
around | +0.029 |
shining | +0.028 |
led | +0.027 |
up | +0.026 |
Neg logit contributions | |
roller | -0.050 |
salon | -0.047 |
ara | -0.045 |
atters | -0.044 |
clinic | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
roller | +0.033 |
salon | +0.031 |
ara | +0.030 |
atters | +0.029 |
heaven | +0.029 |
Neg logit contributions | |
ling | -0.020 |
around | -0.017 |
shining | -0.017 |
led | -0.016 |
up | -0.015 |
Token | put |
Token ID | 1234 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ling | +0.005 |
around | +0.005 |
shining | +0.004 |
him | +0.004 |
up | +0.004 |
Neg logit contributions | |
roller | -0.006 |
salon | -0.006 |
ara | -0.006 |
pitcher | -0.005 |
post | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
roller | +0.084 |
ara | +0.077 |
salon | +0.077 |
atters | +0.070 |
S | +0.070 |
Neg logit contributions | |
ling | -0.093 |
led | -0.080 |
around | -0.076 |
shining | -0.075 |
uses | -0.072 |
Token | there |
Token ID | 612 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
uses | +0.020 |
ling | +0.019 |
him | +0.017 |
Barry | +0.017 |
questions | +0.016 |
Neg logit contributions | |
ara | -0.026 |
Anna | -0.025 |
roller | -0.024 |
S | -0.024 |
salon | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
ling | +0.025 |
shining | +0.021 |
led | +0.021 |
around | +0.021 |
ging | +0.019 |
Neg logit contributions | |
roller | -0.030 |
ara | -0.029 |
salon | -0.029 |
post | -0.026 |
heaven | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
led | +0.002 |
ie | +0.002 |
Neg logit contributions | |
roller | -0.004 |
salon | -0.004 |
ara | -0.004 |
heaven | -0.004 |
pitcher | -0.003 |
Token | do |
Token ID | 466 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ling | +0.012 |
around | +0.010 |
led | +0.010 |
shining | +0.010 |
him | +0.009 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.018 |
ara | -0.018 |
pitcher | -0.017 |
clinic | -0.017 |
Token | od |
Token ID | 375 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
ling | +0.105 |
around | +0.095 |
shining | +0.094 |
led | +0.090 |
up | +0.088 |
Neg logit contributions | |
roller | -0.070 |
salon | -0.066 |
ara | -0.060 |
atters | -0.059 |
heaven | -0.058 |
Token | le |
Token ID | 293 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
shining | +0.402 |
Joey | +0.376 |
Barry | +0.368 |
around | +0.365 |
ling | +0.356 |
Neg logit contributions | |
salon | -0.811 |
ara | -0.780 |
ase | -0.732 |
S | -0.726 |
ress | -0.720 |
Token | who |
Token ID | 508 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
ling | +0.258 |
shining | +0.239 |
led | +0.234 |
around | +0.231 |
up | +0.221 |
Neg logit contributions | |
salon | -0.223 |
roller | -0.216 |
heaven | -0.212 |
clinic | -0.210 |
ara | -0.210 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
ling | +0.214 |
shining | +0.170 |
around | +0.169 |
led | +0.157 |
up | +0.151 |
Neg logit contributions | |
roller | -0.422 |
salon | -0.403 |
ara | -0.392 |
heaven | -0.389 |
post | -0.384 |
Token | to |
Token ID | 284 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
ling | +0.131 |
led | +0.106 |
around | +0.104 |
shining | +0.102 |
ie | +0.096 |
Neg logit contributions | |
roller | -0.172 |
salon | -0.165 |
heaven | -0.154 |
ara | -0.153 |
clinic | -0.152 |
Token | make |
Token ID | 787 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
him | +0.002 |
up | +0.002 |
Neg logit contributions | |
roller | -0.003 |
ara | -0.003 |
salon | -0.003 |
post | -0.003 |
atters | -0.003 |
Token | thing |
Token ID | 1517 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
roller | +0.252 |
salon | +0.240 |
ara | +0.227 |
heaven | +0.222 |
clinic | +0.220 |
Neg logit contributions | |
ling | -0.197 |
around | -0.171 |
shining | -0.167 |
led | -0.160 |
up | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ling | +0.023 |
shining | +0.019 |
around | +0.018 |
led | +0.018 |
ie | +0.017 |
Neg logit contributions | |
roller | -0.025 |
salon | -0.024 |
ara | -0.022 |
heaven | -0.022 |
atters | -0.022 |
Token | John |
Token ID | 1757 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ling | +0.013 |
around | +0.011 |
shining | +0.011 |
up | +0.010 |
led | +0.010 |
Neg logit contributions | |
roller | -0.016 |
salon | -0.015 |
ara | -0.014 |
atters | -0.014 |
clinic | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
ling | +0.098 |
around | +0.085 |
shining | +0.084 |
led | +0.080 |
up | +0.077 |
Neg logit contributions | |
roller | -0.115 |
salon | -0.109 |
ara | -0.104 |
heaven | -0.101 |
clinic | -0.100 |
Token | N |
Token ID | 399 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
around | +0.032 |
ling | +0.031 |
him | +0.031 |
Joey | +0.030 |
shining | +0.030 |
Neg logit contributions | |
roller | -0.033 |
salon | -0.033 |
post | -0.030 |
pitcher | -0.030 |
ara | -0.029 |
Token | od |
Token ID | 375 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
ling | +0.005 |
around | +0.005 |
led | +0.004 |
in | +0.004 |
ie | +0.004 |
Neg logit contributions | |
roller | -0.004 |
salon | -0.004 |
pitcher | -0.004 |
atters | -0.003 |
post | -0.003 |
Token | if |
Token ID | 611 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ling | +0.651 |
shining | +0.604 |
around | +0.582 |
up | +0.546 |
led | +0.538 |
Neg logit contributions | |
roller | -0.572 |
salon | -0.563 |
ara | -0.542 |
atters | -0.510 |
heaven | -0.506 |
Token | you |
Token ID | 345 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ling | +0.198 |
around | +0.174 |
shining | +0.170 |
led | +0.167 |
up | +0.158 |
Neg logit contributions | |
roller | -0.163 |
salon | -0.157 |
ara | -0.146 |
heaven | -0.142 |
clinic | -0.139 |
Token | 're |
Token ID | 821 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
ling | +0.023 |
shining | +0.020 |
around | +0.019 |
led | +0.019 |
up | +0.018 |
Neg logit contributions | |
roller | -0.023 |
salon | -0.022 |
ara | -0.020 |
heaven | -0.020 |
atters | -0.020 |
Token | tired |
Token ID | 10032 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ling | +0.086 |
led | +0.073 |
around | +0.070 |
shining | +0.068 |
ie | +0.067 |
Neg logit contributions | |
roller | -0.113 |
salon | -0.111 |
heaven | -0.107 |
clinic | -0.105 |
ara | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
roller | +0.020 |
salon | +0.019 |
ara | +0.018 |
heaven | +0.018 |
atters | +0.018 |
Neg logit contributions | |
ling | -0.015 |
around | -0.013 |
shining | -0.013 |
led | -0.012 |
up | -0.012 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
roller | +0.136 |
salon | +0.130 |
atters | +0.119 |
ara | +0.118 |
pitcher | +0.117 |
Neg logit contributions | |
ling | -0.130 |
around | -0.127 |
shining | -0.118 |
him | -0.117 |
up | -0.113 |
Token | L |
Token ID | 43 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
roller | +0.052 |
salon | +0.048 |
ara | +0.047 |
heaven | +0.045 |
post | +0.044 |
Neg logit contributions | |
ling | -0.060 |
shining | -0.052 |
around | -0.052 |
led | -0.051 |
ie | -0.048 |
Token | ily |
Token ID | 813 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
roller | +0.174 |
salon | +0.162 |
ara | +0.148 |
clinic | +0.148 |
pitcher | +0.148 |
Neg logit contributions | |
ling | -0.195 |
around | -0.173 |
shining | -0.168 |
led | -0.163 |
ie | -0.162 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
roller | +0.096 |
salon | +0.091 |
ara | +0.085 |
post | +0.085 |
pitcher | +0.085 |
Neg logit contributions | |
ling | -0.062 |
around | -0.054 |
shining | -0.050 |
led | -0.049 |
up | -0.047 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ling | +0.088 |
led | +0.074 |
around | +0.068 |
atop | +0.068 |
ging | +0.067 |
Neg logit contributions | |
salon | -0.090 |
roller | -0.083 |
heaven | -0.079 |
pitcher | -0.077 |
ara | -0.076 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
salon | +0.088 |
roller | +0.085 |
ara | +0.080 |
pitcher | +0.077 |
clinic | +0.075 |
Neg logit contributions | |
ling | -0.073 |
around | -0.064 |
led | -0.063 |
spear | -0.060 |
Barry | -0.058 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
ling | +0.542 |
around | +0.471 |
shining | +0.455 |
led | +0.433 |
up | +0.420 |
Neg logit contributions | |
roller | -0.725 |
salon | -0.693 |
ara | -0.659 |
pitcher | -0.637 |
atters | -0.634 |
Token | . |
Token ID | 13 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
ling | +0.255 |
led | +0.232 |
ging | +0.217 |
ged | +0.211 |
around | +0.208 |
Neg logit contributions | |
salon | -0.289 |
roller | -0.284 |
heaven | -0.272 |
pitcher | -0.271 |
clinic | -0.269 |
Token | She |
Token ID | 1375 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ling | +0.036 |
around | +0.035 |
him | +0.034 |
shining | +0.034 |
Joey | +0.034 |
Neg logit contributions | |
roller | -0.033 |
salon | -0.031 |
clinic | -0.028 |
atters | -0.028 |
lor | -0.028 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
roller | +0.108 |
salon | +0.104 |
ara | +0.101 |
heaven | +0.097 |
post | +0.097 |
Neg logit contributions | |
ling | -0.054 |
around | -0.043 |
shining | -0.042 |
led | -0.039 |
up | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ling | +0.130 |
led | +0.115 |
ging | +0.108 |
around | +0.101 |
itive | +0.101 |
Neg logit contributions | |
salon | -0.109 |
roller | -0.104 |
heaven | -0.098 |
pitcher | -0.096 |
ara | -0.096 |
Token | a |
Token ID | 257 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
roller | +0.065 |
heaven | +0.061 |
salon | +0.060 |
jail | +0.058 |
post | +0.058 |
Neg logit contributions | |
ling | -0.048 |
led | -0.036 |
around | -0.036 |
ie | -0.034 |
shining | -0.033 |
Token | garden |
Token ID | 11376 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
ling | +0.015 |
shining | +0.013 |
around | +0.013 |
up | +0.012 |
led | +0.011 |
Neg logit contributions | |
roller | -0.020 |
salon | -0.019 |
ara | -0.019 |
atters | -0.019 |
heaven | -0.018 |
Token | full |
Token ID | 1336 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
roller | +0.207 |
ara | +0.201 |
salon | +0.199 |
atters | +0.199 |
heaven | +0.185 |
Neg logit contributions | |
ling | -0.098 |
around | -0.098 |
shining | -0.091 |
in | -0.089 |
up | -0.079 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
roller | +0.116 |
salon | +0.112 |
ara | +0.106 |
atters | +0.105 |
heaven | +0.101 |
Neg logit contributions | |
ling | -0.090 |
around | -0.083 |
shining | -0.081 |
in | -0.073 |
up | -0.072 |
Token | wild |
Token ID | 4295 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
roller | +0.060 |
salon | +0.057 |
heaven | +0.057 |
jail | +0.055 |
pitcher | +0.055 |
Neg logit contributions | |
ling | -0.057 |
led | -0.047 |
around | -0.045 |
ging | -0.043 |
ie | -0.043 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.28e+01 |
Pos logit contributions | |
ling | +0.047 |
around | +0.038 |
led | +0.037 |
shining | +0.036 |
bled | +0.036 |
Neg logit contributions | |
roller | -0.068 |
heaven | -0.062 |
ara | -0.062 |
jail | -0.061 |
clinic | -0.061 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
ling | +0.528 |
around | +0.460 |
shining | +0.442 |
led | +0.416 |
up | +0.411 |
Neg logit contributions | |
roller | -0.731 |
salon | -0.688 |
ara | -0.655 |
atters | -0.646 |
pitcher | -0.641 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ling | +0.278 |
led | +0.237 |
around | +0.226 |
shining | +0.226 |
him | +0.216 |
Neg logit contributions | |
roller | -0.308 |
salon | -0.285 |
heaven | -0.283 |
pitcher | -0.273 |
clinic | -0.272 |
Token | He |
Token ID | 679 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ling | +0.017 |
around | +0.016 |
shining | +0.015 |
him | +0.015 |
up | +0.015 |
Neg logit contributions | |
roller | -0.023 |
salon | -0.022 |
ara | -0.020 |
atters | -0.020 |
pitcher | -0.020 |
Token | decided |
Token ID | 3066 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ling | +0.046 |
shining | +0.039 |
around | +0.039 |
led | +0.036 |
up | +0.035 |
Neg logit contributions | |
roller | -0.068 |
salon | -0.066 |
ara | -0.063 |
clinic | -0.061 |
heaven | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
roller | +0.036 |
salon | +0.034 |
post | +0.032 |
vet | +0.031 |
heaven | +0.031 |
Neg logit contributions | |
ling | -0.034 |
led | -0.029 |
shining | -0.028 |
ie | -0.027 |
around | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
ling | +0.036 |
shining | +0.028 |
led | +0.028 |
around | +0.027 |
bee | +0.026 |
Neg logit contributions | |
roller | -0.044 |
salon | -0.043 |
heaven | -0.042 |
vet | -0.041 |
ara | -0.041 |
Token | biggest |
Token ID | 4094 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
ling | +0.034 |
led | +0.030 |
around | +0.029 |
him | +0.026 |
ie | +0.026 |
Neg logit contributions | |
roller | -0.039 |
salon | -0.039 |
pitcher | -0.036 |
ara | -0.036 |
clinic | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ling | +0.200 |
around | +0.175 |
shining | +0.172 |
led | +0.161 |
up | +0.157 |
Neg logit contributions | |
roller | -0.252 |
salon | -0.239 |
ara | -0.226 |
atters | -0.220 |
heaven | -0.220 |
Token | brightest |
Token ID | 33871 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
ling | +0.033 |
led | +0.028 |
ging | +0.027 |
ged | +0.027 |
around | +0.027 |
Neg logit contributions | |
salon | -0.031 |
pitcher | -0.030 |
roller | -0.030 |
heaven | -0.028 |
ara | -0.028 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ling | +0.265 |
around | +0.228 |
led | +0.220 |
shining | +0.218 |
up | +0.204 |
Neg logit contributions | |
roller | -0.333 |
salon | -0.318 |
ara | -0.304 |
pitcher | -0.295 |
heaven | -0.293 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
roller | +0.124 |
ara | +0.119 |
salon | +0.118 |
post | +0.114 |
pitcher | +0.114 |
Neg logit contributions | |
ling | -0.050 |
led | -0.036 |
around | -0.036 |
spear | -0.036 |
nam | -0.035 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
ling | +0.572 |
around | +0.507 |
shining | +0.487 |
up | +0.465 |
him | +0.457 |
Neg logit contributions | |
roller | -0.637 |
salon | -0.601 |
ara | -0.588 |
pitcher | -0.572 |
atters | -0.566 |
Token | she |
Token ID | 673 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ling | +0.235 |
led | +0.187 |
shining | +0.184 |
itive | +0.181 |
around | +0.180 |
Neg logit contributions | |
roller | -0.333 |
salon | -0.322 |
pitcher | -0.312 |
post | -0.311 |
heaven | -0.311 |
Token | could |
Token ID | 714 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
ling | +0.010 |
shining | +0.008 |
around | +0.008 |
up | +0.008 |
led | +0.008 |
Neg logit contributions | |
roller | -0.014 |
salon | -0.013 |
ara | -0.013 |
post | -0.013 |
heaven | -0.013 |
Token | find |
Token ID | 1064 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ling | +0.129 |
around | +0.114 |
shining | +0.111 |
led | +0.104 |
up | +0.102 |
Neg logit contributions | |
roller | -0.152 |
salon | -0.143 |
ara | -0.136 |
heaven | -0.131 |
atters | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
ling | +0.055 |
shining | +0.046 |
around | +0.044 |
led | +0.044 |
spear | +0.040 |
Neg logit contributions | |
roller | -0.066 |
salon | -0.064 |
heaven | -0.063 |
ara | -0.062 |
post | -0.061 |
Token | The |
Token ID | 464 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ling | +0.020 |
around | +0.017 |
shining | +0.017 |
him | +0.016 |
in | +0.016 |
Neg logit contributions | |
roller | -0.021 |
salon | -0.019 |
atters | -0.019 |
heaven | -0.019 |
clinic | -0.018 |
Token | next |
Token ID | 1306 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
roller | +0.042 |
salon | +0.041 |
ara | +0.038 |
pitcher | +0.038 |
heaven | +0.037 |
Neg logit contributions | |
ling | -0.031 |
around | -0.026 |
led | -0.026 |
shining | -0.025 |
up | -0.023 |
Token | day |
Token ID | 1110 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ling | +0.017 |
around | +0.015 |
shining | +0.014 |
in | +0.012 |
up | +0.012 |
Neg logit contributions | |
roller | -0.043 |
salon | -0.041 |
atters | -0.040 |
heaven | -0.039 |
clinic | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ling | +0.053 |
around | +0.048 |
shining | +0.044 |
in | +0.044 |
him | +0.043 |
Neg logit contributions | |
roller | -0.114 |
salon | -0.110 |
atters | -0.109 |
heaven | -0.105 |
clinic | -0.104 |
Token | T |
Token ID | 309 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
ling | +0.023 |
around | +0.021 |
shining | +0.020 |
up | +0.019 |
him | +0.019 |
Neg logit contributions | |
roller | -0.032 |
salon | -0.031 |
atters | -0.030 |
clinic | -0.029 |
ara | -0.029 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.167 |
around | +0.140 |
shining | +0.136 |
led | +0.127 |
up | +0.120 |
Neg logit contributions | |
roller | -0.316 |
salon | -0.302 |
ara | -0.289 |
atters | -0.281 |
heaven | -0.281 |
Token | and |
Token ID | 290 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
ling | +0.254 |
shining | +0.237 |
around | +0.225 |
up | +0.187 |
nam | +0.160 |
Neg logit contributions | |
ara | -0.928 |
roller | -0.924 |
salon | -0.924 |
ress | -0.861 |
lor | -0.857 |
Token | his |
Token ID | 465 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
ling | +0.023 |
around | +0.019 |
shining | +0.019 |
led | +0.018 |
up | +0.017 |
Neg logit contributions | |
roller | -0.040 |
salon | -0.038 |
ara | -0.036 |
atters | -0.036 |
clinic | -0.035 |
Token | mom |
Token ID | 1995 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ling | +0.077 |
led | +0.063 |
around | +0.063 |
shining | +0.058 |
ging | +0.057 |
Neg logit contributions | |
roller | -0.104 |
salon | -0.098 |
ara | -0.094 |
pitcher | -0.094 |
vet | -0.091 |
Token | opened |
Token ID | 4721 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
roller | +0.044 |
salon | +0.042 |
ara | +0.040 |
pitcher | +0.039 |
atters | +0.038 |
Neg logit contributions | |
ling | -0.029 |
around | -0.024 |
shining | -0.024 |
led | -0.023 |
up | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
roller | +0.279 |
salon | +0.264 |
ara | +0.256 |
heaven | +0.252 |
pitcher | +0.247 |
Neg logit contributions | |
ling | -0.146 |
led | -0.110 |
shining | -0.109 |
around | -0.107 |
ie | -0.099 |
Token | garden |
Token ID | 11376 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
roller | +0.085 |
salon | +0.081 |
ara | +0.075 |
clinic | +0.074 |
heaven | +0.074 |
Neg logit contributions | |
ling | -0.078 |
around | -0.068 |
shining | -0.066 |
led | -0.066 |
ie | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
roller | +0.207 |
salon | +0.196 |
ara | +0.188 |
atters | +0.183 |
heaven | +0.182 |
Neg logit contributions | |
ling | -0.138 |
around | -0.119 |
shining | -0.115 |
led | -0.109 |
up | -0.106 |
Token | admire |
Token ID | 21099 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ling | +0.017 |
around | +0.014 |
shining | +0.014 |
led | +0.014 |
up | +0.013 |
Neg logit contributions | |
roller | -0.024 |
salon | -0.023 |
ara | -0.021 |
heaven | -0.021 |
pitcher | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
heaven | +0.028 |
salon | +0.028 |
roller | +0.028 |
ara | +0.028 |
yourselves | +0.026 |
Neg logit contributions | |
ling | -0.020 |
led | -0.016 |
around | -0.015 |
shining | -0.015 |
atop | -0.014 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ling | +0.057 |
led | +0.049 |
around | +0.049 |
him | +0.045 |
shining | +0.045 |
Neg logit contributions | |
roller | -0.061 |
salon | -0.058 |
heaven | -0.055 |
pitcher | -0.055 |
clinic | -0.054 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
roller | +0.099 |
salon | +0.098 |
ara | +0.090 |
pitcher | +0.090 |
heaven | +0.088 |
Neg logit contributions | |
ling | -0.064 |
led | -0.055 |
around | -0.054 |
Barry | -0.051 |
ging | -0.050 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
ling | +0.561 |
around | +0.501 |
shining | +0.477 |
him | +0.448 |
led | +0.448 |
Neg logit contributions | |
roller | -0.649 |
salon | -0.625 |
ara | -0.597 |
pitcher | -0.583 |
atters | -0.566 |
Token | . |
Token ID | 13 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
ling | +0.263 |
led | +0.231 |
around | +0.220 |
shining | +0.212 |
ged | +0.208 |
Neg logit contributions | |
roller | -0.293 |
salon | -0.292 |
heaven | -0.280 |
pitcher | -0.272 |
clinic | -0.270 |
Token | They |
Token ID | 1119 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
around | +0.002 |
him | +0.002 |
ling | +0.002 |
Joey | +0.002 |
up | +0.002 |
Neg logit contributions | |
salon | -0.003 |
roller | -0.003 |
post | -0.002 |
ction | -0.002 |
pitcher | -0.002 |
Token | also |
Token ID | 635 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
salon | +0.148 |
roller | +0.145 |
ara | +0.135 |
heaven | +0.134 |
pitcher | +0.132 |
Neg logit contributions | |
ling | -0.143 |
shining | -0.122 |
led | -0.120 |
around | -0.118 |
up | -0.111 |
Token | see |
Token ID | 766 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
roller | +0.086 |
salon | +0.081 |
ara | +0.077 |
heaven | +0.075 |
atters | +0.075 |
Neg logit contributions | |
ling | -0.070 |
around | -0.062 |
shining | -0.060 |
led | -0.058 |
up | -0.055 |
Token | da |
Token ID | 12379 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
roller | +0.011 |
salon | +0.011 |
ara | +0.010 |
heaven | +0.010 |
pitcher | +0.010 |
Neg logit contributions | |
ling | -0.009 |
around | -0.007 |
led | -0.007 |
shining | -0.007 |
ie | -0.006 |
Token | is |
Token ID | 271 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
ling | +0.157 |
around | +0.141 |
shining | +0.138 |
led | +0.133 |
up | +0.130 |
Neg logit contributions | |
roller | -0.131 |
salon | -0.123 |
ara | -0.116 |
heaven | -0.111 |
atters | -0.110 |
Token | ies |
Token ID | 444 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ling | +0.101 |
around | +0.089 |
shining | +0.084 |
up | +0.074 |
spear | +0.072 |
Neg logit contributions | |
roller | -0.258 |
ara | -0.252 |
salon | -0.251 |
atters | -0.235 |
post | -0.234 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
ling | +0.120 |
around | +0.102 |
shining | +0.099 |
led | +0.098 |
up | +0.091 |
Neg logit contributions | |
roller | -0.163 |
salon | -0.157 |
ara | -0.149 |
heaven | -0.144 |
clinic | -0.144 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ling | +0.013 |
around | +0.011 |
led | +0.011 |
shining | +0.011 |
up | +0.010 |
Neg logit contributions | |
roller | -0.015 |
salon | -0.015 |
ara | -0.015 |
heaven | -0.014 |
pitcher | -0.014 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
roller | +0.120 |
salon | +0.115 |
ara | +0.114 |
pitcher | +0.108 |
post | +0.106 |
Neg logit contributions | |
ling | -0.064 |
around | -0.053 |
led | -0.048 |
shining | -0.047 |
him | -0.044 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
ling | +0.505 |
around | +0.432 |
shining | +0.418 |
led | +0.393 |
up | +0.382 |
Neg logit contributions | |
roller | -0.750 |
salon | -0.718 |
ara | -0.688 |
atters | -0.665 |
pitcher | -0.664 |
Token | , |
Token ID | 11 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ling | +0.269 |
around | +0.227 |
led | +0.221 |
shining | +0.219 |
him | +0.206 |
Neg logit contributions | |
roller | -0.343 |
salon | -0.329 |
ara | -0.316 |
pitcher | -0.306 |
heaven | -0.306 |
Token | and |
Token ID | 290 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ling | +0.018 |
around | +0.016 |
led | +0.015 |
shining | +0.015 |
up | +0.014 |
Neg logit contributions | |
roller | -0.020 |
salon | -0.020 |
ara | -0.019 |
heaven | -0.019 |
pitcher | -0.019 |
Token | tul |
Token ID | 48373 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ling | +0.018 |
led | +0.015 |
around | +0.014 |
shining | +0.014 |
ie | +0.013 |
Neg logit contributions | |
salon | -0.022 |
roller | -0.022 |
heaven | -0.022 |
pitcher | -0.021 |
ara | -0.021 |
Token | ips |
Token ID | 2419 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
ling | +0.129 |
around | +0.112 |
shining | +0.109 |
led | +0.109 |
ie | +0.105 |
Neg logit contributions | |
roller | -0.142 |
salon | -0.128 |
post | -0.121 |
heaven | -0.121 |
clinic | -0.119 |
Token | El |
Token ID | 2574 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
roller | +0.066 |
salon | +0.062 |
atters | +0.058 |
clinic | +0.058 |
pitcher | +0.057 |
Neg logit contributions | |
around | -0.054 |
ling | -0.052 |
in | -0.050 |
shining | -0.050 |
him | -0.050 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.167 |
shining | +0.166 |
around | +0.153 |
him | +0.147 |
spear | +0.143 |
Neg logit contributions | |
ara | -0.164 |
salon | -0.157 |
roller | -0.150 |
heaven | -0.142 |
clinic | -0.138 |
Token | ie |
Token ID | 494 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
shining | +0.379 |
Barry | +0.326 |
ging | +0.323 |
Joey | +0.320 |
ling | +0.304 |
Neg logit contributions | |
ara | -0.804 |
salon | -0.772 |
S | -0.736 |
roller | -0.705 |
ress | -0.704 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
ling | +0.282 |
shining | +0.242 |
led | +0.239 |
around | +0.238 |
up | +0.216 |
Neg logit contributions | |
roller | -0.335 |
salon | -0.318 |
ara | -0.302 |
heaven | -0.301 |
clinic | -0.296 |
Token | El |
Token ID | 2574 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ling | +0.034 |
around | +0.031 |
shining | +0.030 |
led | +0.029 |
up | +0.029 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.017 |
ara | -0.016 |
heaven | -0.015 |
atters | -0.015 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.177 |
shining | +0.162 |
around | +0.157 |
him | +0.148 |
up | +0.145 |
Neg logit contributions | |
roller | -0.160 |
salon | -0.159 |
ara | -0.157 |
atters | -0.142 |
pitcher | -0.142 |
Token | ie |
Token ID | 494 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
shining | +0.506 |
ging | +0.460 |
ling | +0.437 |
Barry | +0.422 |
nam | +0.421 |
Neg logit contributions | |
ara | -0.695 |
salon | -0.614 |
S | -0.592 |
ase | -0.590 |
Anna | -0.586 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ling | +0.165 |
around | +0.125 |
shining | +0.123 |
led | +0.112 |
up | +0.102 |
Neg logit contributions | |
roller | -0.458 |
salon | -0.441 |
ara | -0.426 |
heaven | -0.416 |
atters | -0.415 |
Token | to |
Token ID | 284 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
ling | +0.117 |
led | +0.101 |
around | +0.090 |
atop | +0.086 |
ging | +0.086 |
Neg logit contributions | |
salon | -0.123 |
roller | -0.119 |
heaven | -0.113 |
clinic | -0.107 |
pitcher | -0.107 |
Token | think |
Token ID | 892 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
roller | +0.008 |
salon | +0.007 |
heaven | +0.007 |
ara | +0.007 |
pitcher | +0.007 |
Neg logit contributions | |
ling | -0.008 |
around | -0.007 |
led | -0.007 |
shining | -0.007 |
up | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ling | +0.185 |
led | +0.157 |
around | +0.148 |
shining | +0.147 |
ging | +0.142 |
Neg logit contributions | |
roller | -0.172 |
salon | -0.172 |
post | -0.156 |
ress | -0.152 |
heaven | -0.152 |
Token | think |
Token ID | 892 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
ling | +0.029 |
led | +0.025 |
shining | +0.024 |
around | +0.023 |
ging | +0.023 |
Neg logit contributions | |
salon | -0.023 |
roller | -0.023 |
heaven | -0.022 |
clinic | -0.021 |
ara | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
ling | +0.167 |
led | +0.138 |
shining | +0.129 |
uses | +0.129 |
spear | +0.128 |
Neg logit contributions | |
roller | -0.190 |
salon | -0.188 |
post | -0.179 |
ress | -0.170 |
ara | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ling | +0.030 |
led | +0.026 |
shining | +0.026 |
around | +0.026 |
ie | +0.024 |
Neg logit contributions | |
roller | -0.023 |
salon | -0.021 |
ara | -0.020 |
clinic | -0.019 |
post | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ling | +0.014 |
led | +0.013 |
shining | +0.012 |
itive | +0.012 |
around | +0.012 |
Neg logit contributions | |
roller | -0.007 |
ara | -0.007 |
salon | -0.006 |
post | -0.006 |
S | -0.006 |
Token | El |
Token ID | 9527 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
ling | +0.013 |
led | +0.012 |
shining | +0.011 |
around | +0.011 |
up | +0.011 |
Neg logit contributions | |
roller | -0.007 |
salon | -0.007 |
ara | -0.006 |
post | -0.006 |
clinic | -0.006 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.028 |
shining | +0.025 |
around | +0.025 |
him | +0.024 |
led | +0.023 |
Neg logit contributions | |
roller | -0.028 |
salon | -0.028 |
ara | -0.027 |
ress | -0.025 |
atters | -0.025 |
Token | ie |
Token ID | 494 |
Feature activation | -6.31e+00 |
Pos logit contributions | |
shining | +0.318 |
nam | +0.255 |
ging | +0.252 |
ling | +0.246 |
Barry | +0.244 |
Neg logit contributions | |
ara | -0.884 |
salon | -0.830 |
Anna | -0.782 |
ue | -0.759 |
lor | -0.758 |
Token | would |
Token ID | 561 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
ling | +0.272 |
shining | +0.241 |
around | +0.225 |
led | +0.221 |
ging | +0.211 |
Neg logit contributions | |
salon | -0.336 |
roller | -0.335 |
ara | -0.320 |
clinic | -0.309 |
heaven | -0.307 |
Token | think |
Token ID | 892 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
ling | +0.146 |
led | +0.129 |
shining | +0.123 |
around | +0.122 |
ie | +0.114 |
Neg logit contributions | |
salon | -0.124 |
roller | -0.124 |
heaven | -0.111 |
clinic | -0.110 |
ara | -0.108 |
Token | about |
Token ID | 546 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ling | +0.176 |
led | +0.149 |
shining | +0.141 |
ging | +0.141 |
spear | +0.134 |
Neg logit contributions | |
salon | -0.184 |
roller | -0.173 |
heaven | -0.161 |
ress | -0.157 |
post | -0.157 |
Token | all |
Token ID | 477 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ling | +0.099 |
led | +0.091 |
ging | +0.072 |
bled | +0.071 |
around | +0.071 |
Neg logit contributions | |
salon | -0.126 |
heaven | -0.124 |
clinic | -0.114 |
jail | -0.114 |
roller | -0.113 |
Token | so |
Token ID | 523 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
ling | +0.001 |
led | +0.001 |
around | +0.001 |
uses | +0.001 |
ie | +0.001 |
Neg logit contributions | |
salon | -0.002 |
roller | -0.002 |
heaven | -0.002 |
pitcher | -0.002 |
clinic | -0.002 |
Token | excited |
Token ID | 6568 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ling | +0.018 |
around | +0.015 |
led | +0.014 |
shining | +0.014 |
ie | +0.013 |
Neg logit contributions | |
roller | -0.025 |
salon | -0.025 |
ara | -0.023 |
pitcher | -0.023 |
atters | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
ling | +0.029 |
led | +0.023 |
shining | +0.023 |
spear | +0.023 |
ging | +0.022 |
Neg logit contributions | |
roller | -0.028 |
salon | -0.027 |
ara | -0.026 |
post | -0.026 |
heaven | -0.026 |
Token | start |
Token ID | 923 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
roller | +0.014 |
salon | +0.013 |
atters | +0.012 |
ara | +0.012 |
pitcher | +0.012 |
Neg logit contributions | |
ling | -0.018 |
led | -0.016 |
shining | -0.015 |
around | -0.015 |
ging | -0.014 |
Token | do |
Token ID | 466 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
roller | +0.298 |
salon | +0.288 |
pitcher | +0.263 |
heaven | +0.263 |
stand | +0.257 |
Neg logit contributions | |
ling | -0.270 |
led | -0.232 |
itive | -0.207 |
around | -0.203 |
ie | -0.195 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.052 |
around | +0.043 |
shining | +0.042 |
led | +0.041 |
up | +0.038 |
Neg logit contributions | |
roller | -0.088 |
salon | -0.085 |
ara | -0.080 |
heaven | -0.079 |
atters | -0.078 |
Token | ling |
Token ID | 1359 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
shining | +0.550 |
ling | +0.543 |
Joey | +0.496 |
around | +0.491 |
Barry | +0.475 |
Neg logit contributions | |
salon | -0.627 |
ara | -0.604 |
roller | -0.576 |
ress | -0.574 |
atters | -0.561 |
Token | with |
Token ID | 351 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ling | +0.390 |
led | +0.320 |
shining | +0.320 |
around | +0.293 |
ie | +0.285 |
Neg logit contributions | |
roller | -0.525 |
salon | -0.520 |
heaven | -0.494 |
post | -0.478 |
clinic | -0.470 |
Token | it |
Token ID | 340 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
salon | +0.060 |
roller | +0.060 |
heaven | +0.057 |
ara | +0.056 |
pitcher | +0.054 |
Neg logit contributions | |
ling | -0.062 |
led | -0.052 |
shining | -0.046 |
around | -0.045 |
itive | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
ling | +0.014 |
shining | +0.012 |
led | +0.012 |
around | +0.011 |
him | +0.011 |
Neg logit contributions | |
roller | -0.017 |
salon | -0.017 |
ara | -0.015 |
post | -0.015 |
heaven | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
ling | +0.020 |
around | +0.019 |
shining | +0.018 |
up | +0.017 |
him | +0.017 |
Neg logit contributions | |
roller | -0.021 |
salon | -0.020 |
heaven | -0.018 |
pitcher | -0.018 |
ara | -0.018 |
Token | back |
Token ID | 736 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
ling | +0.017 |
led | +0.015 |
shining | +0.014 |
around | +0.014 |
bee | +0.013 |
Neg logit contributions | |
roller | -0.027 |
salon | -0.024 |
heaven | -0.024 |
ara | -0.024 |
clinic | -0.024 |
Token | with |
Token ID | 351 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
roller | +0.156 |
salon | +0.149 |
ara | +0.141 |
atters | +0.139 |
post | +0.138 |
Neg logit contributions | |
ling | -0.096 |
around | -0.084 |
shining | -0.081 |
up | -0.075 |
led | -0.074 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
roller | +0.079 |
salon | +0.075 |
heaven | +0.073 |
ara | +0.072 |
pitcher | +0.072 |
Neg logit contributions | |
ling | -0.047 |
around | -0.038 |
shining | -0.036 |
led | -0.036 |
ie | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
roller | +0.005 |
salon | +0.005 |
ara | +0.005 |
atters | +0.005 |
heaven | +0.004 |
Neg logit contributions | |
ling | -0.005 |
around | -0.004 |
shining | -0.004 |
led | -0.004 |
up | -0.004 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
heaven | +0.065 |
roller | +0.065 |
salon | +0.063 |
pitcher | +0.062 |
vet | +0.061 |
Neg logit contributions | |
ling | -0.069 |
around | -0.059 |
led | -0.057 |
shining | -0.055 |
ging | -0.054 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
roller | +0.112 |
salon | +0.105 |
ara | +0.104 |
pitcher | +0.102 |
post | +0.098 |
Neg logit contributions | |
ling | -0.062 |
around | -0.053 |
shining | -0.047 |
spear | -0.047 |
led | -0.047 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
ling | +0.532 |
around | +0.467 |
shining | +0.454 |
up | +0.420 |
led | +0.412 |
Neg logit contributions | |
roller | -0.702 |
salon | -0.661 |
ara | -0.638 |
pitcher | -0.623 |
atters | -0.619 |
Token | to |
Token ID | 284 |
Feature activation | +7.56e-05 |
Pos logit contributions | |
ling | +0.252 |
around | +0.210 |
shining | +0.204 |
led | +0.202 |
him | +0.194 |
Neg logit contributions | |
roller | -0.316 |
salon | -0.299 |
pitcher | -0.285 |
heaven | -0.285 |
ara | -0.282 |
Token | fill |
Token ID | 6070 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
roller | +0.000 |
salon | +0.000 |
heaven | +0.000 |
ara | +0.000 |
clinic | +0.000 |
Neg logit contributions | |
ling | -0.000 |
around | -0.000 |
led | -0.000 |
shining | -0.000 |
up | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
roller | +0.123 |
salon | +0.117 |
ara | +0.116 |
heaven | +0.116 |
pitcher | +0.113 |
Neg logit contributions | |
ling | -0.073 |
shining | -0.060 |
around | -0.058 |
led | -0.057 |
itive | -0.052 |
Token | prince |
Token ID | 19716 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
ling | +0.056 |
around | +0.050 |
shining | +0.048 |
led | +0.048 |
him | +0.046 |
Neg logit contributions | |
roller | -0.050 |
salon | -0.047 |
ara | -0.045 |
pitcher | -0.043 |
heaven | -0.043 |
Token | other |
Token ID | 584 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ling | +0.211 |
shining | +0.175 |
around | +0.173 |
led | +0.171 |
up | +0.150 |
Neg logit contributions | |
roller | -0.356 |
salon | -0.345 |
ara | -0.333 |
heaven | -0.327 |
clinic | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
roller | +0.068 |
salon | +0.064 |
heaven | +0.061 |
ara | +0.060 |
post | +0.059 |
Neg logit contributions | |
ling | -0.050 |
shining | -0.044 |
led | -0.042 |
around | -0.041 |
ie | -0.039 |
Token | Jim |
Token ID | 5395 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
around | +0.015 |
Joey | +0.015 |
Peter | +0.015 |
him | +0.014 |
Barry | +0.014 |
Neg logit contributions | |
salon | -0.021 |
roller | -0.019 |
clinic | -0.018 |
atters | -0.018 |
post | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
ling | +0.052 |
around | +0.044 |
shining | +0.043 |
led | +0.041 |
up | +0.039 |
Neg logit contributions | |
roller | -0.080 |
salon | -0.077 |
ara | -0.073 |
heaven | -0.071 |
atters | -0.071 |
Token | J |
Token ID | 449 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
ling | +0.032 |
shining | +0.026 |
led | +0.026 |
around | +0.025 |
up | +0.023 |
Neg logit contributions | |
roller | -0.040 |
salon | -0.039 |
ara | -0.037 |
heaven | -0.036 |
ress | -0.036 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.176 |
around | +0.157 |
shining | +0.157 |
led | +0.147 |
up | +0.144 |
Neg logit contributions | |
roller | -0.167 |
salon | -0.157 |
ara | -0.150 |
atters | -0.143 |
post | -0.141 |
Token | ie |
Token ID | 494 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
ling | +0.463 |
shining | +0.451 |
around | +0.414 |
up | +0.402 |
him | +0.355 |
Neg logit contributions | |
roller | -0.705 |
salon | -0.696 |
ara | -0.681 |
atters | -0.635 |
post | -0.634 |
Token | learned |
Token ID | 4499 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
ling | +0.233 |
around | +0.203 |
shining | +0.190 |
led | +0.183 |
ie | +0.174 |
Neg logit contributions | |
roller | -0.403 |
salon | -0.380 |
ara | -0.363 |
heaven | -0.357 |
post | -0.357 |
Token | that |
Token ID | 326 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
roller | +0.208 |
salon | +0.198 |
ara | +0.190 |
atters | +0.185 |
pitcher | +0.185 |
Neg logit contributions | |
ling | -0.122 |
around | -0.104 |
shining | -0.101 |
led | -0.094 |
up | -0.092 |
Token | working |
Token ID | 1762 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
ling | +0.048 |
led | +0.042 |
around | +0.037 |
ie | +0.036 |
shining | +0.036 |
Neg logit contributions | |
salon | -0.059 |
roller | -0.059 |
heaven | -0.056 |
vet | -0.054 |
ara | -0.053 |
Token | together |
Token ID | 1978 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ling | +0.209 |
shining | +0.174 |
around | +0.167 |
led | +0.164 |
ie | +0.162 |
Neg logit contributions | |
roller | -0.286 |
salon | -0.269 |
ara | -0.259 |
post | -0.257 |
atters | -0.256 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ling | +0.021 |
around | +0.020 |
him | +0.019 |
Joey | +0.018 |
up | +0.018 |
Neg logit contributions | |
salon | -0.030 |
roller | -0.029 |
pitcher | -0.026 |
ara | -0.026 |
heaven | -0.026 |
Token | Sam |
Token ID | 16305 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
ling | +0.016 |
around | +0.014 |
shining | +0.014 |
led | +0.013 |
ie | +0.013 |
Neg logit contributions | |
roller | -0.014 |
salon | -0.012 |
ara | -0.012 |
post | -0.011 |
heaven | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
ling | +0.033 |
around | +0.027 |
shining | +0.027 |
led | +0.025 |
up | +0.023 |
Neg logit contributions | |
roller | -0.060 |
salon | -0.057 |
ara | -0.056 |
heaven | -0.054 |
atters | -0.053 |
Token | picking |
Token ID | 10868 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
roller | +0.000 |
salon | +0.000 |
heaven | +0.000 |
clinic | +0.000 |
pitcher | +0.000 |
Neg logit contributions | |
ling | -0.000 |
led | -0.000 |
ie | -0.000 |
shining | -0.000 |
around | -0.000 |
Token | wild |
Token ID | 4295 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ling | +0.104 |
led | +0.085 |
itive | +0.083 |
bee | +0.080 |
couldn | +0.077 |
Neg logit contributions | |
roller | -0.164 |
ara | -0.158 |
pitcher | -0.156 |
salon | -0.151 |
S | -0.150 |
Token | fl |
Token ID | 2704 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.044 |
led | +0.034 |
shining | +0.034 |
ging | +0.033 |
bled | +0.033 |
Neg logit contributions | |
roller | -0.050 |
salon | -0.048 |
ara | -0.048 |
heaven | -0.046 |
jail | -0.045 |
Token | owers |
Token ID | 3618 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
ling | +0.503 |
around | +0.431 |
shining | +0.418 |
led | +0.395 |
up | +0.379 |
Neg logit contributions | |
roller | -0.762 |
salon | -0.726 |
ara | -0.690 |
pitcher | -0.672 |
atters | -0.670 |
Token | in |
Token ID | 287 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ling | +0.245 |
led | +0.223 |
bee | +0.204 |
itive | +0.202 |
shining | +0.189 |
Neg logit contributions | |
roller | -0.312 |
pitcher | -0.296 |
salon | -0.294 |
heaven | -0.279 |
clinic | -0.278 |
Token | the |
Token ID | 262 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ling | +0.059 |
around | +0.047 |
shining | +0.045 |
led | +0.042 |
up | +0.038 |
Neg logit contributions | |
roller | -0.150 |
salon | -0.144 |
ara | -0.138 |
heaven | -0.136 |
pitcher | -0.135 |
Token | me |
Token ID | 502 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
ling | +0.035 |
shining | +0.033 |
around | +0.033 |
up | +0.031 |
in | +0.029 |
Neg logit contributions | |
roller | -0.027 |
salon | -0.025 |
atters | -0.024 |
ara | -0.023 |
post | -0.023 |
Token | adow |
Token ID | 4584 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
roller | +0.042 |
salon | +0.039 |
ara | +0.037 |
heaven | +0.035 |
atters | +0.035 |
Neg logit contributions | |
ling | -0.049 |
around | -0.044 |
shining | -0.043 |
led | -0.042 |
up | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ling | +0.004 |
led | +0.004 |
around | +0.004 |
uses | +0.003 |
ie | +0.003 |
Neg logit contributions | |
roller | -0.005 |
heaven | -0.005 |
ara | -0.005 |
salon | -0.005 |
pitcher | -0.005 |
Token | gifted |
Token ID | 22527 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ling | +0.010 |
around | +0.009 |
led | +0.009 |
shining | +0.008 |
up | +0.008 |
Neg logit contributions | |
roller | -0.017 |
salon | -0.016 |
ara | -0.016 |
pitcher | -0.015 |
clinic | -0.015 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ling | +0.012 |
around | +0.010 |
shining | +0.010 |
led | +0.010 |
up | +0.009 |
Neg logit contributions | |
roller | -0.015 |
salon | -0.015 |
ara | -0.014 |
heaven | -0.014 |
pitcher | -0.013 |
Token | called |
Token ID | 1444 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
roller | +0.111 |
salon | +0.103 |
lor | +0.094 |
atters | +0.094 |
pitcher | +0.094 |
Neg logit contributions | |
ling | -0.105 |
around | -0.101 |
in | -0.094 |
shining | -0.093 |
ie | -0.091 |
Token | El |
Token ID | 2574 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
roller | +0.066 |
salon | +0.062 |
atters | +0.058 |
clinic | +0.058 |
pitcher | +0.057 |
Neg logit contributions | |
around | -0.054 |
ling | -0.052 |
in | -0.050 |
shining | -0.050 |
him | -0.050 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.167 |
shining | +0.166 |
around | +0.153 |
him | +0.147 |
spear | +0.143 |
Neg logit contributions | |
ara | -0.164 |
salon | -0.157 |
roller | -0.150 |
heaven | -0.142 |
clinic | -0.138 |
Token | ie |
Token ID | 494 |
Feature activation | -6.27e+00 |
Pos logit contributions | |
shining | +0.379 |
Barry | +0.326 |
ging | +0.323 |
Joey | +0.320 |
ling | +0.304 |
Neg logit contributions | |
ara | -0.804 |
salon | -0.772 |
S | -0.736 |
roller | -0.705 |
ress | -0.704 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
ling | +0.282 |
shining | +0.242 |
led | +0.239 |
around | +0.238 |
up | +0.216 |
Neg logit contributions | |
roller | -0.335 |
salon | -0.318 |
ara | -0.302 |
heaven | -0.301 |
clinic | -0.296 |
Token | El |
Token ID | 2574 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ling | +0.034 |
around | +0.031 |
shining | +0.030 |
led | +0.029 |
up | +0.029 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.017 |
ara | -0.016 |
heaven | -0.015 |
atters | -0.015 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.177 |
shining | +0.162 |
around | +0.157 |
him | +0.148 |
up | +0.145 |
Neg logit contributions | |
roller | -0.160 |
salon | -0.159 |
ara | -0.157 |
atters | -0.142 |
pitcher | -0.142 |
Token | ie |
Token ID | 494 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
shining | +0.506 |
ging | +0.460 |
ling | +0.437 |
Barry | +0.422 |
nam | +0.421 |
Neg logit contributions | |
ara | -0.695 |
salon | -0.614 |
S | -0.592 |
ase | -0.590 |
Anna | -0.586 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
ling | +0.027 |
around | +0.024 |
shining | +0.024 |
led | +0.023 |
up | +0.022 |
Neg logit contributions | |
roller | -0.023 |
salon | -0.021 |
ara | -0.020 |
atters | -0.019 |
clinic | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ling | +0.010 |
led | +0.009 |
shining | +0.009 |
around | +0.008 |
itive | +0.008 |
Neg logit contributions | |
roller | -0.006 |
ara | -0.005 |
salon | -0.005 |
post | -0.005 |
atters | -0.005 |
Token | But |
Token ID | 1537 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
ling | +0.009 |
led | +0.008 |
around | +0.008 |
shining | +0.008 |
up | +0.008 |
Neg logit contributions | |
roller | -0.006 |
salon | -0.006 |
ara | -0.005 |
post | -0.005 |
clinic | -0.005 |
Token | what |
Token ID | 644 |
Feature activation | -7.35e+00 |
Pos logit contributions | |
salon | +0.186 |
roller | +0.170 |
ara | +0.168 |
heaven | +0.161 |
clinic | +0.160 |
Neg logit contributions | |
ling | -0.152 |
led | -0.124 |
around | -0.116 |
spear | -0.115 |
shining | -0.115 |
Token | El |
Token ID | 2574 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
ling | +0.332 |
ging | +0.283 |
shining | +0.272 |
led | +0.268 |
uses | +0.255 |
Neg logit contributions | |
salon | -0.384 |
ara | -0.372 |
roller | -0.368 |
ress | -0.343 |
heaven | -0.343 |
Token | od |
Token ID | 375 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
ling | +0.175 |
shining | +0.161 |
around | +0.157 |
him | +0.150 |
up | +0.144 |
Neg logit contributions | |
salon | -0.163 |
roller | -0.161 |
ara | -0.161 |
ress | -0.147 |
pitcher | -0.146 |
Token | ie |
Token ID | 494 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
shining | +0.368 |
nam | +0.313 |
ging | +0.288 |
ling | +0.288 |
Barry | +0.278 |
Neg logit contributions | |
ara | -0.824 |
salon | -0.768 |
ase | -0.709 |
Anna | -0.705 |
S | -0.701 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
ling | +0.249 |
shining | +0.213 |
around | +0.211 |
led | +0.197 |
up | +0.187 |
Neg logit contributions | |
roller | -0.382 |
salon | -0.372 |
ara | -0.357 |
heaven | -0.346 |
clinic | -0.343 |
Token | to |
Token ID | 284 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ling | +0.112 |
led | +0.095 |
around | +0.086 |
ging | +0.083 |
shining | +0.083 |
Neg logit contributions | |
salon | -0.146 |
roller | -0.140 |
heaven | -0.134 |
ara | -0.129 |
clinic | -0.129 |
Token | think |
Token ID | 892 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
roller | +0.007 |
salon | +0.007 |
ara | +0.006 |
heaven | +0.006 |
clinic | +0.006 |
Neg logit contributions | |
ling | -0.007 |
around | -0.006 |
shining | -0.006 |
led | -0.006 |
up | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
ling | +0.180 |
led | +0.154 |
shining | +0.147 |
ging | +0.144 |
around | +0.141 |
Neg logit contributions | |
salon | -0.174 |
roller | -0.170 |
post | -0.156 |
heaven | -0.156 |
clinic | -0.153 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ling | +0.254 |
shining | +0.223 |
around | +0.223 |
led | +0.215 |
up | +0.202 |
Neg logit contributions | |
roller | -0.243 |
salon | -0.233 |
ara | -0.220 |
heaven | -0.215 |
clinic | -0.211 |
Token | And |
Token ID | 843 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
roller | +0.137 |
salon | +0.123 |
ara | +0.116 |
heaven | +0.116 |
atters | +0.115 |
Neg logit contributions | |
ling | -0.186 |
led | -0.160 |
shining | -0.160 |
around | -0.159 |
ie | -0.149 |
Token | they |
Token ID | 484 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
roller | +0.108 |
salon | +0.103 |
ress | +0.097 |
heaven | +0.097 |
ara | +0.095 |
Neg logit contributions | |
ling | -0.077 |
shining | -0.062 |
led | -0.061 |
around | -0.061 |
ie | -0.055 |
Token | hugged |
Token ID | 41130 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
roller | +0.038 |
salon | +0.037 |
ara | +0.036 |
heaven | +0.035 |
atters | +0.034 |
Neg logit contributions | |
ling | -0.018 |
shining | -0.014 |
around | -0.014 |
led | -0.013 |
up | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
roller | +0.049 |
heaven | +0.049 |
ara | +0.046 |
post | +0.046 |
jail | +0.046 |
Neg logit contributions | |
ling | -0.035 |
shining | -0.030 |
led | -0.029 |
atop | -0.025 |
uses | -0.025 |
Token | filled |
Token ID | 5901 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
ling | +0.010 |
around | +0.009 |
shining | +0.009 |
led | +0.008 |
up | +0.008 |
Neg logit contributions | |
roller | -0.014 |
salon | -0.013 |
ara | -0.013 |
heaven | -0.012 |
atters | -0.012 |
Token | each |
Token ID | 1123 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
heaven | +0.252 |
roller | +0.251 |
jail | +0.238 |
ress | +0.234 |
ara | +0.234 |
Neg logit contributions | |
ling | -0.156 |
itive | -0.134 |
bee | -0.133 |
shining | -0.131 |
led | -0.120 |
Token | other |
Token ID | 584 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ling | +0.200 |
around | +0.169 |
shining | +0.169 |
led | +0.157 |
him | +0.147 |
Neg logit contributions | |
roller | -0.356 |
salon | -0.341 |
ara | -0.331 |
heaven | -0.323 |
pitcher | -0.322 |
Token | with |
Token ID | 351 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
roller | +0.073 |
salon | +0.068 |
ara | +0.065 |
heaven | +0.064 |
atters | +0.063 |
Neg logit contributions | |
ling | -0.051 |
shining | -0.044 |
around | -0.044 |
led | -0.042 |
him | -0.040 |
Token | love |
Token ID | 1842 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
roller | +0.062 |
heaven | +0.059 |
salon | +0.059 |
ara | +0.055 |
pitcher | +0.055 |
Neg logit contributions | |
ling | -0.069 |
around | -0.058 |
led | -0.057 |
shining | -0.057 |
ie | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ling | +0.046 |
around | +0.038 |
shining | +0.038 |
led | +0.037 |
up | +0.035 |
Neg logit contributions | |
roller | -0.063 |
salon | -0.061 |
heaven | -0.058 |
ara | -0.058 |
post | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
roller | +0.044 |
salon | +0.042 |
heaven | +0.040 |
post | +0.039 |
ara | +0.039 |
Neg logit contributions | |
ling | -0.033 |
led | -0.027 |
around | -0.027 |
shining | -0.026 |
ie | -0.026 |
Token | great |
Token ID | 1049 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ling | +0.002 |
around | +0.001 |
shining | +0.001 |
led | +0.001 |
up | +0.001 |
Neg logit contributions | |
roller | -0.002 |
salon | -0.002 |
ara | -0.002 |
heaven | -0.002 |
pitcher | -0.002 |
Token | job |
Token ID | 1693 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
ling | +0.022 |
around | +0.020 |
shining | +0.020 |
led | +0.019 |
up | +0.018 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.018 |
ara | -0.017 |
atters | -0.016 |
heaven | -0.016 |
Token | cleaning |
Token ID | 12724 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
roller | +0.186 |
salon | +0.176 |
ara | +0.171 |
atters | +0.166 |
pitcher | +0.164 |
Neg logit contributions | |
ling | -0.111 |
around | -0.097 |
shining | -0.093 |
led | -0.085 |
up | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
roller | +0.046 |
salon | +0.044 |
ara | +0.042 |
heaven | +0.041 |
post | +0.041 |
Neg logit contributions | |
ling | -0.023 |
shining | -0.018 |
led | -0.017 |
around | -0.017 |
bee | -0.016 |
Token | garage |
Token ID | 15591 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
ling | +0.017 |
around | +0.016 |
shining | +0.015 |
up | +0.015 |
led | +0.014 |
Neg logit contributions | |
roller | -0.012 |
salon | -0.011 |
ara | -0.011 |
atters | -0.010 |
heaven | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
roller | +0.282 |
ara | +0.271 |
salon | +0.265 |
atters | +0.257 |
heaven | +0.255 |
Neg logit contributions | |
ling | -0.151 |
around | -0.141 |
shining | -0.126 |
up | -0.123 |
in | -0.118 |
Token | Tim |
Token ID | 5045 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
around | +0.010 |
ling | +0.009 |
him | +0.009 |
Joey | +0.009 |
shining | +0.009 |
Neg logit contributions | |
roller | -0.014 |
salon | -0.014 |
lor | -0.013 |
clinic | -0.013 |
heaven | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
ling | +0.041 |
shining | +0.038 |
around | +0.037 |
led | +0.036 |
atop | +0.035 |
Neg logit contributions | |
roller | -0.052 |
ara | -0.051 |
salon | -0.050 |
ress | -0.047 |
atters | -0.045 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
ling | +0.155 |
around | +0.132 |
shining | +0.130 |
led | +0.120 |
up | +0.114 |
Neg logit contributions | |
roller | -0.271 |
salon | -0.259 |
ara | -0.248 |
pitcher | -0.240 |
atters | -0.238 |
Token | proud |
Token ID | 6613 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
ling | +0.099 |
shining | +0.082 |
around | +0.081 |
led | +0.079 |
ie | +0.077 |
Neg logit contributions | |
roller | -0.141 |
salon | -0.134 |
heaven | -0.129 |
pitcher | -0.127 |
ara | -0.127 |
Token | you |
Token ID | 345 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ling | +0.031 |
around | +0.027 |
shining | +0.026 |
ie | +0.024 |
him | +0.024 |
Neg logit contributions | |
roller | -0.053 |
salon | -0.051 |
clinic | -0.047 |
pitcher | -0.047 |
atters | -0.047 |
Token | can |
Token ID | 460 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
ling | +0.014 |
shining | +0.012 |
around | +0.012 |
led | +0.011 |
up | +0.011 |
Neg logit contributions | |
roller | -0.014 |
salon | -0.013 |
ara | -0.013 |
atters | -0.012 |
pitcher | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
roller | +0.037 |
salon | +0.035 |
ara | +0.033 |
heaven | +0.032 |
clinic | +0.032 |
Neg logit contributions | |
ling | -0.026 |
around | -0.023 |
shining | -0.022 |
led | -0.021 |
up | -0.020 |
Token | We |
Token ID | 775 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
around | +0.006 |
him | +0.006 |
ling | +0.006 |
up | +0.005 |
Barry | +0.005 |
Neg logit contributions | |
roller | -0.006 |
salon | -0.006 |
ara | -0.005 |
pitcher | -0.005 |
heaven | -0.005 |
Token | can |
Token ID | 460 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
roller | +0.072 |
salon | +0.068 |
ara | +0.064 |
atters | +0.062 |
heaven | +0.062 |
Neg logit contributions | |
ling | -0.067 |
around | -0.058 |
shining | -0.058 |
led | -0.056 |
up | -0.053 |
Token | start |
Token ID | 923 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
roller | +0.034 |
salon | +0.033 |
ara | +0.031 |
heaven | +0.030 |
atters | +0.030 |
Neg logit contributions | |
ling | -0.028 |
around | -0.025 |
shining | -0.024 |
led | -0.023 |
up | -0.022 |
Token | by |
Token ID | 416 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
roller | +0.327 |
salon | +0.316 |
heaven | +0.302 |
ara | +0.294 |
atters | +0.289 |
Neg logit contributions | |
ling | -0.251 |
led | -0.209 |
around | -0.197 |
shining | -0.189 |
ie | -0.187 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ling | +0.031 |
around | +0.026 |
led | +0.025 |
shining | +0.025 |
ie | +0.023 |
Neg logit contributions | |
roller | -0.048 |
salon | -0.046 |
ara | -0.043 |
heaven | -0.043 |
atters | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
ling | +0.083 |
bee | +0.070 |
led | +0.067 |
itive | +0.065 |
ie | +0.064 |
Neg logit contributions | |
salon | -0.110 |
roller | -0.109 |
heaven | -0.105 |
pitcher | -0.101 |
ara | -0.099 |
Token | more |
Token ID | 517 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
up | +0.002 |
led | +0.002 |
Neg logit contributions | |
roller | -0.003 |
salon | -0.002 |
ara | -0.002 |
atters | -0.002 |
post | -0.002 |
Token | comfortable |
Token ID | 6792 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
roller | +0.231 |
salon | +0.218 |
ara | +0.204 |
heaven | +0.200 |
clinic | +0.198 |
Neg logit contributions | |
ling | -0.235 |
around | -0.206 |
shining | -0.205 |
led | -0.198 |
him | -0.188 |
Token | do |
Token ID | 466 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
roller | +0.003 |
salon | +0.003 |
post | +0.003 |
atters | +0.003 |
ara | +0.003 |
Neg logit contributions | |
ling | -0.004 |
around | -0.003 |
shining | -0.003 |
him | -0.003 |
up | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ling | +0.066 |
around | +0.060 |
shining | +0.058 |
led | +0.056 |
up | +0.055 |
Neg logit contributions | |
roller | -0.055 |
salon | -0.051 |
ara | -0.048 |
heaven | -0.046 |
atters | -0.046 |
Token | want |
Token ID | 765 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
ling | +0.010 |
around | +0.008 |
shining | +0.008 |
led | +0.008 |
up | +0.008 |
Neg logit contributions | |
roller | -0.011 |
salon | -0.010 |
ara | -0.009 |
heaven | -0.009 |
clinic | -0.009 |
Token | some |
Token ID | 617 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
ling | +0.129 |
around | +0.110 |
shining | +0.107 |
led | +0.103 |
up | +0.097 |
Neg logit contributions | |
roller | -0.175 |
salon | -0.167 |
ara | -0.158 |
heaven | -0.155 |
pitcher | -0.153 |
Token | of |
Token ID | 286 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
roller | +0.045 |
salon | +0.043 |
ara | +0.040 |
heaven | +0.039 |
atters | +0.038 |
Neg logit contributions | |
ling | -0.052 |
around | -0.046 |
shining | -0.046 |
led | -0.044 |
up | -0.043 |
Token | my |
Token ID | 616 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
roller | +0.081 |
salon | +0.074 |
ara | +0.070 |
atters | +0.068 |
post | +0.067 |
Neg logit contributions | |
ling | -0.087 |
around | -0.080 |
shining | -0.079 |
him | -0.076 |
up | -0.075 |
Token | snacks |
Token ID | 28487 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
roller | +0.169 |
salon | +0.164 |
pitcher | +0.159 |
clinic | +0.158 |
ara | +0.157 |
Neg logit contributions | |
ling | -0.254 |
led | -0.221 |
around | -0.217 |
shining | -0.210 |
ie | -0.207 |
Token | ? |
Token ID | 30 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
roller | +0.021 |
salon | +0.020 |
atters | +0.019 |
clinic | +0.019 |
ara | +0.019 |
Neg logit contributions | |
ling | -0.013 |
around | -0.012 |
in | -0.011 |
shining | -0.011 |
up | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
roller | +0.036 |
salon | +0.034 |
pitcher | +0.030 |
post | +0.029 |
ara | +0.029 |
Neg logit contributions | |
around | -0.034 |
him | -0.033 |
ling | -0.033 |
in | -0.032 |
shining | -0.030 |
Token | have |
Token ID | 423 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
roller | +0.104 |
salon | +0.096 |
ara | +0.089 |
post | +0.089 |
ress | +0.088 |
Neg logit contributions | |
ling | -0.076 |
around | -0.070 |
shining | -0.063 |
him | -0.062 |
in | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
roller | +0.103 |
salon | +0.096 |
atters | +0.092 |
ara | +0.092 |
ress | +0.091 |
Neg logit contributions | |
ling | -0.049 |
around | -0.044 |
shining | -0.042 |
him | -0.040 |
up | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
roller | +0.357 |
salon | +0.342 |
ara | +0.320 |
post | +0.316 |
pitcher | +0.312 |
Neg logit contributions | |
ling | -0.253 |
around | -0.213 |
shining | -0.208 |
led | -0.200 |
up | -0.191 |
Token | he |
Token ID | 339 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ling | +0.008 |
led | +0.007 |
ie | +0.007 |
bee | +0.007 |
mo | +0.006 |
Neg logit contributions | |
jail | -0.008 |
roller | -0.008 |
vet | -0.008 |
salon | -0.007 |
heaven | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ling | +0.145 |
shining | +0.128 |
around | +0.119 |
led | +0.116 |
ging | +0.114 |
Neg logit contributions | |
roller | -0.185 |
salon | -0.183 |
ara | -0.173 |
clinic | -0.163 |
pitcher | -0.161 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ling | +0.025 |
led | +0.020 |
ie | +0.019 |
shining | +0.019 |
ging | +0.019 |
Neg logit contributions | |
roller | -0.025 |
salon | -0.025 |
vet | -0.024 |
jail | -0.023 |
heaven | -0.023 |
Token | terrible |
Token ID | 7818 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ling | +0.007 |
led | +0.006 |
around | +0.006 |
ie | +0.006 |
shining | +0.006 |
Neg logit contributions | |
roller | -0.008 |
salon | -0.008 |
pitcher | -0.008 |
ara | -0.008 |
post | -0.007 |
Token | mess |
Token ID | 2085 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ling | +0.024 |
around | +0.021 |
led | +0.020 |
shining | +0.020 |
atop | +0.019 |
Neg logit contributions | |
roller | -0.026 |
salon | -0.025 |
ara | -0.024 |
pitcher | -0.023 |
post | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
roller | +0.250 |
salon | +0.242 |
post | +0.229 |
ara | +0.229 |
heaven | +0.224 |
Neg logit contributions | |
ling | -0.167 |
shining | -0.138 |
around | -0.137 |
led | -0.129 |
ie | -0.123 |
Token | His |
Token ID | 2399 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ling | +0.017 |
led | +0.015 |
around | +0.015 |
shining | +0.014 |
ie | +0.014 |
Neg logit contributions | |
roller | -0.016 |
salon | -0.014 |
ara | -0.013 |
post | -0.013 |
pitcher | -0.013 |
Token | mar |
Token ID | 1667 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
ling | +0.076 |
around | +0.065 |
led | +0.065 |
shining | +0.061 |
ie | +0.060 |
Neg logit contributions | |
roller | -0.085 |
salon | -0.077 |
pitcher | -0.074 |
ara | -0.074 |
jail | -0.070 |
Token | bles |
Token ID | 7689 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
ling | +0.108 |
shining | +0.097 |
around | +0.097 |
up | +0.086 |
him | +0.084 |
Neg logit contributions | |
roller | -0.253 |
salon | -0.238 |
pitcher | -0.231 |
ara | -0.227 |
atters | -0.226 |
Token | were |
Token ID | 547 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
ling | +0.333 |
shining | +0.296 |
around | +0.292 |
up | +0.275 |
Barry | +0.269 |
Neg logit contributions | |
roller | -0.427 |
salon | -0.419 |
pitcher | -0.388 |
ara | -0.375 |
atters | -0.371 |
Token | She |
Token ID | 1375 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
roller | +0.004 |
salon | +0.004 |
pitcher | +0.004 |
ress | +0.004 |
clinic | +0.004 |
Neg logit contributions | |
around | -0.004 |
ling | -0.004 |
him | -0.004 |
shining | -0.004 |
up | -0.004 |
Token | knows |
Token ID | 4206 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
roller | +0.126 |
salon | +0.117 |
ara | +0.109 |
pitcher | +0.106 |
post | +0.106 |
Neg logit contributions | |
ling | -0.133 |
around | -0.118 |
shining | -0.115 |
led | -0.112 |
up | -0.109 |
Token | she |
Token ID | 673 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ling | +0.100 |
led | +0.083 |
around | +0.077 |
shining | +0.075 |
atop | +0.072 |
Neg logit contributions | |
salon | -0.099 |
heaven | -0.091 |
roller | -0.090 |
ara | -0.089 |
vet | -0.087 |
Token | is |
Token ID | 318 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
roller | +0.012 |
salon | +0.012 |
ara | +0.012 |
heaven | +0.011 |
atters | +0.011 |
Neg logit contributions | |
ling | -0.020 |
shining | -0.018 |
around | -0.018 |
led | -0.017 |
ie | -0.016 |
Token | strong |
Token ID | 1913 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
heaven | +0.158 |
salon | +0.152 |
clinic | +0.144 |
roller | +0.143 |
vet | +0.142 |
Neg logit contributions | |
ling | -0.148 |
led | -0.127 |
ie | -0.124 |
shining | -0.118 |
around | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
ling | +0.044 |
around | +0.039 |
shining | +0.036 |
led | +0.034 |
up | +0.034 |
Neg logit contributions | |
roller | -0.069 |
salon | -0.065 |
ara | -0.061 |
pitcher | -0.060 |
atters | -0.060 |
Token | happy |
Token ID | 3772 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
ling | +0.003 |
ie | +0.002 |
shining | +0.002 |
around | +0.002 |
led | +0.002 |
Neg logit contributions | |
salon | -0.003 |
heaven | -0.003 |
roller | -0.003 |
post | -0.003 |
atters | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
ling | +0.028 |
shining | +0.023 |
around | +0.023 |
led | +0.022 |
up | +0.021 |
Neg logit contributions | |
roller | -0.037 |
salon | -0.035 |
ara | -0.033 |
heaven | -0.033 |
clinic | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
roller | +0.005 |
salon | +0.005 |
pitcher | +0.005 |
ction | +0.005 |
atters | +0.004 |
Neg logit contributions | |
around | -0.004 |
ling | -0.004 |
him | -0.004 |
shining | -0.004 |
up | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
roller | +0.021 |
salon | +0.019 |
ara | +0.019 |
heaven | +0.018 |
atters | +0.018 |
Neg logit contributions | |
ling | -0.020 |
around | -0.017 |
shining | -0.017 |
led | -0.017 |
up | -0.016 |
Token | She |
Token ID | 3347 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
roller | +0.023 |
salon | +0.022 |
bidder | +0.020 |
clinic | +0.020 |
jail | +0.019 |
Neg logit contributions | |
ling | -0.020 |
around | -0.017 |
in | -0.015 |
him | -0.015 |
up | -0.015 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
roller | +0.085 |
salon | +0.078 |
ara | +0.075 |
atters | +0.074 |
lor | +0.072 |
Neg logit contributions | |
ling | -0.079 |
around | -0.073 |
shining | -0.073 |
him | -0.067 |
up | -0.067 |
Token | ay |
Token ID | 323 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ling | +0.065 |
around | +0.061 |
ie | +0.059 |
shining | +0.057 |
led | +0.055 |
Neg logit contributions | |
salon | -0.068 |
clinic | -0.068 |
heaven | -0.066 |
bidder | -0.065 |
vet | -0.064 |
Token | ons |
Token ID | 684 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
ling | +0.064 |
around | +0.055 |
shining | +0.054 |
led | +0.051 |
up | +0.049 |
Neg logit contributions | |
roller | -0.098 |
salon | -0.094 |
ara | -0.089 |
heaven | -0.087 |
atters | -0.087 |
Token | she |
Token ID | 673 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
ling | +0.135 |
around | +0.124 |
shining | +0.111 |
in | +0.104 |
up | +0.103 |
Neg logit contributions | |
roller | -0.264 |
salon | -0.247 |
ara | -0.244 |
atters | -0.239 |
clinic | -0.235 |
Token | had |
Token ID | 550 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
ling | +0.001 |
shining | +0.001 |
around | +0.001 |
up | +0.001 |
led | +0.001 |
Neg logit contributions | |
roller | -0.001 |
salon | -0.001 |
ara | -0.001 |
post | -0.001 |
heaven | -0.001 |
Token | forgotten |
Token ID | 11564 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ling | +0.038 |
around | +0.035 |
shining | +0.033 |
led | +0.031 |
in | +0.031 |
Neg logit contributions | |
roller | -0.057 |
salon | -0.053 |
ara | -0.051 |
pitcher | -0.051 |
clinic | -0.050 |
Token | about |
Token ID | 546 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
roller | +0.189 |
salon | +0.180 |
ara | +0.171 |
heaven | +0.167 |
atters | +0.166 |
Neg logit contributions | |
ling | -0.128 |
around | -0.109 |
shining | -0.107 |
led | -0.102 |
up | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ling | +0.086 |
around | +0.070 |
led | +0.069 |
shining | +0.068 |
up | +0.062 |
Neg logit contributions | |
roller | -0.107 |
salon | -0.104 |
ara | -0.097 |
heaven | -0.097 |
post | -0.096 |
Token | She |
Token ID | 1375 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
around | +0.008 |
up | +0.008 |
ling | +0.008 |
shining | +0.007 |
in | +0.007 |
Neg logit contributions | |
roller | -0.007 |
lor | -0.007 |
salon | -0.007 |
heaven | -0.006 |
clinic | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
roller | +0.137 |
salon | +0.130 |
ara | +0.124 |
heaven | +0.121 |
atters | +0.121 |
Neg logit contributions | |
ling | -0.086 |
around | -0.073 |
shining | -0.071 |
led | -0.067 |
up | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
ling | +0.118 |
led | +0.096 |
around | +0.092 |
shining | +0.091 |
ie | +0.084 |
Neg logit contributions | |
roller | -0.148 |
salon | -0.146 |
ara | -0.134 |
heaven | -0.134 |
post | -0.131 |
Token | but |
Token ID | 475 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
ling | +0.007 |
around | +0.006 |
shining | +0.006 |
led | +0.005 |
ie | +0.005 |
Neg logit contributions | |
roller | -0.010 |
salon | -0.010 |
ara | -0.009 |
pitcher | -0.009 |
heaven | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ling | +0.106 |
led | +0.083 |
shining | +0.081 |
around | +0.081 |
ie | +0.076 |
Neg logit contributions | |
roller | -0.147 |
salon | -0.147 |
ara | -0.138 |
heaven | -0.135 |
pitcher | -0.135 |
Token | small |
Token ID | 1402 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ling | +0.007 |
around | +0.005 |
led | +0.005 |
shining | +0.005 |
ie | +0.005 |
Neg logit contributions | |
roller | -0.010 |
salon | -0.009 |
pitcher | -0.009 |
ara | -0.009 |
heaven | -0.009 |
Token | square |
Token ID | 6616 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
roller | +0.014 |
salon | +0.013 |
ara | +0.012 |
lor | +0.012 |
atters | +0.012 |
Neg logit contributions | |
ling | -0.013 |
around | -0.012 |
shining | -0.012 |
up | -0.011 |
led | -0.011 |
Token | box |
Token ID | 3091 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
roller | +0.096 |
salon | +0.092 |
ara | +0.088 |
heaven | +0.086 |
atters | +0.086 |
Neg logit contributions | |
ling | -0.056 |
around | -0.047 |
shining | -0.046 |
led | -0.043 |
up | -0.041 |
Token | had |
Token ID | 550 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
roller | +0.220 |
salon | +0.210 |
ara | +0.200 |
heaven | +0.195 |
atters | +0.195 |
Neg logit contributions | |
ling | -0.126 |
around | -0.106 |
shining | -0.103 |
led | -0.097 |
up | -0.092 |
Token | a |
Token ID | 257 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
around | +0.020 |
shining | +0.020 |
all | +0.019 |
ling | +0.019 |
in | +0.017 |
Neg logit contributions | |
roller | -0.059 |
salon | -0.059 |
ara | -0.057 |
clinic | -0.056 |
ress | -0.055 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
shining | +0.001 |
ling | +0.001 |
around | +0.001 |
spear | +0.001 |
all | +0.001 |
Neg logit contributions | |
salon | -0.002 |
heaven | -0.002 |
ara | -0.002 |
ress | -0.002 |
lor | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
ling | +0.055 |
around | +0.049 |
shining | +0.048 |
up | +0.044 |
led | +0.043 |
Neg logit contributions | |
roller | -0.073 |
salon | -0.072 |
ara | -0.068 |
heaven | -0.067 |
clinic | -0.066 |
Token | rolling |
Token ID | 10708 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
roller | +0.130 |
salon | +0.124 |
ara | +0.119 |
heaven | +0.115 |
pitcher | +0.115 |
Neg logit contributions | |
ling | -0.080 |
around | -0.071 |
shining | -0.067 |
led | -0.063 |
up | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ling | +0.071 |
shining | +0.054 |
around | +0.051 |
led | +0.050 |
ie | +0.045 |
Neg logit contributions | |
roller | -0.180 |
salon | -0.170 |
ara | -0.164 |
atters | -0.163 |
post | -0.163 |
Token | eating |
Token ID | 6600 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
roller | +0.260 |
salon | +0.251 |
heaven | +0.235 |
pitcher | +0.234 |
ara | +0.233 |
Neg logit contributions | |
ling | -0.206 |
around | -0.171 |
led | -0.169 |
shining | -0.159 |
ie | -0.155 |
Token | , |
Token ID | 11 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
ling | +0.138 |
around | +0.113 |
shining | +0.111 |
led | +0.108 |
ie | +0.100 |
Neg logit contributions | |
roller | -0.215 |
salon | -0.207 |
ara | -0.198 |
heaven | -0.194 |
pitcher | -0.194 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
ling | +0.006 |
around | +0.005 |
shining | +0.005 |
led | +0.005 |
up | +0.005 |
Neg logit contributions | |
roller | -0.004 |
salon | -0.003 |
ara | -0.003 |
heaven | -0.003 |
pitcher | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
roller | +0.250 |
salon | +0.237 |
atters | +0.226 |
post | +0.224 |
ara | +0.223 |
Neg logit contributions | |
ling | -0.163 |
around | -0.139 |
shining | -0.132 |
led | -0.128 |
up | -0.124 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
roller | +0.066 |
salon | +0.063 |
ara | +0.058 |
heaven | +0.058 |
pitcher | +0.058 |
Neg logit contributions | |
ling | -0.060 |
around | -0.051 |
led | -0.051 |
shining | -0.049 |
atop | -0.046 |
Token | suggested |
Token ID | 5220 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
roller | +0.052 |
salon | +0.049 |
ara | +0.046 |
atters | +0.046 |
heaven | +0.045 |
Neg logit contributions | |
ling | -0.034 |
around | -0.029 |
shining | -0.029 |
led | -0.027 |
up | -0.026 |
Token | they |
Token ID | 484 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ling | +0.043 |
around | +0.037 |
shining | +0.037 |
led | +0.036 |
ie | +0.034 |
Neg logit contributions | |
roller | -0.046 |
salon | -0.046 |
ara | -0.043 |
heaven | -0.042 |
pitcher | -0.042 |
Token | go |
Token ID | 467 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
roller | +0.023 |
salon | +0.022 |
heaven | +0.020 |
pitcher | +0.020 |
ara | +0.020 |
Neg logit contributions | |
ling | -0.027 |
led | -0.023 |
shining | -0.023 |
around | -0.023 |
ie | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
roller | +0.147 |
salon | +0.143 |
post | +0.137 |
ara | +0.136 |
lor | +0.133 |
Neg logit contributions | |
ling | -0.067 |
around | -0.065 |
up | -0.059 |
shining | -0.057 |
in | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
ling | +0.048 |
shining | +0.048 |
him | +0.048 |
around | +0.045 |
up | +0.042 |
Neg logit contributions | |
roller | -0.131 |
salon | -0.125 |
ress | -0.118 |
ara | -0.118 |
atters | -0.116 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ling | +0.002 |
around | +0.002 |
shining | +0.002 |
led | +0.002 |
up | +0.001 |
Neg logit contributions | |
roller | -0.002 |
salon | -0.002 |
ara | -0.002 |
heaven | -0.002 |
atters | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
ling | +0.070 |
around | +0.059 |
shining | +0.058 |
led | +0.056 |
up | +0.052 |
Neg logit contributions | |
roller | -0.108 |
salon | -0.103 |
ara | -0.097 |
pitcher | -0.095 |
heaven | -0.095 |
Token | even |
Token ID | 772 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ling | +0.025 |
around | +0.020 |
shining | +0.020 |
led | +0.020 |
ie | +0.018 |
Neg logit contributions | |
salon | -0.033 |
roller | -0.033 |
heaven | -0.030 |
pitcher | -0.030 |
ara | -0.030 |
Token | ignored |
Token ID | 9514 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
ling | +0.108 |
shining | +0.094 |
itive | +0.090 |
around | +0.089 |
bee | +0.087 |
Neg logit contributions | |
salon | -0.113 |
pitcher | -0.106 |
heaven | -0.105 |
ara | -0.103 |
roller | -0.101 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
roller | +0.041 |
heaven | +0.041 |
jail | +0.041 |
salon | +0.038 |
post | +0.038 |
Neg logit contributions | |
ling | -0.030 |
led | -0.025 |
shining | -0.024 |
atop | -0.023 |
itive | -0.023 |
Token | my |
Token ID | 1820 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
ling | +0.041 |
shining | +0.040 |
led | +0.040 |
atop | +0.037 |
around | +0.036 |
Neg logit contributions | |
salon | -0.051 |
roller | -0.050 |
ress | -0.048 |
ara | -0.047 |
heaven | -0.046 |
Token | when |
Token ID | 618 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ling | +0.190 |
shining | +0.170 |
led | +0.163 |
around | +0.160 |
ie | +0.148 |
Neg logit contributions | |
roller | -0.227 |
salon | -0.219 |
heaven | -0.205 |
clinic | -0.200 |
ara | -0.199 |
Token | he |
Token ID | 339 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ling | +0.005 |
led | +0.004 |
around | +0.004 |
ie | +0.004 |
bee | +0.003 |
Neg logit contributions | |
salon | -0.007 |
roller | -0.007 |
jail | -0.007 |
heaven | -0.007 |
ara | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ling | +0.144 |
around | +0.124 |
shining | +0.123 |
led | +0.113 |
up | +0.112 |
Neg logit contributions | |
roller | -0.194 |
salon | -0.187 |
ara | -0.181 |
pitcher | -0.173 |
heaven | -0.172 |
Token | he |
Token ID | 339 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
ling | +0.065 |
shining | +0.054 |
around | +0.054 |
led | +0.053 |
ie | +0.051 |
Neg logit contributions | |
roller | -0.079 |
salon | -0.077 |
ara | -0.071 |
heaven | -0.071 |
pitcher | -0.070 |
Token | was |
Token ID | 373 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ling | +0.141 |
shining | +0.122 |
around | +0.119 |
led | +0.107 |
up | +0.107 |
Neg logit contributions | |
roller | -0.190 |
salon | -0.183 |
ara | -0.182 |
atters | -0.170 |
clinic | -0.169 |
Token | still |
Token ID | 991 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
salon | +0.013 |
roller | +0.013 |
heaven | +0.012 |
pitcher | +0.012 |
jail | +0.012 |
Neg logit contributions | |
ling | -0.011 |
led | -0.010 |
ie | -0.009 |
around | -0.009 |
shining | -0.009 |
Token | grew |
Token ID | 6348 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
roller | +0.078 |
salon | +0.074 |
ara | +0.070 |
heaven | +0.068 |
atters | +0.068 |
Neg logit contributions | |
ling | -0.056 |
around | -0.048 |
shining | -0.047 |
led | -0.045 |
up | -0.043 |
Token | bigger |
Token ID | 5749 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
roller | +0.081 |
post | +0.074 |
salon | +0.074 |
pitcher | +0.073 |
atters | +0.072 |
Neg logit contributions | |
ling | -0.065 |
around | -0.054 |
led | -0.053 |
bee | -0.053 |
uses | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
roller | +0.095 |
salon | +0.090 |
ara | +0.085 |
atters | +0.083 |
heaven | +0.083 |
Neg logit contributions | |
ling | -0.062 |
around | -0.054 |
shining | -0.051 |
led | -0.049 |
up | -0.048 |
Token | Anna |
Token ID | 11735 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
around | +0.007 |
ling | +0.006 |
up | +0.006 |
shining | +0.006 |
him | +0.006 |
Neg logit contributions | |
roller | -0.009 |
salon | -0.009 |
pitcher | -0.008 |
clinic | -0.008 |
heaven | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
roller | +0.296 |
salon | +0.283 |
ara | +0.269 |
heaven | +0.262 |
atters | +0.262 |
Neg logit contributions | |
ling | -0.180 |
around | -0.152 |
shining | -0.149 |
led | -0.140 |
up | -0.133 |
Token | amazed |
Token ID | 24562 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
roller | +0.017 |
salon | +0.016 |
ara | +0.015 |
heaven | +0.015 |
atters | +0.015 |
Neg logit contributions | |
ling | -0.010 |
around | -0.009 |
shining | -0.009 |
led | -0.008 |
up | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ling | +0.153 |
shining | +0.132 |
led | +0.131 |
bee | +0.126 |
spear | +0.123 |
Neg logit contributions | |
ara | -0.164 |
roller | -0.162 |
salon | -0.160 |
post | -0.154 |
heaven | -0.151 |
Token | full |
Token ID | 1336 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ling | +0.012 |
shining | +0.009 |
around | +0.009 |
led | +0.009 |
ie | +0.009 |
Neg logit contributions | |
roller | -0.016 |
salon | -0.016 |
ara | -0.015 |
post | -0.015 |
pitcher | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
roller | +0.132 |
salon | +0.124 |
atters | +0.118 |
ara | +0.118 |
clinic | +0.115 |
Neg logit contributions | |
ling | -0.091 |
around | -0.085 |
shining | -0.082 |
in | -0.074 |
him | -0.074 |
Token | joy |
Token ID | 8716 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
roller | +0.068 |
salon | +0.066 |
heaven | +0.064 |
ara | +0.062 |
clinic | +0.061 |
Neg logit contributions | |
ling | -0.080 |
led | -0.068 |
around | -0.068 |
shining | -0.067 |
ie | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
roller | +0.010 |
salon | +0.010 |
post | +0.009 |
ara | +0.009 |
heaven | +0.009 |
Neg logit contributions | |
ling | -0.010 |
around | -0.008 |
led | -0.008 |
shining | -0.008 |
spear | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ling | +0.011 |
led | +0.008 |
ie | +0.008 |
ering | +0.008 |
around | +0.008 |
Neg logit contributions | |
roller | -0.013 |
pitcher | -0.013 |
ara | -0.013 |
salon | -0.013 |
jail | -0.012 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
ling | +0.008 |
around | +0.007 |
led | +0.007 |
shining | +0.006 |
him | +0.006 |
Neg logit contributions | |
roller | -0.011 |
vet | -0.011 |
ara | -0.011 |
pitcher | -0.011 |
salon | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ling | +0.205 |
around | +0.174 |
shining | +0.172 |
led | +0.161 |
up | +0.154 |
Neg logit contributions | |
roller | -0.318 |
salon | -0.303 |
ara | -0.290 |
heaven | -0.282 |
pitcher | -0.280 |
Token | to |
Token ID | 284 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
ling | +0.077 |
shining | +0.065 |
led | +0.064 |
ie | +0.061 |
around | +0.061 |
Neg logit contributions | |
roller | -0.073 |
salon | -0.069 |
ara | -0.065 |
pitcher | -0.065 |
ress | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
roller | +0.027 |
salon | +0.026 |
ara | +0.025 |
heaven | +0.025 |
atters | +0.025 |
Neg logit contributions | |
ling | -0.013 |
around | -0.010 |
shining | -0.010 |
led | -0.010 |
ie | -0.008 |
Token | sheep |
Token ID | 15900 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
ling | +0.007 |
led | +0.007 |
around | +0.006 |
atop | +0.005 |
shining | +0.005 |
Neg logit contributions | |
roller | -0.010 |
vet | -0.010 |
salon | -0.009 |
ara | -0.009 |
pitcher | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ling | +0.207 |
led | +0.181 |
shining | +0.179 |
around | +0.170 |
ging | +0.162 |
Neg logit contributions | |
roller | -0.221 |
salon | -0.216 |
ara | -0.200 |
clinic | -0.199 |
heaven | -0.198 |
Token | " |
Token ID | 366 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ling | +0.013 |
led | +0.012 |
ie | +0.011 |
itive | +0.010 |
shining | +0.010 |
Neg logit contributions | |
roller | -0.010 |
salon | -0.009 |
ara | -0.009 |
vet | -0.009 |
post | -0.008 |
Token | I |
Token ID | 40 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
ling | +0.102 |
around | +0.090 |
shining | +0.088 |
led | +0.084 |
up | +0.081 |
Neg logit contributions | |
roller | -0.101 |
salon | -0.093 |
atters | -0.086 |
clinic | -0.085 |
heaven | -0.083 |
Token | think |
Token ID | 892 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
roller | +0.030 |
salon | +0.028 |
ara | +0.026 |
ress | +0.026 |
post | +0.026 |
Neg logit contributions | |
ling | -0.022 |
around | -0.020 |
shining | -0.018 |
led | -0.017 |
up | -0.017 |
Token | your |
Token ID | 534 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
ling | +0.205 |
led | +0.178 |
shining | +0.171 |
around | +0.168 |
atop | +0.163 |
Neg logit contributions | |
roller | -0.132 |
salon | -0.128 |
heaven | -0.119 |
ara | -0.117 |
pitcher | -0.113 |
Token | day |
Token ID | 1110 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ling | +0.014 |
around | +0.012 |
shining | +0.012 |
up | +0.010 |
led | +0.010 |
Neg logit contributions | |
roller | -0.025 |
salon | -0.024 |
heaven | -0.022 |
ress | -0.022 |
ara | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ling | +0.046 |
around | +0.039 |
shining | +0.037 |
led | +0.035 |
up | +0.033 |
Neg logit contributions | |
roller | -0.087 |
salon | -0.083 |
ara | -0.080 |
heaven | -0.078 |
atters | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
around | +0.027 |
ling | +0.025 |
up | +0.024 |
shining | +0.022 |
him | +0.020 |
Neg logit contributions | |
roller | -0.153 |
salon | -0.144 |
ara | -0.142 |
pitcher | -0.140 |
lor | -0.140 |
Token | park |
Token ID | 3952 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
ling | +0.018 |
up | +0.018 |
around | +0.018 |
shining | +0.018 |
all | +0.017 |
Neg logit contributions | |
roller | -0.015 |
atters | -0.013 |
ress | -0.013 |
ird | -0.012 |
post | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
roller | +0.309 |
salon | +0.293 |
ara | +0.282 |
atters | +0.276 |
pitcher | +0.274 |
Neg logit contributions | |
ling | -0.182 |
around | -0.160 |
shining | -0.149 |
up | -0.139 |
led | -0.138 |
Token | playing |
Token ID | 2712 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ling | +0.010 |
led | +0.008 |
around | +0.008 |
shining | +0.008 |
ie | +0.008 |
Neg logit contributions | |
roller | -0.018 |
salon | -0.018 |
ara | -0.017 |
pitcher | -0.016 |
heaven | -0.016 |
Token | tag |
Token ID | 7621 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ling | +0.166 |
shining | +0.142 |
around | +0.139 |
led | +0.134 |
ie | +0.128 |
Neg logit contributions | |
roller | -0.227 |
salon | -0.217 |
ara | -0.207 |
heaven | -0.203 |
clinic | -0.202 |
Token | and |
Token ID | 290 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
roller | +0.219 |
salon | +0.209 |
ara | +0.198 |
post | +0.195 |
clinic | +0.192 |
Neg logit contributions | |
ling | -0.189 |
shining | -0.165 |
led | -0.157 |
around | -0.156 |
ie | -0.150 |
Token | chasing |
Token ID | 20023 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
ling | +0.017 |
around | +0.014 |
led | +0.014 |
shining | +0.013 |
ie | +0.013 |
Neg logit contributions | |
roller | -0.027 |
salon | -0.026 |
ara | -0.024 |
pitcher | -0.024 |
heaven | -0.024 |
Token | each |
Token ID | 1123 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
ling | +0.158 |
shining | +0.152 |
led | +0.126 |
ie | +0.126 |
itive | +0.124 |
Neg logit contributions | |
roller | -0.231 |
ara | -0.225 |
heaven | -0.220 |
salon | -0.213 |
jail | -0.213 |
Token | other |
Token ID | 584 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ling | +0.187 |
around | +0.154 |
shining | +0.150 |
led | +0.141 |
up | +0.132 |
Neg logit contributions | |
roller | -0.381 |
salon | -0.366 |
ara | -0.350 |
heaven | -0.342 |
atters | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ling | +0.000 |
around | +0.000 |
shining | +0.000 |
up | +0.000 |
led | +0.000 |
Neg logit contributions | |
roller | -0.001 |
salon | -0.001 |
ara | -0.001 |
pitcher | -0.001 |
atters | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
around | +0.012 |
ling | +0.012 |
shining | +0.011 |
up | +0.011 |
him | +0.011 |
Neg logit contributions | |
roller | -0.009 |
salon | -0.008 |
ara | -0.008 |
pitcher | -0.008 |
lor | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
salon | +0.113 |
roller | +0.113 |
ara | +0.107 |
clinic | +0.101 |
heaven | +0.099 |
Neg logit contributions | |
ling | -0.098 |
shining | -0.082 |
led | -0.078 |
around | -0.078 |
ging | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
ling | +0.026 |
ging | +0.021 |
led | +0.021 |
around | +0.020 |
atop | +0.020 |
Neg logit contributions | |
salon | -0.024 |
vet | -0.024 |
heaven | -0.022 |
roller | -0.022 |
jail | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ling | +0.001 |
around | +0.001 |
shining | +0.001 |
led | +0.001 |
up | +0.001 |
Neg logit contributions | |
roller | -0.002 |
salon | -0.002 |
ara | -0.002 |
heaven | -0.002 |
pitcher | -0.002 |
Token | bear |
Token ID | 6842 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
roller | +0.080 |
salon | +0.075 |
ara | +0.071 |
atters | +0.070 |
post | +0.070 |
Neg logit contributions | |
ling | -0.071 |
around | -0.063 |
shining | -0.062 |
up | -0.057 |
ie | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ling | +0.172 |
around | +0.142 |
shining | +0.138 |
led | +0.137 |
up | +0.123 |
Neg logit contributions | |
roller | -0.302 |
salon | -0.291 |
ara | -0.275 |
heaven | -0.272 |
clinic | -0.272 |
Token | thought |
Token ID | 1807 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
ling | +0.023 |
ging | +0.018 |
around | +0.018 |
led | +0.017 |
ering | +0.017 |
Neg logit contributions | |
vet | -0.019 |
salon | -0.019 |
roller | -0.019 |
heaven | -0.018 |
ara | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
ling | +0.235 |
led | +0.192 |
shining | +0.185 |
uses | +0.181 |
atop | +0.178 |
Neg logit contributions | |
salon | -0.199 |
roller | -0.199 |
post | -0.196 |
heaven | -0.188 |
ara | -0.185 |
Token | was |
Token ID | 373 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
ling | +0.002 |
ging | +0.002 |
nam | +0.002 |
itive | +0.002 |
led | +0.002 |
Neg logit contributions | |
post | -0.001 |
house | -0.001 |
roller | -0.001 |
salon | -0.001 |
ara | -0.001 |
Token | cute |
Token ID | 13779 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
heaven | +0.004 |
jail | +0.004 |
roller | +0.004 |
vet | +0.004 |
salon | +0.004 |
Neg logit contributions | |
ling | -0.004 |
led | -0.004 |
ging | -0.003 |
ged | -0.003 |
around | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
ling | +0.056 |
shining | +0.044 |
led | +0.044 |
around | +0.042 |
itive | +0.042 |
Neg logit contributions | |
roller | -0.067 |
heaven | -0.065 |
salon | -0.063 |
jail | -0.062 |
ara | -0.062 |
Token | anywhere |
Token ID | 6609 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
ling | +0.029 |
led | +0.026 |
shining | +0.025 |
bee | +0.024 |
itive | +0.023 |
Neg logit contributions | |
roller | -0.026 |
salon | -0.024 |
heaven | -0.024 |
post | -0.023 |
jail | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ling | +0.191 |
shining | +0.159 |
led | +0.159 |
around | +0.154 |
ie | +0.143 |
Neg logit contributions | |
roller | -0.216 |
salon | -0.206 |
heaven | -0.198 |
post | -0.193 |
jail | -0.191 |
Token | The |
Token ID | 383 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
ling | +0.006 |
around | +0.006 |
him | +0.006 |
up | +0.006 |
shining | +0.005 |
Neg logit contributions | |
roller | -0.009 |
salon | -0.009 |
atters | -0.008 |
ara | -0.008 |
pitcher | -0.008 |
Token | creatures |
Token ID | 8109 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
roller | +0.040 |
salon | +0.040 |
ara | +0.037 |
pitcher | +0.037 |
vet | +0.036 |
Neg logit contributions | |
ling | -0.035 |
around | -0.031 |
led | -0.030 |
shining | -0.030 |
him | -0.028 |
Token | in |
Token ID | 287 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ling | +0.192 |
shining | +0.192 |
fl | +0.181 |
up | +0.167 |
itive | +0.166 |
Neg logit contributions | |
roller | -0.257 |
salon | -0.256 |
fountain | -0.239 |
pitcher | -0.237 |
post | -0.233 |
Token | the |
Token ID | 262 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
ling | +0.062 |
around | +0.048 |
shining | +0.048 |
led | +0.045 |
up | +0.041 |
Neg logit contributions | |
roller | -0.147 |
salon | -0.141 |
ara | -0.136 |
heaven | -0.134 |
pitcher | -0.132 |
Token | jar |
Token ID | 17379 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ling | +0.038 |
around | +0.034 |
shining | +0.033 |
up | +0.031 |
led | +0.031 |
Neg logit contributions | |
roller | -0.032 |
salon | -0.029 |
atters | -0.028 |
ara | -0.027 |
ress | -0.027 |
Token | were |
Token ID | 547 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
roller | +0.083 |
salon | +0.079 |
ara | +0.076 |
heaven | +0.074 |
atters | +0.074 |
Neg logit contributions | |
ling | -0.049 |
around | -0.042 |
shining | -0.040 |
led | -0.038 |
up | -0.036 |
Token | gone |
Token ID | 3750 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ling | +0.036 |
led | +0.029 |
shining | +0.029 |
ie | +0.029 |
around | +0.029 |
Neg logit contributions | |
roller | -0.053 |
salon | -0.051 |
heaven | -0.048 |
pitcher | -0.048 |
clinic | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
roller | +0.125 |
salon | +0.118 |
ara | +0.111 |
heaven | +0.110 |
post | +0.109 |
Neg logit contributions | |
ling | -0.093 |
around | -0.079 |
shining | -0.078 |
led | -0.076 |
ie | -0.071 |
Token | excited |
Token ID | 6568 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
ling | +0.018 |
around | +0.015 |
shining | +0.015 |
led | +0.014 |
ie | +0.014 |
Neg logit contributions | |
roller | -0.034 |
salon | -0.033 |
ara | -0.031 |
pitcher | -0.031 |
atters | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ling | +0.027 |
shining | +0.023 |
led | +0.022 |
around | +0.021 |
atop | +0.021 |
Neg logit contributions | |
roller | -0.030 |
salon | -0.029 |
ara | -0.028 |
post | -0.027 |
heaven | -0.027 |
Token | began |
Token ID | 2540 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ling | +0.022 |
shining | +0.018 |
around | +0.018 |
led | +0.017 |
ie | +0.016 |
Neg logit contributions | |
roller | -0.033 |
salon | -0.032 |
ara | -0.030 |
pitcher | -0.029 |
heaven | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
roller | +0.118 |
salon | +0.112 |
ara | +0.105 |
heaven | +0.105 |
clinic | +0.104 |
Neg logit contributions | |
ling | -0.074 |
around | -0.061 |
shining | -0.060 |
led | -0.059 |
ie | -0.055 |
Token | count |
Token ID | 954 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
roller | +0.013 |
salon | +0.013 |
ara | +0.012 |
heaven | +0.012 |
pitcher | +0.012 |
Neg logit contributions | |
ling | -0.011 |
around | -0.010 |
shining | -0.009 |
led | -0.009 |
up | -0.009 |
Token | how |
Token ID | 703 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
ling | +0.035 |
led | +0.029 |
shining | +0.027 |
itive | +0.026 |
bee | +0.025 |
Neg logit contributions | |
roller | -0.050 |
salon | -0.049 |
ara | -0.045 |
post | -0.044 |
ress | -0.044 |
Token | many |
Token ID | 867 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ling | +0.344 |
shining | +0.283 |
bee | +0.282 |
itive | +0.274 |
led | +0.273 |
Neg logit contributions | |
roller | -0.385 |
salon | -0.380 |
ara | -0.354 |
post | -0.349 |
ress | -0.344 |
Token | patterns |
Token ID | 7572 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
roller | +0.058 |
salon | +0.057 |
ara | +0.055 |
pitcher | +0.052 |
heaven | +0.052 |
Neg logit contributions | |
ling | -0.051 |
shining | -0.043 |
around | -0.043 |
led | -0.041 |
up | -0.040 |
Token | were |
Token ID | 547 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ling | +0.029 |
shining | +0.022 |
around | +0.021 |
led | +0.021 |
itive | +0.020 |
Neg logit contributions | |
roller | -0.041 |
salon | -0.040 |
post | -0.039 |
ara | -0.038 |
pitcher | -0.037 |
Token | on |
Token ID | 319 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
ling | +0.043 |
led | +0.035 |
around | +0.034 |
shining | +0.033 |
ie | +0.031 |
Neg logit contributions | |
roller | -0.068 |
salon | -0.066 |
pitcher | -0.061 |
heaven | -0.061 |
post | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
ling | +0.111 |
around | +0.091 |
shining | +0.088 |
led | +0.083 |
up | +0.078 |
Neg logit contributions | |
roller | -0.227 |
salon | -0.217 |
ara | -0.208 |
heaven | -0.204 |
pitcher | -0.203 |
Token | flew |
Token ID | 13112 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ling | +0.012 |
shining | +0.010 |
around | +0.010 |
him | +0.009 |
led | +0.009 |
Neg logit contributions | |
roller | -0.016 |
salon | -0.016 |
ara | -0.015 |
clinic | -0.015 |
heaven | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
roller | +0.023 |
post | +0.022 |
salon | +0.020 |
ara | +0.020 |
atters | +0.020 |
Neg logit contributions | |
ling | -0.011 |
itive | -0.009 |
led | -0.009 |
uses | -0.008 |
bee | -0.008 |
Token | circles |
Token ID | 13332 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ling | +0.047 |
around | +0.043 |
shining | +0.041 |
up | +0.036 |
him | +0.035 |
Neg logit contributions | |
roller | -0.155 |
salon | -0.150 |
ara | -0.144 |
atters | -0.143 |
clinic | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
roller | +0.068 |
post | +0.065 |
salon | +0.063 |
ara | +0.060 |
heaven | +0.059 |
Neg logit contributions | |
ling | -0.059 |
nam | -0.050 |
shining | -0.048 |
led | -0.048 |
uses | -0.048 |
Token | swoop |
Token ID | 38527 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ling | +0.017 |
ie | +0.015 |
led | +0.015 |
itive | +0.014 |
him | +0.013 |
Neg logit contributions | |
roller | -0.025 |
salon | -0.025 |
post | -0.024 |
heaven | -0.023 |
atters | -0.022 |
Token | ing |
Token ID | 278 |
Feature activation | -7.67e+00 |
Pos logit contributions | |
ling | +0.086 |
nam | +0.074 |
ie | +0.071 |
shining | +0.070 |
uses | +0.067 |
Neg logit contributions | |
roller | -0.163 |
ara | -0.147 |
post | -0.146 |
salon | -0.143 |
lor | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
ling | +0.254 |
ie | +0.208 |
uses | +0.200 |
itive | +0.200 |
nam | +0.199 |
Neg logit contributions | |
roller | -0.447 |
post | -0.420 |
salon | -0.398 |
ara | -0.387 |
pitcher | -0.386 |
Token | diving |
Token ID | 23186 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ling | +0.028 |
ie | +0.022 |
led | +0.022 |
around | +0.021 |
itive | +0.021 |
Neg logit contributions | |
roller | -0.031 |
salon | -0.031 |
post | -0.029 |
heaven | -0.028 |
ara | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
ling | +0.048 |
shining | +0.038 |
ie | +0.036 |
led | +0.034 |
around | +0.033 |
Neg logit contributions | |
roller | -0.104 |
post | -0.097 |
salon | -0.094 |
ara | -0.093 |
atters | -0.092 |
Token | Then |
Token ID | 3244 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
ling | +0.025 |
around | +0.024 |
shining | +0.022 |
him | +0.021 |
up | +0.021 |
Neg logit contributions | |
roller | -0.024 |
salon | -0.023 |
ara | -0.021 |
heaven | -0.020 |
pitcher | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
roller | +0.148 |
salon | +0.142 |
ara | +0.136 |
heaven | +0.133 |
clinic | +0.132 |
Neg logit contributions | |
ling | -0.093 |
around | -0.075 |
shining | -0.074 |
led | -0.072 |
ie | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ling | +0.002 |
shining | +0.001 |
led | +0.001 |
around | +0.001 |
itive | +0.001 |
Neg logit contributions | |
roller | -0.002 |
ara | -0.002 |
post | -0.002 |
S | -0.002 |
salon | -0.002 |
Token | hook |
Token ID | 8011 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
ling | +0.001 |
around | +0.001 |
shining | +0.001 |
led | +0.001 |
ie | +0.001 |
Neg logit contributions | |
roller | -0.001 |
salon | -0.001 |
ara | -0.001 |
pitcher | -0.001 |
clinic | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ling | +0.010 |
shining | +0.009 |
around | +0.008 |
led | +0.008 |
ie | +0.008 |
Neg logit contributions | |
roller | -0.013 |
salon | -0.012 |
post | -0.011 |
heaven | -0.011 |
pitcher | -0.011 |
Token | set |
Token ID | 900 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
ling | +0.012 |
around | +0.011 |
shining | +0.010 |
led | +0.010 |
up | +0.009 |
Neg logit contributions | |
roller | -0.017 |
salon | -0.017 |
ara | -0.016 |
heaven | -0.015 |
pitcher | -0.015 |
Token | Bub |
Token ID | 19645 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
roller | +0.276 |
salon | +0.255 |
atters | +0.248 |
heaven | +0.247 |
post | +0.247 |
Neg logit contributions | |
ling | -0.142 |
shining | -0.112 |
led | -0.109 |
around | -0.106 |
ie | -0.098 |
Token | bles |
Token ID | 7689 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
ling | +0.126 |
around | +0.120 |
shining | +0.120 |
led | +0.098 |
him | +0.098 |
Neg logit contributions | |
roller | -0.313 |
salon | -0.292 |
ara | -0.290 |
atters | -0.282 |
lor | -0.280 |
Token | free |
Token ID | 1479 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ling | +0.344 |
shining | +0.304 |
led | +0.288 |
around | +0.278 |
ie | +0.271 |
Neg logit contributions | |
roller | -0.469 |
salon | -0.441 |
atters | -0.428 |
heaven | -0.425 |
pitcher | -0.418 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
roller | +0.106 |
salon | +0.099 |
heaven | +0.098 |
post | +0.097 |
ara | +0.095 |
Neg logit contributions | |
ling | -0.079 |
shining | -0.067 |
led | -0.066 |
around | -0.064 |
ie | -0.060 |
Token | Bub |
Token ID | 19645 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
ling | +0.004 |
around | +0.004 |
shining | +0.003 |
up | +0.003 |
led | +0.003 |
Neg logit contributions | |
roller | -0.008 |
salon | -0.008 |
ara | -0.008 |
heaven | -0.008 |
pitcher | -0.008 |
Token | bles |
Token ID | 7689 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
ling | +0.130 |
around | +0.125 |
shining | +0.123 |
him | +0.107 |
led | +0.100 |
Neg logit contributions | |
roller | -0.308 |
ara | -0.292 |
salon | -0.289 |
ress | -0.279 |
atters | -0.277 |
Token | was |
Token ID | 373 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ling | +0.348 |
shining | +0.316 |
around | +0.298 |
up | +0.279 |
led | +0.276 |
Neg logit contributions | |
roller | -0.451 |
salon | -0.425 |
pitcher | -0.404 |
ara | -0.401 |
ress | -0.396 |
Token | son |
Token ID | 3367 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ling | +0.016 |
around | +0.015 |
shining | +0.015 |
him | +0.014 |
up | +0.014 |
Neg logit contributions | |
roller | -0.019 |
salon | -0.017 |
atters | -0.016 |
clinic | -0.016 |
ara | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ling | +0.133 |
around | +0.115 |
shining | +0.109 |
led | +0.104 |
up | +0.101 |
Neg logit contributions | |
roller | -0.206 |
salon | -0.195 |
ara | -0.185 |
pitcher | -0.181 |
atters | -0.181 |
Token | This |
Token ID | 770 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ling | +0.005 |
around | +0.005 |
him | +0.005 |
shining | +0.005 |
up | +0.005 |
Neg logit contributions | |
roller | -0.005 |
salon | -0.005 |
post | -0.004 |
pitcher | -0.004 |
bidder | -0.004 |
Token | lovely |
Token ID | 14081 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ling | +0.060 |
around | +0.054 |
shining | +0.053 |
up | +0.050 |
led | +0.049 |
Neg logit contributions | |
roller | -0.049 |
salon | -0.046 |
ara | -0.042 |
atters | -0.042 |
post | -0.042 |
Token | muff |
Token ID | 27563 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
ling | +0.009 |
around | +0.008 |
shining | +0.008 |
led | +0.008 |
up | +0.007 |
Neg logit contributions | |
roller | -0.010 |
salon | -0.010 |
ara | -0.009 |
heaven | -0.009 |
clinic | -0.009 |
Token | in |
Token ID | 259 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
ling | +0.125 |
shining | +0.109 |
around | +0.108 |
up | +0.096 |
him | +0.095 |
Neg logit contributions | |
roller | -0.222 |
salon | -0.221 |
ara | -0.211 |
pitcher | -0.205 |
atters | -0.204 |
Token | isn |
Token ID | 2125 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
ling | +0.386 |
around | +0.345 |
shining | +0.327 |
led | +0.321 |
up | +0.311 |
Neg logit contributions | |
roller | -0.413 |
salon | -0.385 |
ara | -0.361 |
atters | -0.349 |
pitcher | -0.349 |
Token | 't |
Token ID | 470 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ling | +0.037 |
around | +0.033 |
shining | +0.033 |
led | +0.032 |
ie | +0.030 |
Neg logit contributions | |
roller | -0.027 |
salon | -0.025 |
ara | -0.024 |
atters | -0.023 |
pitcher | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
roller | +0.063 |
salon | +0.060 |
heaven | +0.059 |
ara | +0.057 |
post | +0.057 |
Neg logit contributions | |
ling | -0.054 |
led | -0.045 |
around | -0.045 |
shining | -0.044 |
atop | -0.040 |
Token | us |
Token ID | 514 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ling | +0.104 |
around | +0.089 |
led | +0.087 |
shining | +0.087 |
up | +0.080 |
Neg logit contributions | |
roller | -0.097 |
salon | -0.093 |
heaven | -0.086 |
ara | -0.086 |
pitcher | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
roller | +0.024 |
salon | +0.023 |
ara | +0.022 |
heaven | +0.021 |
atters | +0.021 |
Neg logit contributions | |
ling | -0.023 |
around | -0.020 |
shining | -0.020 |
led | -0.019 |
up | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
ling | +0.051 |
around | +0.042 |
led | +0.042 |
shining | +0.042 |
him | +0.039 |
Neg logit contributions | |
roller | -0.070 |
salon | -0.066 |
pitcher | -0.063 |
ara | -0.062 |
post | -0.062 |
Token | bright |
Token ID | 6016 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ling | +0.119 |
around | +0.099 |
led | +0.094 |
shining | +0.094 |
up | +0.087 |
Neg logit contributions | |
roller | -0.174 |
salon | -0.168 |
ara | -0.159 |
heaven | -0.157 |
pitcher | -0.156 |
Token | yellow |
Token ID | 7872 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ling | +0.053 |
around | +0.045 |
shining | +0.044 |
led | +0.043 |
up | +0.041 |
Neg logit contributions | |
roller | -0.071 |
ara | -0.066 |
salon | -0.066 |
pitcher | -0.064 |
heaven | -0.063 |
Token | neck |
Token ID | 7393 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
ling | +0.071 |
around | +0.062 |
shining | +0.059 |
led | +0.059 |
up | +0.056 |
Neg logit contributions | |
roller | -0.089 |
salon | -0.084 |
ara | -0.083 |
pitcher | -0.080 |
heaven | -0.079 |
Token | l |
Token ID | 75 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
ling | +0.142 |
shining | +0.123 |
around | +0.123 |
led | +0.122 |
him | +0.117 |
Neg logit contributions | |
roller | -0.186 |
salon | -0.174 |
ara | -0.167 |
post | -0.166 |
pitcher | -0.160 |
Token | aces |
Token ID | 2114 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
ling | +0.253 |
shining | +0.227 |
around | +0.214 |
nam | +0.211 |
Barry | +0.208 |
Neg logit contributions | |
roller | -0.280 |
post | -0.262 |
heaven | -0.259 |
ara | -0.256 |
atters | -0.255 |
Token | and |
Token ID | 290 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
ling | +0.322 |
shining | +0.265 |
around | +0.263 |
led | +0.260 |
him | +0.250 |
Neg logit contributions | |
roller | -0.418 |
salon | -0.397 |
post | -0.373 |
atters | -0.369 |
ara | -0.365 |
Token | flower |
Token ID | 15061 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
ling | +0.016 |
around | +0.012 |
led | +0.012 |
ie | +0.012 |
shining | +0.011 |
Neg logit contributions | |
roller | -0.020 |
salon | -0.019 |
pitcher | -0.019 |
post | -0.018 |
ara | -0.018 |
Token | crown |
Token ID | 12389 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
roller | +0.044 |
salon | +0.041 |
ara | +0.039 |
pitcher | +0.039 |
heaven | +0.039 |
Neg logit contributions | |
ling | -0.034 |
around | -0.029 |
shining | -0.028 |
led | -0.028 |
up | -0.026 |
Token | s |
Token ID | 82 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ling | +0.060 |
shining | +0.052 |
around | +0.050 |
led | +0.047 |
up | +0.047 |
Neg logit contributions | |
roller | -0.072 |
salon | -0.068 |
ara | -0.065 |
post | -0.065 |
atters | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ling | +0.046 |
led | +0.037 |
around | +0.037 |
ie | +0.035 |
shining | +0.035 |
Neg logit contributions | |
roller | -0.057 |
salon | -0.052 |
post | -0.050 |
pitcher | -0.050 |
heaven | -0.049 |