TOP ACTIVATIONS
MAX = 0.168

. On the way back he saw an old
. On the way , Jenny was so excited
. On the way home something amazing happened .
On the way home from school , Jimmy
. On the way , A str id saw
. On the way home , she heard something
continued walking . Along the way they found a post standing
On the way home , she made a
so excited . On the way , they stopped at a
. On the way back home the car had
walking home . Along the way , she played with a
way home . Along the way , he met some other
. On the way home , Lily saw a
. On the way home , Hannah looked out
. On the way home , Jack was feeling
Along the way , Sally and her mom
Along the way , Mark met some new
. On the way to school , he was
. On the way back home , Betsy could
. On the way home , Tim my thought

MIN ACTIVATIONS
MIN = -0.147

was filled with delicious ch ocol ates . He was happy
the soup , it was ste aming hot ! She pretended
and laughed and ate ch ocol ates . They had a
It was filled with ch ocol ates and coins . She
room . The dish was ste aming hot . It was
inside ! There were ch ocol ates , cookies , and
, and his skin was wrink ly . The frog lived
not eat too many ch ocol ates and his friend learned
that her injury was too severe and she would never be
It was sweet , ch ocol at y and warm ,
nice , but it was wrink led and dirty . She
and dream of horses and ste aks . They are good
pride as they watched it ste aming away on the stove
king ate too many ch ocol ates and his tum my
so it wouldn 't get wrink led . She took her
, cup cakes and ch ocol ates .
unes . They are too wrink ly and sour for cakes
iled and po ached and ste amed and microw aved and
cakes and cookies and ch ocol ates and ice cream .
oll ip ops , ch ocol ates , g ummies ,

INTERVAL 0.089 - 0.168
CONTAINS 0.579%

park . They had the best time playing together on the
then Jack said , " Let 's race inside the tent
smiled and said , " Of course you can ! But
explore . He found a way out of the lake on
wet . Conf used , they started arguing

INTERVAL 0.011 - 0.089
CONTAINS 30.408%

When they arrived , Mia was very excited . She
blue snow man . But you know , snow men are
in its pocket . It me owed to let the child
The peanut stops spinning . It lands on the
the stove . Emily learned an important lesson that

INTERVAL -0.068 - 0.011
CONTAINS 67.597%

chest . " Hmm , it sounds good . You are
slide and Max climbed up to the top . Tim watched
the mint , the basil , and the rose mary .
so lonely . The little girl was about to
shady rock and watched the fish swim in the water below

INTERVAL -0.147 - -0.068
CONTAINS 1.415%

was fun to learn . <|endoftext|> Once upon a time there
, a page with a pizza , and a page with
sorry . They had been mean and greedy .
, so she set off for a walk . She passed
. He wished he was not rude and mean . He
Token.
Token ID13
Feature activation+6.75e-03

Pos logit contributions
ursion+0.041
 bet+0.039
anna+0.039
 Sure+0.037
 sur+0.037
Neg logit contributions
es-0.024
 rats-0.022
ts-0.021
 stains-0.020
 marks-0.020
Token
Token ID198
Feature activation+4.87e-03

Pos logit contributions
ursion+0.012
anna+0.011
ounded+0.011
 bet+0.011
 sur+0.011
Neg logit contributions
es-0.008
 not-0.008
isk-0.007
 mice-0.007
 rats-0.007
Token
Token ID198
Feature activation+6.09e-03

Pos logit contributions
ursion+0.009
 bet+0.009
anna+0.009
 pleasure+0.008
 sur+0.008
Neg logit contributions
es-0.006
 not-0.005
 rats-0.005
ts-0.005
 marks-0.005
TokenOn
Token ID2202
Feature activation+3.03e-02

Pos logit contributions
ursion+0.010
anna+0.010
 bet+0.010
 pleasure+0.010
 Sure+0.009
Neg logit contributions
es-0.008
 rats-0.007
ts-0.007
 not-0.007
 marks-0.007
Token the
Token ID262
Feature activation+3.58e-02

Pos logit contributions
ursion+0.064
 bet+0.062
anna+0.062
 Sure+0.060
Of+0.060
Neg logit contributions
es-0.028
 rats-0.025
 stains-0.024
ts-0.024
 marks-0.023
Token way
Token ID835
Feature activation+1.68e-01

Pos logit contributions
ursion+0.062
anna+0.057
 Sure+0.056
 bet+0.056
Of+0.055
Neg logit contributions
 marks-0.047
 rats-0.047
 not-0.046
 mice-0.046
 puzzles-0.045
Token back
Token ID736
Feature activation+2.05e-02

Pos logit contributions
ursion+0.268
anna+0.259
 bet+0.259
Of+0.251
 pleasure+0.241
Neg logit contributions
es-0.246
 rats-0.218
 not-0.216
 marks-0.211
ts-0.208
Token he
Token ID339
Feature activation+1.41e-02

Pos logit contributions
anna+0.036
ursion+0.035
Of+0.035
 bet+0.033
ya+0.032
Neg logit contributions
es-0.027
ings-0.024
 marks-0.024
 rats-0.024
 not-0.023
Token saw
Token ID2497
Feature activation-3.08e-03

Pos logit contributions
ursion+0.024
anna+0.022
 bet+0.022
Of+0.021
 pleasure+0.021
Neg logit contributions
es-0.020
 rats-0.018
ts-0.018
 marks-0.018
 not-0.018
Token an
Token ID281
Feature activation+2.91e-02

Pos logit contributions
es+0.003
 stains+0.003
 rats+0.003
ts+0.002
bes+0.002
Neg logit contributions
 bet-0.006
ursion-0.006
Of-0.006
anna-0.006
 pleasure-0.006
Token old
Token ID1468
Feature activation+2.70e-02

Pos logit contributions
ursion+0.056
 Sure+0.053
anna+0.053
Of+0.053
 bet+0.052
Neg logit contributions
 rats-0.032
es-0.031
 marks-0.030
 mice-0.030
ts-0.029
Token.
Token ID13
Feature activation+1.74e-02

Pos logit contributions
ursion+0.050
 bet+0.049
anna+0.047
Of+0.047
 sur+0.047
Neg logit contributions
es-0.022
 marks-0.018
 not-0.017
 stains-0.017
 rats-0.016
Token
Token ID198
Feature activation+7.94e-03

Pos logit contributions
 adventurer+0.036
 sur+0.034
ursion+0.034
ya+0.034
anna+0.034
Neg logit contributions
es-0.014
ings-0.013
 not-0.012
't-0.012
 all-0.010
Token
Token ID198
Feature activation+8.18e-03

Pos logit contributions
ursion+0.016
 bet+0.015
 adventurer+0.015
 pleasure+0.015
 sur+0.015
Neg logit contributions
es-0.008
 not-0.007
ings-0.006
 marks-0.006
bes-0.006
TokenOn
Token ID2202
Feature activation+2.98e-02

Pos logit contributions
ursion+0.014
 bet+0.014
 pleasure+0.014
anna+0.014
 Sure+0.013
Neg logit contributions
es-0.010
 not-0.009
 marks-0.009
 stains-0.009
bes-0.009
Token the
Token ID262
Feature activation+3.64e-02

Pos logit contributions
ursion+0.065
 bet+0.063
anna+0.063
Of+0.061
 Sure+0.061
Neg logit contributions
es-0.026
 rats-0.023
ts-0.022
 stains-0.022
 marks-0.021
Token way
Token ID835
Feature activation+1.68e-01

Pos logit contributions
ursion+0.065
 bet+0.061
 sur+0.058
uster+0.056
 Sure+0.056
Neg logit contributions
 pictures-0.051
 marks-0.050
 cookies-0.048
 puzzles-0.048
 all-0.047
Token,
Token ID11
Feature activation+4.39e-03

Pos logit contributions
ursion+0.279
 bet+0.272
anna+0.271
Of+0.260
 pleasure+0.254
Neg logit contributions
es-0.233
 not-0.206
 marks-0.198
 rats-0.197
 stains-0.196
Token Jenny
Token ID28437
Feature activation+2.75e-02

Pos logit contributions
ursion+0.005
anna+0.005
 bet+0.005
 Sure+0.004
Of+0.004
Neg logit contributions
es-0.008
 marks-0.008
 stains-0.008
 rats-0.008
 not-0.008
Token was
Token ID373
Feature activation+9.30e-03

Pos logit contributions
ursion+0.046
 pleasure+0.044
Of+0.043
 bet+0.043
 Sure+0.042
Neg logit contributions
es-0.041
 marks-0.035
 not-0.034
 stains-0.034
ts-0.034
Token so
Token ID523
Feature activation+3.58e-02

Pos logit contributions
ursion+0.016
 bet+0.015
anna+0.015
Of+0.015
 Sure+0.015
Neg logit contributions
es-0.013
 rats-0.011
 not-0.011
ts-0.011
 marks-0.011
Token excited
Token ID6568
Feature activation-9.29e-03

Pos logit contributions
ursion+0.055
anna+0.053
 bet+0.050
 Sure+0.049
Of+0.049
Neg logit contributions
es-0.055
 not-0.053
 rats-0.050
 marks-0.050
ts-0.049
Token.
Token ID13
Feature activation+7.73e-03

Pos logit contributions
es+0.005
 rats+0.004
ts+0.004
 stains+0.004
 marks+0.004
Neg logit contributions
ursion-0.012
 bet-0.012
anna-0.012
 Sure-0.011
Of-0.011
Token
Token ID198
Feature activation+2.83e-03

Pos logit contributions
ursion+0.016
 sur+0.016
 adventurer+0.015
uster+0.014
anna+0.014
Neg logit contributions
es-0.007
 not-0.007
 mice-0.006
 stains-0.006
 rats-0.006
Token
Token ID198
Feature activation+3.14e-03

Pos logit contributions
ursion+0.005
 bet+0.004
anna+0.004
Of+0.004
 sur+0.004
Neg logit contributions
es-0.004
 rats-0.004
ts-0.004
 stains-0.004
 marks-0.004
TokenOn
Token ID2202
Feature activation+2.92e-02

Pos logit contributions
ursion+0.004
 bet+0.004
anna+0.004
Of+0.004
 Sure+0.004
Neg logit contributions
es-0.005
 rats-0.005
ts-0.005
 stains-0.005
 marks-0.005
Token the
Token ID262
Feature activation+3.17e-02

Pos logit contributions
ursion+0.060
 bet+0.058
anna+0.057
 Sure+0.055
 pleasure+0.055
Neg logit contributions
es-0.030
 rats-0.026
ts-0.025
 stains-0.025
 marks-0.024
Token way
Token ID835
Feature activation+1.67e-01

Pos logit contributions
ursion+0.043
 bet+0.039
anna+0.039
 sur+0.038
Of+0.036
Neg logit contributions
 rats-0.054
es-0.053
 puzzles-0.052
 cookies-0.051
 not-0.051
Token home
Token ID1363
Feature activation-6.50e-05

Pos logit contributions
ursion+0.257
 bet+0.247
anna+0.246
Of+0.235
 sur+0.230
Neg logit contributions
es-0.254
 rats-0.231
 not-0.226
 stains-0.225
 marks-0.222
Token something
Token ID1223
Feature activation-2.72e-02

Pos logit contributions
es+0.000
 rats+0.000
ts+0.000
 stains+0.000
 marks+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
 Sure-0.000
Of-0.000
Token amazing
Token ID4998
Feature activation+3.45e-03

Pos logit contributions
es+0.034
 not+0.032
 stains+0.032
 rats+0.032
 marks+0.031
Neg logit contributions
ursion-0.050
anna-0.047
 bet-0.046
 Sure-0.044
Of-0.043
Token happened
Token ID3022
Feature activation+1.30e-02

Pos logit contributions
ursion+0.007
 bet+0.007
anna+0.007
Of+0.006
 Sure+0.006
Neg logit contributions
es-0.004
 rats-0.003
ts-0.003
 stains-0.003
 marks-0.003
Token.
Token ID13
Feature activation+3.82e-03

Pos logit contributions
ursion+0.025
 bet+0.024
anna+0.024
 Sure+0.023
Of+0.023
Neg logit contributions
es-0.014
 rats-0.013
ts-0.013
 stains-0.013
 marks-0.013
Token
Token ID220
Feature activation+3.58e-02

Pos logit contributions
ursion+0.016
 bet+0.014
anna+0.014
ounded+0.014
 sur+0.013
Neg logit contributions
es-0.011
 not-0.010
 mice-0.010
 rats-0.009
 bones-0.009
Token
Token ID198
Feature activation+3.49e-03

Pos logit contributions
ursion+0.054
 bet+0.051
anna+0.051
 Sure+0.048
Of+0.048
Neg logit contributions
es-0.056
 rats-0.052
ts-0.050
 stains-0.050
 marks-0.050
Token
Token ID198
Feature activation+4.77e-03

Pos logit contributions
ursion+0.006
 bet+0.006
anna+0.006
 pleasure+0.006
 sur+0.006
Neg logit contributions
es-0.005
 not-0.004
ts-0.004
 rats-0.004
 marks-0.004
TokenOn
Token ID2202
Feature activation+2.99e-02

Pos logit contributions
ursion+0.007
 bet+0.006
anna+0.006
 Sure+0.006
Of+0.006
Neg logit contributions
es-0.008
 rats-0.007
ts-0.007
 stains-0.007
 marks-0.007
Token the
Token ID262
Feature activation+3.62e-02

Pos logit contributions
ursion+0.066
 bet+0.064
anna+0.064
Of+0.061
 Sure+0.061
Neg logit contributions
es-0.026
 rats-0.023
ts-0.022
 stains-0.021
 marks-0.021
Token way
Token ID835
Feature activation+1.67e-01

Pos logit contributions
ursion+0.063
anna+0.060
uster+0.058
Of+0.058
 Sure+0.058
Neg logit contributions
 not-0.051
 pictures-0.050
 marks-0.049
 puzzles-0.046
 things-0.045
Token home
Token ID1363
Feature activation+7.34e-04

Pos logit contributions
ursion+0.280
anna+0.273
 bet+0.272
Of+0.266
 pleasure+0.251
Neg logit contributions
es-0.231
 not-0.205
 rats-0.202
 marks-0.197
 stains-0.192
Token from
Token ID422
Feature activation-6.16e-03

Pos logit contributions
ursion+0.001
 bet+0.001
anna+0.001
Of+0.001
 Sure+0.001
Neg logit contributions
es-0.001
 rats-0.001
ts-0.001
 stains-0.001
 marks-0.001
Token school
Token ID1524
Feature activation+1.39e-02

Pos logit contributions
es+0.007
 rats+0.006
 stains+0.006
ts+0.006
 marks+0.006
Neg logit contributions
ursion-0.012
 bet-0.012
anna-0.012
 Sure-0.011
 sur-0.011
Token,
Token ID11
Feature activation-7.42e-03

Pos logit contributions
ursion+0.027
 bet+0.026
anna+0.025
Of+0.025
 pleasure+0.024
Neg logit contributions
es-0.017
 rats-0.014
ts-0.014
 marks-0.014
 not-0.014
Token Jimmy
Token ID12963
Feature activation+1.28e-02

Pos logit contributions
es+0.015
 rats+0.014
ts+0.014
 stains+0.014
 marks+0.013
Neg logit contributions
ursion-0.008
 bet-0.007
anna-0.007
 Sure-0.007
Of-0.007
Token.
Token ID13
Feature activation+8.09e-03

Pos logit contributions
es+0.025
 rats+0.022
ts+0.021
 stains+0.021
 marks+0.021
Neg logit contributions
ursion-0.048
 bet-0.047
anna-0.046
Of-0.045
 Sure-0.045
Token
Token ID198
Feature activation+2.09e-03

Pos logit contributions
ursion+0.016
anna+0.016
 adventurer+0.015
 sur+0.015
ya+0.015
Neg logit contributions
es-0.008
 not-0.008
 mice-0.007
ings-0.007
isk-0.007
Token
Token ID198
Feature activation+2.92e-03

Pos logit contributions
ursion+0.004
 bet+0.004
anna+0.003
Of+0.003
 Sure+0.003
Neg logit contributions
es-0.003
 rats-0.003
ts-0.002
 stains-0.002
 marks-0.002
TokenOn
Token ID2202
Feature activation+2.99e-02

Pos logit contributions
ursion+0.005
 bet+0.004
anna+0.004
Of+0.004
 Sure+0.004
Neg logit contributions
es-0.004
 rats-0.004
 stains-0.004
ts-0.004
 marks-0.004
Token the
Token ID262
Feature activation+3.11e-02

Pos logit contributions
ursion+0.065
 bet+0.063
anna+0.063
 Sure+0.060
Of+0.060
Neg logit contributions
es-0.027
 rats-0.023
ts-0.022
 stains-0.022
 marks-0.022
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
 bet+0.049
ursion+0.048
uster+0.045
anna+0.045
 sur+0.045
Neg logit contributions
 cookies-0.047
 sandwiches-0.046
 not-0.045
 puzzles-0.045
 pictures-0.044
Token,
Token ID11
Feature activation+3.64e-03

Pos logit contributions
ursion+0.276
 bet+0.269
anna+0.266
Of+0.260
 sur+0.250
Neg logit contributions
es-0.229
 not-0.208
 rats-0.200
 marks-0.193
 stains-0.191
Token A
Token ID317
Feature activation+4.40e-02

Pos logit contributions
ursion+0.007
anna+0.007
 bet+0.007
Of+0.006
 Sure+0.006
Neg logit contributions
es-0.004
 rats-0.004
ts-0.004
 stains-0.004
 marks-0.004
Tokenstr
Token ID2536
Feature activation+2.16e-02

Pos logit contributions
ursion+0.090
anna+0.087
 bet+0.083
 Sure+0.079
ounded+0.077
Neg logit contributions
 rats-0.043
 mice-0.041
 cookies-0.041
 not-0.040
 marks-0.039
Tokenid
Token ID312
Feature activation-4.53e-04

Pos logit contributions
ursion+0.036
anna+0.035
 bet+0.033
 Sure+0.032
 sur+0.032
Neg logit contributions
es-0.029
 stains-0.028
 rats-0.028
ts-0.028
 sandwiches-0.027
Token saw
Token ID2497
Feature activation-1.52e-02

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 stains+0.001
 marks+0.001
Neg logit contributions
ursion-0.001
 bet-0.001
anna-0.001
Of-0.001
 Sure-0.001
Token.
Token ID13
Feature activation+2.59e-03

Pos logit contributions
es+0.026
 rats+0.024
 stains+0.023
ts+0.023
 marks+0.022
Neg logit contributions
ursion-0.040
 bet-0.039
anna-0.038
 Sure-0.037
 sur-0.037
Token
Token ID198
Feature activation-9.21e-04

Pos logit contributions
ursion+0.004
anna+0.004
 sur+0.004
 bet+0.004
ya+0.004
Neg logit contributions
es-0.004
 not-0.003
 rats-0.003
isk-0.003
 marks-0.003
Token
Token ID198
Feature activation-1.26e-04

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 stains+0.001
 marks+0.001
Neg logit contributions
ursion-0.002
 bet-0.001
anna-0.001
 pleasure-0.001
Of-0.001
TokenOn
Token ID2202
Feature activation+2.96e-02

Pos logit contributions
es+0.000
 rats+0.000
ts+0.000
 stains+0.000
 marks+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
Of-0.000
 Sure-0.000
Token the
Token ID262
Feature activation+3.72e-02

Pos logit contributions
ursion+0.062
 bet+0.060
anna+0.059
 Sure+0.058
Of+0.057
Neg logit contributions
es-0.029
 rats-0.025
 stains-0.024
ts-0.024
 marks-0.024
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.064
anna+0.063
 bet+0.061
 sur+0.060
 pleasure+0.059
Neg logit contributions
 rats-0.051
 mice-0.049
 not-0.049
 marks-0.048
 monsters-0.048
Token home
Token ID1363
Feature activation-1.46e-03

Pos logit contributions
ursion+0.283
anna+0.278
 bet+0.276
Of+0.266
 sur+0.261
Neg logit contributions
es-0.221
 rats-0.200
 not-0.198
 marks-0.187
 stains-0.186
Token,
Token ID11
Feature activation-7.77e-03

Pos logit contributions
es+0.002
 rats+0.002
ts+0.002
 stains+0.002
 marks+0.002
Neg logit contributions
ursion-0.003
 bet-0.002
anna-0.002
 Sure-0.002
Of-0.002
Token she
Token ID673
Feature activation+1.90e-02

Pos logit contributions
es+0.010
 stains+0.010
ts+0.009
 rats+0.009
bes+0.009
Neg logit contributions
ursion-0.013
 bet-0.013
 Sure-0.012
Of-0.012
 pleasure-0.012
Token heard
Token ID2982
Feature activation-8.64e-03

Pos logit contributions
ursion+0.030
 bet+0.029
anna+0.029
Of+0.027
 Sure+0.027
Neg logit contributions
es-0.028
 rats-0.026
ts-0.025
 stains-0.025
 marks-0.025
Token something
Token ID1223
Feature activation-2.46e-02

Pos logit contributions
es+0.008
ts+0.008
 rats+0.007
 stains+0.007
bes+0.007
Neg logit contributions
ursion-0.017
 bet-0.017
anna-0.017
Of-0.017
 Sure-0.016
Token continued
Token ID3767
Feature activation+5.65e-02

Pos logit contributions
ursion+0.016
 bet+0.015
anna+0.015
Of+0.014
 Sure+0.014
Neg logit contributions
es-0.015
 rats-0.014
ts-0.014
 stains-0.014
 marks-0.014
Token walking
Token ID6155
Feature activation+5.68e-02

Pos logit contributions
ursion+0.105
 bet+0.101
anna+0.099
Of+0.096
 Sure+0.095
Neg logit contributions
es-0.070
 rats-0.062
ts-0.060
 stains-0.060
 marks-0.059
Token.
Token ID13
Feature activation+5.36e-03

Pos logit contributions
ursion+0.125
 Shall+0.119
anna+0.119
 pleasure+0.114
Of+0.114
Neg logit contributions
es-0.056
 all-0.049
 not-0.042
ts-0.041
 mice-0.040
Token Along
Token ID17159
Feature activation+8.99e-02

Pos logit contributions
ursion+0.008
 sur+0.007
 bet+0.007
anna+0.007
ounded+0.007
Neg logit contributions
es-0.009
 rats-0.008
 stains-0.008
 not-0.008
 mice-0.008
Token the
Token ID262
Feature activation+3.38e-02

Pos logit contributions
ursion+0.221
anna+0.214
 bet+0.214
Of+0.208
 Sure+0.205
Neg logit contributions
es-0.055
 rats-0.045
ts-0.041
 stains-0.041
 not-0.040
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.051
 Sure+0.048
Of+0.048
anna+0.048
 bet+0.046
Neg logit contributions
 not-0.051
 marks-0.051
 all-0.050
 rats-0.050
 pictures-0.049
Token they
Token ID484
Feature activation+1.80e-02

Pos logit contributions
ursion+0.326
 bet+0.314
anna+0.308
Of+0.305
 sur+0.297
Neg logit contributions
es-0.189
 rats-0.166
 not-0.160
 stains-0.154
 marks-0.151
Token found
Token ID1043
Feature activation-3.00e-03

Pos logit contributions
ursion+0.029
anna+0.028
 bet+0.027
 pleasure+0.026
 Sure+0.026
Neg logit contributions
es-0.027
 rats-0.024
ts-0.024
 stains-0.023
 marks-0.023
Token a
Token ID257
Feature activation+9.34e-03

Pos logit contributions
es+0.003
ts+0.003
 rats+0.003
 stains+0.003
bes+0.003
Neg logit contributions
 bet-0.006
ursion-0.006
 pleasure-0.006
Of-0.006
 Sure-0.006
Token post
Token ID1281
Feature activation+1.52e-02

Pos logit contributions
ursion+0.020
anna+0.019
 bet+0.018
 Sure+0.017
Of+0.017
Neg logit contributions
 rats-0.009
 not-0.008
 marks-0.008
 stains-0.008
es-0.008
Token standing
Token ID5055
Feature activation-1.35e-02

Pos logit contributions
ursion+0.029
 bet+0.028
anna+0.028
Of+0.027
 Sure+0.027
Neg logit contributions
es-0.017
 rats-0.016
ts-0.015
 stains-0.015
 marks-0.015
Token
Token ID220
Feature activation+3.47e-02

Pos logit contributions
 sur+0.011
ursion+0.010
 adventurer+0.010
den+0.010
ya+0.010
Neg logit contributions
es-0.007
 not-0.006
isk-0.005
 mice-0.005
't-0.005
Token
Token ID198
Feature activation+1.71e-03

Pos logit contributions
ursion+0.060
 bet+0.058
anna+0.056
 sur+0.055
Of+0.054
Neg logit contributions
es-0.048
 not-0.041
 rats-0.040
 marks-0.039
 stains-0.039
Token
Token ID198
Feature activation+2.28e-03

Pos logit contributions
ursion+0.003
 bet+0.003
anna+0.003
 pleasure+0.003
 sur+0.003
Neg logit contributions
es-0.002
 not-0.002
ts-0.002
 rats-0.002
 marks-0.002
TokenOn
Token ID2202
Feature activation+2.85e-02

Pos logit contributions
ursion+0.004
 bet+0.003
anna+0.003
Of+0.003
 Sure+0.003
Neg logit contributions
es-0.003
 rats-0.003
ts-0.003
 stains-0.003
 marks-0.003
Token the
Token ID262
Feature activation+3.56e-02

Pos logit contributions
ursion+0.063
 bet+0.061
anna+0.060
 Sure+0.058
Of+0.058
Neg logit contributions
es-0.025
 rats-0.022
ts-0.021
 stains-0.021
 marks-0.020
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.061
 bet+0.057
 Sure+0.054
 sur+0.053
anna+0.053
Neg logit contributions
 cookies-0.050
 rats-0.050
 not-0.049
 ow-0.049
 marks-0.049
Token home
Token ID1363
Feature activation-5.94e-04

Pos logit contributions
ursion+0.268
 bet+0.261
anna+0.259
Of+0.249
 sur+0.243
Neg logit contributions
es-0.236
 rats-0.212
 not-0.211
 stains-0.203
 marks-0.202
Token,
Token ID11
Feature activation-6.49e-03

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 stains+0.001
 marks+0.001
Neg logit contributions
ursion-0.001
 bet-0.001
anna-0.001
 Sure-0.001
Of-0.001
Token she
Token ID673
Feature activation+1.80e-02

Pos logit contributions
es+0.007
 rats+0.006
 stains+0.006
ts+0.006
 marks+0.006
Neg logit contributions
ursion-0.013
 bet-0.013
anna-0.013
 Sure-0.012
Of-0.012
Token made
Token ID925
Feature activation-3.27e-02

Pos logit contributions
ursion+0.029
 bet+0.027
anna+0.027
Of+0.026
 Sure+0.026
Neg logit contributions
es-0.026
 rats-0.024
ts-0.024
 stains-0.024
 marks-0.023
Token a
Token ID257
Feature activation-2.40e-03

Pos logit contributions
es+0.037
 rats+0.034
ts+0.033
adoes+0.031
 stains+0.031
Neg logit contributions
anna-0.059
 bet-0.058
 pleasure-0.057
ursion-0.057
Of-0.056
Token so
Token ID523
Feature activation+3.83e-02

Pos logit contributions
ursion+0.024
 bet+0.023
anna+0.023
 Sure+0.022
Of+0.022
Neg logit contributions
es-0.020
 not-0.018
 rats-0.018
ts-0.018
 marks-0.017
Token excited
Token ID6568
Feature activation-7.30e-03

Pos logit contributions
ursion+0.057
anna+0.053
 bet+0.053
 Sure+0.052
Of+0.051
Neg logit contributions
es-0.061
 not-0.056
ts-0.055
 rats-0.054
 marks-0.053
Token.
Token ID13
Feature activation+8.92e-03

Pos logit contributions
es+0.009
 rats+0.008
ts+0.008
 stains+0.008
 marks+0.008
Neg logit contributions
ursion-0.013
 bet-0.013
anna-0.013
 Sure-0.012
Of-0.012
Token On
Token ID1550
Feature activation+3.68e-02

Pos logit contributions
ursion+0.018
anna+0.018
ounded+0.017
 sur+0.017
ya+0.017
Neg logit contributions
es-0.008
 not-0.007
 marks-0.007
 bones-0.007
 mice-0.007
Token the
Token ID262
Feature activation+3.32e-02

Pos logit contributions
ursion+0.078
 bet+0.076
anna+0.076
Of+0.073
 Sure+0.073
Neg logit contributions
es-0.034
 rats-0.030
ts-0.029
 stains-0.029
 marks-0.028
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.058
 bet+0.054
Of+0.053
 Sure+0.053
 Shall+0.051
Neg logit contributions
 not-0.044
 marks-0.044
 pictures-0.044
es-0.043
 puzzles-0.043
Token,
Token ID11
Feature activation+2.64e-03

Pos logit contributions
ursion+0.294
anna+0.289
 bet+0.283
Of+0.282
 sur+0.266
Neg logit contributions
es-0.215
 not-0.189
 marks-0.180
 rats-0.179
 stains-0.172
Token they
Token ID484
Feature activation+1.58e-02

Pos logit contributions
ursion+0.004
 bet+0.004
anna+0.004
 Sure+0.004
Of+0.004
Neg logit contributions
es-0.004
 rats-0.004
ts-0.004
 stains-0.004
 marks-0.003
Token stopped
Token ID5025
Feature activation+2.22e-02

Pos logit contributions
ursion+0.025
anna+0.023
 bet+0.023
 Sure+0.022
Of+0.022
Neg logit contributions
es-0.024
ts-0.022
 rats-0.022
 stains-0.021
 marks-0.021
Token at
Token ID379
Feature activation-2.98e-03

Pos logit contributions
ursion+0.040
 bet+0.038
anna+0.038
 Sure+0.036
Of+0.036
Neg logit contributions
es-0.028
 rats-0.026
ts-0.025
 stains-0.025
 marks-0.024
Token a
Token ID257
Feature activation+3.23e-02

Pos logit contributions
es+0.003
 rats+0.003
 stains+0.003
ts+0.002
adoes+0.002
Neg logit contributions
 bet-0.006
ursion-0.006
 Sure-0.006
 pleasure-0.006
anna-0.006
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
ursion+0.030
anna+0.029
Of+0.028
ounded+0.027
 bet+0.027
Neg logit contributions
es-0.013
 marks-0.011
 not-0.011
ts-0.010
 stains-0.010
Token
Token ID198
Feature activation+2.41e-03

Pos logit contributions
ursion+0.022
ounded+0.021
 sur+0.021
anna+0.021
ya+0.020
Neg logit contributions
es-0.013
 mice-0.011
 not-0.011
isk-0.010
 rats-0.010
Token
Token ID198
Feature activation+2.60e-03

Pos logit contributions
ursion+0.004
 bet+0.004
anna+0.004
Of+0.004
 Sure+0.004
Neg logit contributions
es-0.003
 rats-0.003
ts-0.003
 stains-0.002
 marks-0.002
TokenOn
Token ID2202
Feature activation+3.26e-02

Pos logit contributions
ursion+0.004
anna+0.004
 bet+0.004
 Sure+0.004
Of+0.004
Neg logit contributions
es-0.004
 rats-0.003
ts-0.003
 stains-0.003
 marks-0.003
Token the
Token ID262
Feature activation+3.20e-02

Pos logit contributions
ursion+0.070
 bet+0.068
anna+0.067
 Sure+0.065
Of+0.065
Neg logit contributions
es-0.030
 rats-0.026
ts-0.025
 stains-0.025
 marks-0.024
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.051
anna+0.046
 bet+0.045
 Sure+0.044
Of+0.044
Neg logit contributions
 puzzles-0.048
 marks-0.048
 not-0.048
 pictures-0.047
 cookies-0.046
Token back
Token ID736
Feature activation+2.01e-02

Pos logit contributions
ursion+0.303
anna+0.296
Of+0.294
 bet+0.291
 sur+0.274
Neg logit contributions
es-0.207
 not-0.185
 marks-0.175
 rats-0.171
 stains-0.167
Token home
Token ID1363
Feature activation-2.59e-03

Pos logit contributions
anna+0.038
Of+0.037
ursion+0.036
 bet+0.034
 Shall+0.034
Neg logit contributions
es-0.025
 marks-0.023
ings-0.023
 not-0.021
 rats-0.021
Token the
Token ID262
Feature activation+2.99e-02

Pos logit contributions
es+0.003
 rats+0.003
ts+0.003
 stains+0.003
 marks+0.003
Neg logit contributions
ursion-0.005
 bet-0.004
anna-0.004
 Sure-0.004
Of-0.004
Token car
Token ID1097
Feature activation+2.18e-02

Pos logit contributions
ursion+0.053
anna+0.050
 bet+0.050
 Sure+0.047
Of+0.047
Neg logit contributions
es-0.037
 rats-0.037
 marks-0.035
 stains-0.035
ts-0.035
Token had
Token ID550
Feature activation-1.40e-02

Pos logit contributions
ursion+0.041
 bet+0.039
anna+0.039
Of+0.038
 pleasure+0.037
Neg logit contributions
es-0.027
 rats-0.023
 marks-0.023
ts-0.023
 not-0.022
Token walking
Token ID6155
Feature activation+4.43e-02

Pos logit contributions
ursion+0.056
 bet+0.054
anna+0.054
 Sure+0.051
Of+0.051
Neg logit contributions
es-0.048
 rats-0.044
ts-0.043
 stains-0.043
 marks-0.042
Token home
Token ID1363
Feature activation-3.54e-02

Pos logit contributions
ursion+0.094
anna+0.089
 bet+0.089
Of+0.086
 pleasure+0.085
Neg logit contributions
es-0.044
 rats-0.036
ts-0.036
 not-0.036
 marks-0.035
Token.
Token ID13
Feature activation-2.22e-03

Pos logit contributions
es+0.039
 rats+0.037
 stains+0.036
ts+0.035
 marks+0.035
Neg logit contributions
ursion-0.066
 bet-0.065
anna-0.064
 Sure-0.062
 sur-0.061
Token Along
Token ID17159
Feature activation+8.86e-02

Pos logit contributions
es+0.003
 not+0.002
 mice+0.002
 rats+0.002
isk+0.002
Neg logit contributions
 sur-0.004
ursion-0.004
anna-0.004
 bet-0.004
ounded-0.004
Token the
Token ID262
Feature activation+3.40e-02

Pos logit contributions
ursion+0.210
 bet+0.204
anna+0.204
Of+0.198
 Sure+0.195
Neg logit contributions
es-0.062
 rats-0.051
ts-0.048
 stains-0.047
 marks-0.046
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.052
anna+0.049
uster+0.049
 sur+0.048
 bet+0.048
Neg logit contributions
 not-0.053
 pictures-0.051
 rats-0.050
 animals-0.049
 marks-0.049
Token,
Token ID11
Feature activation-2.53e-03

Pos logit contributions
ursion+0.325
 bet+0.316
anna+0.312
Of+0.308
 sur+0.299
Neg logit contributions
es-0.185
 rats-0.159
 not-0.158
 marks-0.147
 stains-0.147
Token she
Token ID673
Feature activation+2.13e-02

Pos logit contributions
es+0.004
 stains+0.004
 rats+0.004
 marks+0.004
ts+0.004
Neg logit contributions
ursion-0.004
 bet-0.004
anna-0.003
 Sure-0.003
Of-0.003
Token played
Token ID2826
Feature activation-2.70e-02

Pos logit contributions
ursion+0.037
 bet+0.034
anna+0.034
Of+0.033
 pleasure+0.033
Neg logit contributions
es-0.030
ts-0.026
 rats-0.026
 not-0.026
 marks-0.025
Token with
Token ID351
Feature activation-5.57e-03

Pos logit contributions
 stains+0.033
 rats+0.032
es+0.032
oni+0.031
 burns+0.031
Neg logit contributions
 bet-0.046
ursion-0.043
 Sure-0.043
Of-0.042
anna-0.042
Token a
Token ID257
Feature activation+4.81e-03

Pos logit contributions
es+0.007
 stains+0.006
bes+0.006
ts+0.006
oni+0.006
Neg logit contributions
 bet-0.009
 pleasure-0.009
ursion-0.009
 Sure-0.009
Of-0.009
Token way
Token ID835
Feature activation+1.22e-01

Pos logit contributions
es+0.040
 rats+0.040
 marks+0.039
 not+0.038
 stains+0.038
Neg logit contributions
ursion-0.052
anna-0.049
 bet-0.048
Of-0.047
 Sure-0.046
Token home
Token ID1363
Feature activation-3.02e-02

Pos logit contributions
ursion+0.217
anna+0.211
 bet+0.208
Of+0.202
 Sure+0.198
Neg logit contributions
 not-0.150
es-0.149
 marks-0.139
 stains-0.136
 rats-0.135
Token.
Token ID13
Feature activation+4.17e-03

Pos logit contributions
es+0.036
 rats+0.034
 stains+0.032
ts+0.031
 mice+0.031
Neg logit contributions
ursion-0.053
 bet-0.052
anna-0.052
 Sure-0.050
 pleasure-0.049
Token Along
Token ID17159
Feature activation+9.17e-02

Pos logit contributions
ursion+0.007
anna+0.006
 bet+0.006
 sur+0.006
Of+0.006
Neg logit contributions
es-0.006
 not-0.005
 rats-0.005
 marks-0.005
isk-0.005
Token the
Token ID262
Feature activation+3.47e-02

Pos logit contributions
ursion+0.213
 bet+0.206
anna+0.206
Of+0.199
 Sure+0.197
Neg logit contributions
es-0.068
 rats-0.058
ts-0.055
 stains-0.054
 marks-0.053
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.049
Of+0.046
 sur+0.044
 bet+0.043
 Sure+0.043
Neg logit contributions
 marks-0.060
 rats-0.059
 not-0.058
es-0.057
 monsters-0.057
Token,
Token ID11
Feature activation-2.78e-03

Pos logit contributions
ursion+0.323
 bet+0.314
anna+0.313
Of+0.303
 pleasure+0.294
Neg logit contributions
es-0.187
 rats-0.166
 not-0.160
 marks-0.152
 stains-0.149
Token he
Token ID339
Feature activation+8.93e-03

Pos logit contributions
es+0.004
 rats+0.004
ts+0.004
 not+0.004
 marks+0.004
Neg logit contributions
ursion-0.004
anna-0.004
 bet-0.004
Of-0.004
 Sure-0.004
Token met
Token ID1138
Feature activation+2.11e-02

Pos logit contributions
ursion+0.013
 bet+0.013
anna+0.013
 Sure+0.012
 sur+0.012
Neg logit contributions
es-0.014
 rats-0.013
 stains-0.013
ts-0.013
 marks-0.012
Token some
Token ID617
Feature activation-1.29e-02

Pos logit contributions
 bet+0.040
Of+0.039
ursion+0.039
anna+0.039
 pleasure+0.039
Neg logit contributions
es-0.021
 stains-0.020
ts-0.020
 rats-0.019
bes-0.019
Token other
Token ID584
Feature activation+8.44e-02

Pos logit contributions
es+0.015
 rats+0.013
ts+0.013
 stains+0.013
 marks+0.013
Neg logit contributions
ursion-0.025
 bet-0.024
anna-0.024
 Sure-0.023
Of-0.023
Token.
Token ID13
Feature activation-6.48e-04

Pos logit contributions
es+0.037
 rats+0.034
ts+0.033
 stains+0.032
 marks+0.032
Neg logit contributions
ursion-0.052
 bet-0.050
anna-0.049
Of-0.048
 pleasure-0.047
Token
Token ID198
Feature activation-3.00e-03

Pos logit contributions
es+0.001
 not+0.001
 stains+0.001
 marks+0.001
adoes+0.001
Neg logit contributions
ursion-0.001
 sur-0.001
 bet-0.001
anna-0.001
 pleasure-0.001
Token
Token ID198
Feature activation-2.08e-03

Pos logit contributions
es+0.004
 not+0.004
 rats+0.004
 marks+0.004
 stains+0.003
Neg logit contributions
ursion-0.005
 bet-0.005
anna-0.005
 pleasure-0.005
 sur-0.005
TokenOn
Token ID2202
Feature activation+2.43e-02

Pos logit contributions
es+0.003
 rats+0.003
ts+0.003
 stains+0.003
 marks+0.003
Neg logit contributions
ursion-0.003
anna-0.003
 bet-0.003
Of-0.003
 Sure-0.003
Token the
Token ID262
Feature activation+3.11e-02

Pos logit contributions
ursion+0.049
 bet+0.047
anna+0.046
 Sure+0.046
Of+0.045
Neg logit contributions
es-0.026
 rats-0.023
ts-0.021
 stains-0.021
 marks-0.021
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.034
 bet+0.032
anna+0.031
 sur+0.030
 pleasure+0.028
Neg logit contributions
es-0.061
 rats-0.060
 not-0.060
 puzzles-0.059
 stains-0.059
Token home
Token ID1363
Feature activation-9.56e-04

Pos logit contributions
ursion+0.230
 bet+0.217
anna+0.215
 Sure+0.204
Of+0.202
Neg logit contributions
es-0.278
 rats-0.260
ts-0.257
 stains-0.254
 marks-0.251
Token,
Token ID11
Feature activation-1.19e-02

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 stains+0.001
 marks+0.001
Neg logit contributions
ursion-0.002
 bet-0.002
anna-0.001
 Sure-0.001
Of-0.001
Token Lily
Token ID20037
Feature activation+1.32e-02

Pos logit contributions
es+0.019
ts+0.017
 rats+0.017
 marks+0.017
 stains+0.017
Neg logit contributions
ursion-0.016
 bet-0.016
 Sure-0.016
Of-0.015
anna-0.015
Token saw
Token ID2497
Feature activation-1.26e-02

Pos logit contributions
ursion+0.020
 bet+0.019
anna+0.019
 Sure+0.018
Of+0.018
Neg logit contributions
es-0.020
 rats-0.019
ts-0.018
 stains-0.018
 marks-0.018
Token a
Token ID257
Feature activation+6.18e-03

Pos logit contributions
es+0.016
bes+0.015
ts+0.015
icer+0.015
ink+0.014
Neg logit contributions
Of-0.021
ursion-0.019
 bet-0.019
 Sure-0.019
 pleasure-0.019
Token.
Token ID13
Feature activation+5.76e-03

Pos logit contributions
es+0.021
 not+0.018
 marks+0.017
 rats+0.017
 stains+0.017
Neg logit contributions
ursion-0.045
 bet-0.043
anna-0.042
Of-0.041
 Sure-0.040
Token
Token ID198
Feature activation+1.28e-03

Pos logit contributions
ursion+0.009
 bet+0.009
 sur+0.009
anna+0.009
den+0.009
Neg logit contributions
es-0.007
 not-0.007
 stains-0.007
 accidents-0.006
ings-0.006
Token
Token ID198
Feature activation+1.82e-03

Pos logit contributions
ursion+0.003
 bet+0.003
anna+0.003
 Sure+0.002
Of+0.002
Neg logit contributions
es-0.001
 rats-0.001
 stains-0.001
ts-0.001
 marks-0.001
TokenOn
Token ID2202
Feature activation+2.84e-02

Pos logit contributions
ursion+0.003
 bet+0.003
anna+0.003
 Sure+0.002
 pleasure+0.002
Neg logit contributions
es-0.003
 rats-0.003
 stains-0.003
ts-0.003
 marks-0.003
Token the
Token ID262
Feature activation+3.47e-02

Pos logit contributions
ursion+0.063
 bet+0.061
anna+0.061
Of+0.059
 Sure+0.059
Neg logit contributions
es-0.024
 rats-0.021
ts-0.020
 stains-0.020
 marks-0.019
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.064
 bet+0.062
anna+0.060
uster+0.059
 Sure+0.057
Neg logit contributions
 not-0.044
 sandwiches-0.043
 marks-0.042
 pictures-0.041
 cookies-0.040
Token home
Token ID1363
Feature activation-7.87e-04

Pos logit contributions
ursion+0.277
 bet+0.275
anna+0.266
Of+0.261
 sur+0.255
Neg logit contributions
es-0.223
 not-0.202
 rats-0.189
 stains-0.188
 marks-0.186
Token,
Token ID11
Feature activation-7.00e-03

Pos logit contributions
es+0.001
 rats+0.001
 stains+0.001
ts+0.001
 marks+0.001
Neg logit contributions
ursion-0.001
 bet-0.001
anna-0.001
Of-0.001
 Sure-0.001
Token Hannah
Token ID26013
Feature activation+3.20e-02

Pos logit contributions
es+0.013
 rats+0.012
 stains+0.012
ts+0.012
 marks+0.012
Neg logit contributions
ursion-0.008
 bet-0.008
anna-0.008
 Sure-0.007
Of-0.007
Token looked
Token ID3114
Feature activation+1.66e-02

Pos logit contributions
ursion+0.055
 bet+0.052
 pleasure+0.051
Of+0.050
 Sure+0.050
Neg logit contributions
es-0.045
 not-0.039
ts-0.038
 rats-0.038
 marks-0.038
Token out
Token ID503
Feature activation+3.09e-02

Pos logit contributions
ursion+0.033
 bet+0.031
anna+0.031
Of+0.030
 Sure+0.030
Neg logit contributions
es-0.018
 not-0.016
 stains-0.015
 rats-0.015
 marks-0.015
Token.
Token ID13
Feature activation+1.00e-02

Pos logit contributions
es+0.032
 rats+0.028
 stains+0.027
ts+0.027
 not+0.027
Neg logit contributions
ursion-0.066
 bet-0.063
anna-0.062
Of-0.060
 Sure-0.060
Token
Token ID198
Feature activation+3.54e-03

Pos logit contributions
ursion+0.020
anna+0.020
 bet+0.019
 sur+0.019
fy+0.018
Neg logit contributions
 not-0.010
es-0.009
 mice-0.008
oni-0.008
 marks-0.008
Token
Token ID198
Feature activation+4.40e-03

Pos logit contributions
ursion+0.007
 pleasure+0.007
 bet+0.007
anna+0.007
 adventurer+0.007
Neg logit contributions
es-0.004
 not-0.003
oni-0.003
 marks-0.003
ings-0.003
TokenOn
Token ID2202
Feature activation+2.92e-02

Pos logit contributions
ursion+0.008
 pleasure+0.008
anna+0.008
 bet+0.008
 sur+0.007
Neg logit contributions
es-0.005
 not-0.005
 marks-0.004
 mice-0.004
ts-0.004
Token the
Token ID262
Feature activation+3.38e-02

Pos logit contributions
ursion+0.062
 bet+0.060
anna+0.060
 Sure+0.058
Of+0.058
Neg logit contributions
es-0.027
 rats-0.024
 stains-0.023
ts-0.023
 marks-0.022
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.053
uster+0.050
anna+0.050
 Sure+0.048
 bet+0.048
Neg logit contributions
 not-0.051
 pictures-0.051
 marks-0.050
 puzzles-0.050
 cookies-0.049
Token home
Token ID1363
Feature activation-2.29e-04

Pos logit contributions
ursion+0.269
anna+0.263
 bet+0.261
Of+0.252
 pleasure+0.243
Neg logit contributions
es-0.236
 not-0.209
 rats-0.209
 marks-0.204
 stains-0.200
Token,
Token ID11
Feature activation-3.17e-03

Pos logit contributions
es+0.000
 rats+0.000
ts+0.000
 stains+0.000
 marks+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
Of-0.000
 Sure-0.000
Token Jack
Token ID3619
Feature activation+1.72e-02

Pos logit contributions
es+0.005
 rats+0.005
ts+0.005
 marks+0.005
 stains+0.005
Neg logit contributions
ursion-0.005
anna-0.004
 bet-0.004
Of-0.004
 Sure-0.004
Token was
Token ID373
Feature activation+8.43e-03

Pos logit contributions
ursion+0.027
 bet+0.025
anna+0.025
Of+0.025
 pleasure+0.025
Neg logit contributions
es-0.027
 rats-0.024
 marks-0.023
ts-0.023
 not-0.023
Token feeling
Token ID4203
Feature activation-3.12e-02

Pos logit contributions
ursion+0.014
 bet+0.014
anna+0.014
Of+0.013
 Sure+0.013
Neg logit contributions
es-0.011
 rats-0.010
ts-0.010
 stains-0.010
 marks-0.010
Token
Token ID220
Feature activation+3.01e-02

Pos logit contributions
den+0.008
ursion+0.008
anna+0.008
 sur+0.008
 adventurer+0.007
Neg logit contributions
 not-0.005
es-0.005
ings-0.005
 mice-0.005
isk-0.004
Token
Token ID198
Feature activation-2.56e-03

Pos logit contributions
ursion+0.050
 bet+0.048
anna+0.047
 sur+0.045
Of+0.045
Neg logit contributions
es-0.043
 rats-0.037
 not-0.037
 marks-0.037
 stains-0.037
Token
Token ID198
Feature activation-2.81e-04

Pos logit contributions
es+0.003
 not+0.003
 stains+0.003
 marks+0.003
 rats+0.003
Neg logit contributions
ursion-0.004
anna-0.004
 bet-0.004
 pleasure-0.004
 Sure-0.004
TokenAlong
Token ID24035
Feature activation+1.12e-01

Pos logit contributions
es+0.000
 rats+0.000
ts+0.000
 stains+0.000
 marks+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
 Sure-0.000
Of-0.000
Token the
Token ID262
Feature activation+3.63e-02

Pos logit contributions
ursion+0.263
anna+0.258
Of+0.257
 bet+0.256
 Sure+0.252
Neg logit contributions
es-0.074
 marks-0.052
 not-0.052
 stains-0.051
 rats-0.050
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.050
 Sure+0.049
Of+0.049
 bet+0.048
anna+0.048
Neg logit contributions
 pictures-0.059
 marks-0.058
 not-0.056
 puzzles-0.055
 all-0.054
Token,
Token ID11
Feature activation-9.60e-04

Pos logit contributions
ursion+0.337
Of+0.324
 bet+0.323
anna+0.319
 sur+0.311
Neg logit contributions
es-0.173
 not-0.153
 rats-0.136
ings-0.135
 marks-0.131
Token Sally
Token ID25737
Feature activation+2.46e-02

Pos logit contributions
es+0.002
 rats+0.001
 not+0.001
 stains+0.001
 mice+0.001
Neg logit contributions
ursion-0.001
anna-0.001
 bet-0.001
 Sure-0.001
 sur-0.001
Token and
Token ID290
Feature activation+2.03e-02

Pos logit contributions
ursion+0.043
 bet+0.040
Of+0.039
 pleasure+0.039
 Sure+0.039
Neg logit contributions
es-0.034
 marks-0.029
 not-0.029
 rats-0.029
 stains-0.029
Token her
Token ID607
Feature activation+1.49e-03

Pos logit contributions
ursion+0.040
 bet+0.039
anna+0.039
Of+0.037
 Sure+0.037
Neg logit contributions
es-0.022
 rats-0.020
ts-0.020
 stains-0.019
 marks-0.018
Token mom
Token ID1995
Feature activation-3.87e-02

Pos logit contributions
ursion+0.003
 bet+0.003
anna+0.003
Of+0.003
 Sure+0.003
Neg logit contributions
es-0.002
 rats-0.001
ts-0.001
 stains-0.001
 marks-0.001
Token
Token ID220
Feature activation+3.69e-02

Pos logit contributions
ursion+0.025
ya+0.025
anna+0.025
ounded+0.025
 sur+0.024
Neg logit contributions
es-0.011
 not-0.010
isk-0.009
 mice-0.009
 bones-0.009
Token
Token ID198
Feature activation+6.69e-03

Pos logit contributions
ursion+0.059
 bet+0.056
anna+0.056
Of+0.053
 sur+0.053
Neg logit contributions
es-0.055
 rats-0.049
ts-0.048
 marks-0.047
 stains-0.047
Token
Token ID198
Feature activation+8.99e-03

Pos logit contributions
ursion+0.013
anna+0.012
 bet+0.012
 pleasure+0.012
ounded+0.011
Neg logit contributions
es-0.008
 not-0.007
bes-0.006
ts-0.006
isk-0.006
TokenAlong
Token ID24035
Feature activation+1.10e-01

Pos logit contributions
ursion+0.015
anna+0.014
 bet+0.014
 pleasure+0.014
 Sure+0.013
Neg logit contributions
es-0.013
 rats-0.011
 not-0.011
ts-0.011
 marks-0.011
Token the
Token ID262
Feature activation+3.89e-02

Pos logit contributions
ursion+0.242
anna+0.239
 bet+0.237
Of+0.236
 pleasure+0.230
Neg logit contributions
es-0.094
ts-0.073
 rats-0.072
 marks-0.071
 stains-0.068
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
Of+0.056
ursion+0.055
anna+0.053
 Sure+0.052
 bet+0.052
Neg logit contributions
 pictures-0.061
 puzzles-0.058
 marks-0.058
 not-0.058
 rats-0.056
Token,
Token ID11
Feature activation+4.12e-03

Pos logit contributions
ursion+0.323
anna+0.314
 bet+0.314
Of+0.314
 pleasure+0.297
Neg logit contributions
es-0.190
 not-0.158
 rats-0.155
 marks-0.150
ts-0.145
Token Mark
Token ID2940
Feature activation+2.23e-02

Pos logit contributions
ursion+0.007
 bet+0.007
anna+0.007
Of+0.006
 Sure+0.006
Neg logit contributions
es-0.006
 rats-0.005
ts-0.005
 stains-0.005
 marks-0.005
Token met
Token ID1138
Feature activation+1.78e-02

Pos logit contributions
ursion+0.039
 bet+0.036
Of+0.036
 pleasure+0.035
 Sure+0.035
Neg logit contributions
es-0.032
 rats-0.028
ts-0.028
 marks-0.027
 stains-0.027
Token some
Token ID617
Feature activation-1.53e-02

Pos logit contributions
ursion+0.036
 bet+0.036
anna+0.035
Of+0.034
 Sure+0.034
Neg logit contributions
es-0.017
 stains-0.015
 rats-0.015
ts-0.015
 marks-0.014
Token new
Token ID649
Feature activation+5.57e-02

Pos logit contributions
es+0.018
 rats+0.017
ts+0.016
 marks+0.016
 mice+0.015
Neg logit contributions
ursion-0.030
anna-0.028
 bet-0.028
 Sure-0.027
Of-0.027
Token.
Token ID13
Feature activation+4.25e-03

Pos logit contributions
es+0.030
 rats+0.026
ts+0.025
 stains+0.025
 marks+0.025
Neg logit contributions
ursion-0.059
 bet-0.057
anna-0.057
Of-0.055
 Sure-0.055
Token
Token ID198
Feature activation+1.45e-03

Pos logit contributions
ursion+0.008
 bet+0.007
ounded+0.007
anna+0.007
 sur+0.007
Neg logit contributions
es-0.005
 not-0.005
 mice-0.005
 rats-0.004
 bones-0.004
Token
Token ID198
Feature activation+2.86e-03

Pos logit contributions
ursion+0.003
 bet+0.002
anna+0.002
 pleasure+0.002
 sur+0.002
Neg logit contributions
es-0.002
 rats-0.002
 not-0.002
ts-0.002
 marks-0.002
TokenOn
Token ID2202
Feature activation+2.86e-02

Pos logit contributions
ursion+0.004
 bet+0.004
anna+0.004
 Sure+0.004
Of+0.004
Neg logit contributions
es-0.004
 rats-0.004
ts-0.004
 stains-0.004
 marks-0.004
Token the
Token ID262
Feature activation+3.09e-02

Pos logit contributions
ursion+0.060
 bet+0.058
anna+0.057
 Sure+0.056
 pleasure+0.055
Neg logit contributions
es-0.028
 rats-0.025
 stains-0.023
ts-0.023
 marks-0.023
Token way
Token ID835
Feature activation+1.66e-01

Pos logit contributions
ursion+0.047
 bet+0.043
anna+0.042
Of+0.041
 sur+0.040
Neg logit contributions
 puzzles-0.049
 not-0.049
 marks-0.049
 cookies-0.048
 pictures-0.047
Token to
Token ID284
Feature activation-1.58e-03

Pos logit contributions
ursion+0.285
anna+0.277
 bet+0.276
Of+0.272
 pleasure+0.257
Neg logit contributions
es-0.224
 not-0.195
 rats-0.195
 marks-0.189
 stains-0.183
Token school
Token ID1524
Feature activation+1.59e-02

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 marks+0.001
 stains+0.001
Neg logit contributions
ursion-0.004
anna-0.004
 bet-0.004
Of-0.003
 Sure-0.003
Token,
Token ID11
Feature activation-6.13e-03

Pos logit contributions
ursion+0.031
 bet+0.030
anna+0.029
Of+0.029
 pleasure+0.028
Neg logit contributions
es-0.019
 rats-0.016
ts-0.016
 not-0.016
 marks-0.016
Token he
Token ID339
Feature activation+6.76e-03

Pos logit contributions
es+0.009
 rats+0.008
 stains+0.008
ts+0.008
 marks+0.008
Neg logit contributions
ursion-0.010
 bet-0.010
anna-0.009
 Sure-0.009
Of-0.009
Token was
Token ID373
Feature activation+6.81e-03

Pos logit contributions
ursion+0.010
 bet+0.010
anna+0.010
 Sure+0.009
 sur+0.009
Neg logit contributions
es-0.010
 rats-0.010
 stains-0.009
ts-0.009
 marks-0.009
Token.
Token ID13
Feature activation+4.20e-03

Pos logit contributions
ursion+0.045
 bet+0.042
anna+0.042
Of+0.041
 Sure+0.040
Neg logit contributions
es-0.023
 rats-0.020
 marks-0.019
 stains-0.019
 not-0.019
Token
Token ID198
Feature activation-1.99e-04

Pos logit contributions
 sur+0.008
ursion+0.008
ounded+0.007
 bet+0.007
anna+0.007
Neg logit contributions
es-0.005
 mice-0.004
isk-0.004
 not-0.004
 rats-0.004
Token
Token ID198
Feature activation+1.14e-03

Pos logit contributions
es+0.000
 not+0.000
 rats+0.000
ts+0.000
 marks+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
 pleasure-0.000
 sur-0.000
TokenOn
Token ID2202
Feature activation+3.08e-02

Pos logit contributions
ursion+0.002
anna+0.002
 bet+0.002
 pleasure+0.002
 Sure+0.002
Neg logit contributions
es-0.002
 rats-0.002
ts-0.002
 stains-0.001
 marks-0.001
Token the
Token ID262
Feature activation+3.19e-02

Pos logit contributions
ursion+0.063
 bet+0.061
anna+0.060
 Sure+0.058
 pleasure+0.058
Neg logit contributions
es-0.030
 rats-0.028
ts-0.026
 stains-0.026
 mice-0.025
Token way
Token ID835
Feature activation+1.65e-01

Pos logit contributions
ursion+0.052
 bet+0.047
anna+0.047
 sur+0.045
 Sure+0.044
Neg logit contributions
 marks-0.049
 cookies-0.048
 puzzles-0.048
 pictures-0.048
 stains-0.046
Token back
Token ID736
Feature activation+1.88e-02

Pos logit contributions
ursion+0.281
 bet+0.271
anna+0.270
Of+0.261
 sur+0.254
Neg logit contributions
es-0.227
 rats-0.201
 marks-0.196
 stains-0.195
 not-0.195
Token home
Token ID1363
Feature activation-5.52e-03

Pos logit contributions
anna+0.035
ursion+0.034
Of+0.034
 bet+0.032
 Shall+0.031
Neg logit contributions
es-0.024
ings-0.021
 marks-0.021
 puzzles-0.020
 rats-0.020
Token,
Token ID11
Feature activation-8.01e-03

Pos logit contributions
es+0.007
 rats+0.007
ts+0.007
 stains+0.007
 marks+0.007
Neg logit contributions
ursion-0.009
 bet-0.009
anna-0.009
 Sure-0.008
Of-0.008
Token Betsy
Token ID45775
Feature activation-8.33e-03

Pos logit contributions
es+0.011
 stains+0.010
 rats+0.010
ts+0.010
 marks+0.010
Neg logit contributions
ursion-0.013
 bet-0.012
anna-0.012
 Sure-0.012
Of-0.012
Token could
Token ID714
Feature activation+3.51e-02

Pos logit contributions
es+0.013
 rats+0.012
ts+0.012
 stains+0.012
 marks+0.012
Neg logit contributions
ursion-0.012
anna-0.012
 bet-0.012
 Sure-0.011
 sur-0.011
Token.
Token ID13
Feature activation+6.89e-03

Pos logit contributions
ursion+0.049
anna+0.048
 bet+0.047
Of+0.046
 Sure+0.045
Neg logit contributions
es-0.015
 not-0.013
 marks-0.012
 stains-0.011
 rats-0.011
Token
Token ID198
Feature activation+3.64e-03

Pos logit contributions
ursion+0.013
anna+0.013
 bet+0.013
ya+0.013
 sur+0.013
Neg logit contributions
es-0.007
 not-0.007
isk-0.006
 marks-0.006
 bones-0.006
Token
Token ID198
Feature activation+5.18e-03

Pos logit contributions
ursion+0.006
 bet+0.006
anna+0.006
Of+0.006
 Sure+0.006
Neg logit contributions
es-0.005
 rats-0.004
ts-0.004
 stains-0.004
 marks-0.004
TokenOn
Token ID2202
Feature activation+2.80e-02

Pos logit contributions
ursion+0.009
 bet+0.008
anna+0.008
Of+0.008
 Sure+0.008
Neg logit contributions
es-0.007
 rats-0.007
ts-0.006
 stains-0.006
 marks-0.006
Token the
Token ID262
Feature activation+3.15e-02

Pos logit contributions
ursion+0.059
 bet+0.057
anna+0.057
 Sure+0.055
 pleasure+0.055
Neg logit contributions
es-0.027
 rats-0.024
 stains-0.022
ts-0.022
 marks-0.022
Token way
Token ID835
Feature activation+1.65e-01

Pos logit contributions
ursion+0.043
 bet+0.040
anna+0.039
 sur+0.037
Of+0.036
Neg logit contributions
es-0.054
 rats-0.053
 puzzles-0.053
 marks-0.052
 stains-0.052
Token home
Token ID1363
Feature activation-3.13e-03

Pos logit contributions
ursion+0.268
anna+0.261
 bet+0.261
Of+0.252
 pleasure+0.240
Neg logit contributions
es-0.237
 rats-0.211
 not-0.209
 marks-0.206
 stains-0.203
Token,
Token ID11
Feature activation-5.27e-03

Pos logit contributions
es+0.004
 rats+0.004
ts+0.004
 stains+0.004
 marks+0.004
Neg logit contributions
ursion-0.005
 bet-0.005
anna-0.005
 Sure-0.005
Of-0.005
Token Tim
Token ID5045
Feature activation+4.10e-03

Pos logit contributions
es+0.006
 rats+0.006
ts+0.006
 stains+0.006
 marks+0.005
Neg logit contributions
ursion-0.010
anna-0.009
 bet-0.009
Of-0.009
 Sure-0.009
Tokenmy
Token ID1820
Feature activation-8.33e-04

Pos logit contributions
ursion+0.008
 bet+0.007
Of+0.007
 Sure+0.007
 pleasure+0.007
Neg logit contributions
es-0.005
 marks-0.005
 rats-0.004
isk-0.004
 stains-0.004
Token thought
Token ID1807
Feature activation+1.66e-02

Pos logit contributions
es+0.001
 rats+0.001
 marks+0.001
 stains+0.001
ts+0.001
Neg logit contributions
ursion-0.001
 bet-0.001
Of-0.001
 pleasure-0.001
anna-0.001
Token was
Token ID373
Feature activation-4.22e-03

Pos logit contributions
es+0.041
 rats+0.039
 stains+0.037
ts+0.037
 marks+0.036
Neg logit contributions
ursion-0.072
 bet-0.070
anna-0.069
 Sure-0.066
Of-0.066
Token filled
Token ID5901
Feature activation-7.60e-02

Pos logit contributions
es+0.005
 rats+0.005
 stains+0.005
ts+0.005
 marks+0.004
Neg logit contributions
ursion-0.008
 bet-0.007
anna-0.007
 pleasure-0.007
 Sure-0.007
Token with
Token ID351
Feature activation-1.71e-02

Pos logit contributions
 rats+0.094
 stains+0.089
 ow+0.085
 blood+0.084
es+0.084
Neg logit contributions
 bet-0.130
ursion-0.129
 Sure-0.126
anna-0.125
 sur-0.125
Token delicious
Token ID12625
Feature activation-4.43e-02

Pos logit contributions
es+0.025
 rats+0.023
ts+0.022
 stains+0.022
 marks+0.022
Neg logit contributions
ursion-0.027
 bet-0.026
anna-0.025
 pleasure-0.025
Of-0.024
Token ch
Token ID442
Feature activation+5.80e-03

Pos logit contributions
es+0.050
isk+0.044
 not+0.044
ts+0.043
 rats+0.042
Neg logit contributions
anna-0.081
 pleasure-0.080
 bet-0.079
ursion-0.079
 sur-0.077
Tokenocol
Token ID4668
Feature activation-1.47e-01

Pos logit contributions
ursion+0.010
anna+0.010
 bet+0.009
 pleasure+0.009
 sur+0.009
Neg logit contributions
es-0.008
 rats-0.007
 not-0.007
 stains-0.007
ts-0.007
Tokenates
Token ID689
Feature activation-1.33e-02

Pos logit contributions
 rats+0.138
 stains+0.133
 not+0.131
 accidents+0.124
 blood+0.119
Neg logit contributions
anna-0.295
ursion-0.286
 pad-0.262
 bet-0.262
 pleasure-0.255
Token.
Token ID13
Feature activation+4.04e-03

Pos logit contributions
es+0.015
 rats+0.015
ts+0.014
 stains+0.014
adoes+0.013
Neg logit contributions
ursion-0.024
anna-0.024
 bet-0.023
 sur-0.022
 Sure-0.022
Token He
Token ID679
Feature activation-1.48e-02

Pos logit contributions
ursion+0.008
anna+0.008
 bet+0.007
ounded+0.007
den+0.007
Neg logit contributions
es-0.004
 not-0.003
 mice-0.003
isk-0.003
 all-0.003
Token was
Token ID373
Feature activation+7.42e-03

Pos logit contributions
es+0.022
ts+0.019
 not+0.019
 rats+0.019
 marks+0.019
Neg logit contributions
ursion-0.025
 bet-0.023
anna-0.023
 Sure-0.022
 pleasure-0.021
Token happy
Token ID3772
Feature activation-3.28e-02

Pos logit contributions
ursion+0.011
 bet+0.011
anna+0.011
 Sure+0.010
Of+0.010
Neg logit contributions
es-0.011
 not-0.011
 rats-0.010
ts-0.010
 stains-0.010
Token the
Token ID262
Feature activation+2.40e-02

Pos logit contributions
es+0.007
isk+0.007
bes+0.007
adoes+0.006
 stains+0.006
Neg logit contributions
 bet-0.012
 pleasure-0.011
 Sure-0.011
anna-0.011
ursion-0.011
Token soup
Token ID17141
Feature activation-3.33e-02

Pos logit contributions
 bet+0.037
ursion+0.036
 pleasure+0.035
anna+0.035
 Sure+0.034
Neg logit contributions
es-0.038
isk-0.033
ts-0.032
adoes-0.031
 rats-0.031
Token,
Token ID11
Feature activation-1.62e-02

Pos logit contributions
 rats+0.044
es+0.043
adoes+0.043
ts+0.042
isk+0.042
Neg logit contributions
ursion-0.050
 bet-0.049
anna-0.047
 Sure-0.047
 Shall-0.046
Token it
Token ID340
Feature activation-2.25e-02

Pos logit contributions
es+0.025
isk+0.024
ts+0.023
bes+0.022
 stains+0.022
Neg logit contributions
 bet-0.023
ursion-0.022
 Sure-0.022
Of-0.021
anna-0.021
Token was
Token ID373
Feature activation-2.97e-04

Pos logit contributions
adoes+0.037
 rats+0.036
isk+0.035
ings+0.035
es+0.035
Neg logit contributions
 bet-0.026
ursion-0.024
 Shall-0.023
 Sure-0.023
anna-0.023
Token ste
Token ID2876
Feature activation-1.43e-01

Pos logit contributions
es+0.000
isk+0.000
 rats+0.000
ts+0.000
adoes+0.000
Neg logit contributions
 pleasure-0.000
 bet-0.000
ursion-0.000
 Shall-0.000
 pad-0.000
Tokenaming
Token ID3723
Feature activation-2.40e-02

Pos logit contributions
 rats+0.235
es+0.222
 stains+0.218
adoes+0.215
 snakes+0.213
Neg logit contributions
ursion-0.207
anna-0.182
 bet-0.182
 sur-0.161
 Sure-0.161
Token hot
Token ID3024
Feature activation-4.74e-02

Pos logit contributions
es+0.031
 rats+0.029
ts+0.029
isk+0.027
 blood+0.025
Neg logit contributions
ursion-0.041
anna-0.040
 bet-0.039
 sur-0.037
 Sure-0.037
Token!
Token ID0
Feature activation-3.18e-03

Pos logit contributions
es+0.054
 rats+0.049
ts+0.048
 stains+0.046
 marks+0.046
Neg logit contributions
ursion-0.090
 bet-0.087
anna-0.087
 Sure-0.083
Of-0.082
Token She
Token ID1375
Feature activation-1.67e-02

Pos logit contributions
es+0.006
 rats+0.005
 marks+0.005
 not+0.005
 stains+0.005
Neg logit contributions
ursion-0.004
 bet-0.004
anna-0.004
 sur-0.004
Of-0.004
Token pretended
Token ID36766
Feature activation+2.21e-02

Pos logit contributions
es+0.025
 rats+0.024
 stains+0.023
adoes+0.023
ts+0.023
Neg logit contributions
ursion-0.024
 bet-0.024
anna-0.024
 Sure-0.022
Of-0.022
Token and
Token ID290
Feature activation-8.90e-03

Pos logit contributions
anna+0.056
 bet+0.055
 Sure+0.054
ursion+0.054
Of+0.053
Neg logit contributions
es-0.035
 stains-0.033
 rats-0.033
bes-0.031
ts-0.031
Token laughed
Token ID13818
Feature activation-3.19e-02

Pos logit contributions
es+0.014
ts+0.013
 rats+0.013
 stains+0.013
 not+0.013
Neg logit contributions
ursion-0.014
anna-0.013
 bet-0.013
 pleasure-0.012
Of-0.012
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
 rats+0.043
es+0.042
ts+0.042
 stains+0.041
isk+0.041
Neg logit contributions
 bet-0.048
ursion-0.047
anna-0.046
Of-0.046
 Sure-0.046
Token ate
Token ID15063
Feature activation-7.76e-02

Pos logit contributions
es+0.022
ts+0.020
 rats+0.020
 stains+0.020
 not+0.020
Neg logit contributions
ursion-0.023
anna-0.022
 bet-0.021
 Sure-0.020
Of-0.020
Token ch
Token ID442
Feature activation-3.82e-03

Pos logit contributions
es+0.093
isk+0.087
 rats+0.086
 stains+0.084
adoes+0.083
Neg logit contributions
 bet-0.128
 pleasure-0.125
anna-0.125
 Sure-0.124
ursion-0.122
Tokenocol
Token ID4668
Feature activation-1.41e-01

Pos logit contributions
 not+0.006
 rats+0.005
 stains+0.005
es+0.005
isk+0.005
Neg logit contributions
anna-0.006
ursion-0.005
 bet-0.005
 sur-0.005
 pleasure-0.005
Tokenates
Token ID689
Feature activation-5.34e-03

Pos logit contributions
 not+0.128
 rats+0.125
 accidents+0.123
 stains+0.123
 mess+0.116
Neg logit contributions
anna-0.277
ursion-0.264
den-0.250
 pad-0.245
 bet-0.244
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
 rats+0.007
adoes+0.007
isk+0.007
 stains+0.007
ts+0.007
Neg logit contributions
anna-0.008
 bet-0.008
ursion-0.007
 sur-0.007
Of-0.007
Token They
Token ID1119
Feature activation-2.44e-02

Pos logit contributions
es+0.019
 mice+0.018
 stains+0.018
 not+0.017
 rats+0.017
Neg logit contributions
ursion-0.030
anna-0.028
 bet-0.027
 sur-0.027
ounded-0.027
Token had
Token ID550
Feature activation-1.72e-02

Pos logit contributions
es+0.038
 rats+0.037
adoes+0.037
ings+0.036
 accidents+0.035
Neg logit contributions
 bet-0.034
ursion-0.032
Of-0.031
 sur-0.031
anna-0.031
Token a
Token ID257
Feature activation-3.31e-03

Pos logit contributions
es+0.020
 rats+0.018
adoes+0.018
ts+0.017
 stains+0.017
Neg logit contributions
 bet-0.031
ursion-0.030
anna-0.030
 pleasure-0.030
Of-0.029
Token It
Token ID632
Feature activation-2.58e-02

Pos logit contributions
anna+0.001
ursion+0.001
ounded+0.001
 sur+0.001
 bet+0.001
Neg logit contributions
es-0.000
 mice-0.000
 pictures-0.000
ings-0.000
ados-0.000
Token was
Token ID373
Feature activation+2.24e-04

Pos logit contributions
 rats+0.032
es+0.031
ts+0.030
 stains+0.029
adoes+0.029
Neg logit contributions
ursion-0.043
 bet-0.043
anna-0.042
 Sure-0.041
Of-0.040
Token filled
Token ID5901
Feature activation-6.95e-02

Pos logit contributions
 pleasure+0.000
 bet+0.000
 Katie+0.000
 Sure+0.000
 sur+0.000
Neg logit contributions
es-0.000
ts-0.000
 rats-0.000
bes-0.000
adoes-0.000
Token with
Token ID351
Feature activation-1.30e-02

Pos logit contributions
 rats+0.102
 blood+0.094
 ow+0.093
 stains+0.091
 burns+0.089
Neg logit contributions
ya-0.107
 Katie-0.105
 bet-0.105
very-0.104
 Sure-0.103
Token ch
Token ID442
Feature activation+6.60e-03

Pos logit contributions
es+0.018
 rats+0.016
ts+0.016
isk+0.015
bes+0.015
Neg logit contributions
 bet-0.021
 pleasure-0.021
ursion-0.020
Of-0.020
anna-0.019
Tokenocol
Token ID4668
Feature activation-1.39e-01

Pos logit contributions
ursion+0.010
 bet+0.010
anna+0.010
 pleasure+0.009
 sur+0.009
Neg logit contributions
es-0.010
 not-0.009
 rats-0.009
 stains-0.009
isk-0.009
Tokenates
Token ID689
Feature activation-7.24e-04

Pos logit contributions
 rats+0.141
 not+0.140
 stains+0.133
 accidents+0.123
 mess+0.121
Neg logit contributions
anna-0.263
ursion-0.257
 pad-0.240
 bet-0.233
enna-0.232
Token and
Token ID290
Feature activation-2.04e-03

Pos logit contributions
 rats+0.001
ts+0.001
isk+0.001
es+0.001
adoes+0.001
Neg logit contributions
anna-0.001
ursion-0.001
 bet-0.001
 pleasure-0.001
ya-0.001
Token coins
Token ID10796
Feature activation-2.07e-03

Pos logit contributions
es+0.003
 rats+0.002
ts+0.002
 stains+0.002
 marks+0.002
Neg logit contributions
ursion-0.004
 bet-0.004
anna-0.003
 Sure-0.003
Of-0.003
Token.
Token ID13
Feature activation+5.22e-03

Pos logit contributions
 rats+0.003
es+0.002
 mice+0.002
ts+0.002
adoes+0.002
Neg logit contributions
ursion-0.003
anna-0.003
 bet-0.003
 sur-0.003
 pleasure-0.003
Token She
Token ID1375
Feature activation-7.84e-03

Pos logit contributions
ursion+0.009
anna+0.009
den+0.009
 sur+0.009
fy+0.009
Neg logit contributions
es-0.006
 pictures-0.005
 marks-0.005
 mice-0.005
 not-0.005
Token room
Token ID2119
Feature activation-9.07e-03

Pos logit contributions
es+0.064
 rats+0.059
ts+0.057
 stains+0.056
 marks+0.055
Neg logit contributions
ursion-0.102
anna-0.099
 bet-0.099
 Sure-0.094
Of-0.093
Token.
Token ID13
Feature activation-9.85e-03

Pos logit contributions
es+0.009
 rats+0.008
ts+0.008
 stains+0.008
 marks+0.008
Neg logit contributions
ursion-0.018
 bet-0.018
anna-0.018
Of-0.017
 Sure-0.017
Token The
Token ID383
Feature activation-9.76e-06

Pos logit contributions
 mice+0.010
 rats+0.009
 not+0.009
es+0.009
 puzzles+0.009
Neg logit contributions
ursion-0.019
anna-0.019
 sur-0.018
ounded-0.018
Of-0.018
Token dish
Token ID9433
Feature activation-3.66e-02

Feature not active on prev token;
no predictions were affected.
Token was
Token ID373
Feature activation-4.88e-03

Pos logit contributions
 rats+0.058
ts+0.056
es+0.056
adoes+0.055
isk+0.055
Neg logit contributions
ursion-0.050
 bet-0.048
 Sure-0.046
anna-0.046
Of-0.043
Token ste
Token ID2876
Feature activation-1.36e-01

Pos logit contributions
es+0.009
 rats+0.008
adoes+0.007
ts+0.007
isk+0.007
Neg logit contributions
 pleasure-0.006
 bet-0.006
ursion-0.006
anna-0.006
 sur-0.006
Tokenaming
Token ID3723
Feature activation-2.47e-02

Pos logit contributions
 rats+0.217
es+0.209
 stains+0.204
 snakes+0.197
 blood+0.196
Neg logit contributions
ursion-0.204
anna-0.188
 bet-0.183
Of-0.170
 sur-0.166
Token hot
Token ID3024
Feature activation-4.37e-02

Pos logit contributions
es+0.030
 rats+0.027
ts+0.026
 stains+0.026
 marks+0.025
Neg logit contributions
ursion-0.046
anna-0.044
 bet-0.044
 Sure-0.042
Of-0.042
Token.
Token ID13
Feature activation-4.32e-03

Pos logit contributions
es+0.049
 rats+0.045
 stains+0.043
 marks+0.043
ts+0.042
Neg logit contributions
ursion-0.085
 bet-0.082
anna-0.081
Of-0.078
 Sure-0.078
Token It
Token ID632
Feature activation-3.04e-02

Pos logit contributions
 not+0.004
es+0.004
 mice+0.004
 rats+0.004
 marks+0.003
Neg logit contributions
ursion-0.009
anna-0.009
 sur-0.008
ounded-0.008
Of-0.008
Token was
Token ID373
Feature activation-3.46e-03

Pos logit contributions
es+0.041
 rats+0.037
ts+0.037
adoes+0.036
 stains+0.036
Neg logit contributions
 bet-0.050
ursion-0.049
anna-0.048
 Sure-0.046
Of-0.046
Token inside
Token ID2641
Feature activation+1.48e-02

Pos logit contributions
es+0.024
ts+0.023
 rats+0.023
 stains+0.022
adoes+0.022
Neg logit contributions
ursion-0.035
anna-0.034
 bet-0.034
 Sure-0.032
Of-0.032
Token!
Token ID0
Feature activation-1.82e-03

Pos logit contributions
ursion+0.025
 bet+0.025
anna+0.025
 pleasure+0.024
 Sure+0.024
Neg logit contributions
es-0.018
 rats-0.017
ts-0.017
 stains-0.016
adoes-0.016
Token There
Token ID1318
Feature activation+5.28e-02

Pos logit contributions
es+0.002
 mice+0.002
 rats+0.002
 stains+0.002
 puzzles+0.002
Neg logit contributions
ursion-0.003
 sur-0.003
anna-0.003
 bet-0.003
ounded-0.003
Token were
Token ID547
Feature activation-2.08e-02

Pos logit contributions
 bet+0.075
ursion+0.074
 Sure+0.071
 Katie+0.070
 pleasure+0.068
Neg logit contributions
bes-0.077
 rats-0.076
adoes-0.075
isk-0.075
ts-0.075
Token ch
Token ID442
Feature activation+2.44e-03

Pos logit contributions
es+0.025
adoes+0.023
bes+0.022
ts+0.022
isk+0.022
Neg logit contributions
 pleasure-0.033
 bet-0.032
Of-0.032
anna-0.032
ya-0.031
Tokenocol
Token ID4668
Feature activation-1.35e-01

Pos logit contributions
anna+0.003
uster+0.003
ursion+0.002
 bet+0.002
ya+0.002
Neg logit contributions
 not-0.005
es-0.004
 stains-0.004
bes-0.004
 rats-0.004
Tokenates
Token ID689
Feature activation+2.61e-03

Pos logit contributions
 rats+0.134
 not+0.133
 stains+0.129
 accidents+0.125
 mess+0.120
Neg logit contributions
anna-0.248
ursion-0.245
 pad-0.231
 bet-0.225
 Sure-0.223
Token,
Token ID11
Feature activation-1.47e-02

Pos logit contributions
anna+0.003
 pad+0.003
ya+0.003
 bet+0.003
 Katie+0.003
Neg logit contributions
 rats-0.004
adoes-0.004
ts-0.004
isk-0.004
 blood-0.004
Token cookies
Token ID14746
Feature activation-4.61e-02

Pos logit contributions
es+0.016
ts+0.014
ings+0.014
 rats+0.014
adoes+0.013
Neg logit contributions
 bet-0.026
Of-0.026
anna-0.026
 Sure-0.026
 pleasure-0.025
Token,
Token ID11
Feature activation-1.40e-02

Pos logit contributions
 rats+0.069
adoes+0.068
ts+0.067
es+0.065
 blood+0.064
Neg logit contributions
ursion-0.059
anna-0.058
 bet-0.057
 pad-0.056
 Sure-0.055
Token and
Token ID290
Feature activation+6.04e-03

Pos logit contributions
es+0.018
ts+0.017
ings+0.016
 rats+0.016
adoes+0.016
Neg logit contributions
anna-0.021
Of-0.021
 bet-0.021
 Sure-0.020
 pleasure-0.020
Token,
Token ID11
Feature activation-2.96e-02

Pos logit contributions
es+0.030
ts+0.027
 stains+0.027
 rats+0.026
 marks+0.026
Neg logit contributions
ursion-0.039
 bet-0.038
anna-0.037
 sur-0.037
 Sure-0.036
Token and
Token ID290
Feature activation-1.83e-04

Pos logit contributions
es+0.047
ts+0.043
 rats+0.042
 marks+0.042
 stains+0.042
Neg logit contributions
ursion-0.042
 bet-0.041
anna-0.040
 Sure-0.039
Of-0.039
Token his
Token ID465
Feature activation-2.08e-02

Pos logit contributions
es+0.000
 marks+0.000
 stains+0.000
 rats+0.000
ings+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
Of-0.000
 Sure-0.000
Token skin
Token ID4168
Feature activation-2.32e-02

Pos logit contributions
es+0.031
ts+0.027
 stains+0.026
 rats+0.026
adoes+0.025
Neg logit contributions
 bet-0.034
 pleasure-0.033
ursion-0.033
anna-0.031
 sur-0.031
Token was
Token ID373
Feature activation-1.06e-02

Pos logit contributions
 rats+0.038
 mice+0.037
 injuries+0.037
adoes+0.036
es+0.036
Neg logit contributions
anna-0.027
ursion-0.023
 bet-0.023
 So-0.022
shirt-0.021
Token wrink
Token ID34866
Feature activation-1.33e-01

Pos logit contributions
es+0.018
 rats+0.016
adoes+0.016
ts+0.015
 marks+0.015
Neg logit contributions
anna-0.014
ursion-0.013
 pleasure-0.013
 bet-0.013
 sur-0.012
Tokenly
Token ID306
Feature activation+2.60e-02

Pos logit contributions
es+0.222
 rats+0.221
bes+0.209
 snakes+0.208
ts+0.207
Neg logit contributions
anna-0.168
ursion-0.162
 bet-0.146
ya-0.141
 sur-0.139
Token.
Token ID13
Feature activation-1.39e-02

Pos logit contributions
anna+0.038
 bet+0.037
 pad+0.037
ursion+0.036
 pleasure+0.035
Neg logit contributions
ts-0.035
isk-0.034
es-0.033
 rats-0.032
bes-0.030
Token The
Token ID383
Feature activation-4.01e-04

Pos logit contributions
es+0.022
 rats+0.021
 stains+0.020
ts+0.020
 mice+0.020
Neg logit contributions
ursion-0.021
 bet-0.020
anna-0.019
 sur-0.018
Of-0.018
Token frog
Token ID21264
Feature activation-5.55e-03

Pos logit contributions
es+0.001
ts+0.001
bes+0.001
 rats+0.001
isk+0.001
Neg logit contributions
 bet-0.001
ursion-0.001
 sur-0.001
Of-0.001
 pleasure-0.001
Token lived
Token ID5615
Feature activation-4.30e-02

Pos logit contributions
adoes+0.009
 rats+0.009
es+0.009
 accidents+0.009
 stains+0.009
Neg logit contributions
anna-0.007
 bet-0.007
ursion-0.007
Of-0.006
 Sure-0.006
Token not
Token ID407
Feature activation-6.90e-02

Pos logit contributions
es+0.006
 rats+0.006
ts+0.005
 stains+0.005
 mice+0.005
Neg logit contributions
ursion-0.008
 bet-0.008
anna-0.008
Of-0.007
 pleasure-0.007
Token eat
Token ID4483
Feature activation-7.30e-02

Pos logit contributions
es+0.113
ts+0.102
 rats+0.101
 stains+0.097
 marks+0.095
Neg logit contributions
ursion-0.100
 bet-0.098
anna-0.096
Of-0.091
 sur-0.088
Token too
Token ID1165
Feature activation-4.22e-02

Pos logit contributions
es+0.081
bes+0.068
isk+0.067
 stains+0.067
adoes+0.066
Neg logit contributions
 bet-0.126
anna-0.126
 pleasure-0.123
 sur-0.118
Of-0.118
Token many
Token ID867
Feature activation-6.00e-03

Pos logit contributions
es+0.075
ts+0.069
bes+0.069
adoes+0.069
isk+0.069
Neg logit contributions
ursion-0.053
 bet-0.050
anna-0.048
 Sure-0.045
 pleasure-0.045
Token ch
Token ID442
Feature activation+3.78e-03

Pos logit contributions
es+0.005
 rats+0.005
ts+0.004
 stains+0.004
 marks+0.004
Neg logit contributions
ursion-0.013
 bet-0.013
anna-0.013
Of-0.012
 Sure-0.012
Tokenocol
Token ID4668
Feature activation-1.33e-01

Pos logit contributions
anna+0.006
 bet+0.006
ursion+0.006
 sur+0.005
 pleasure+0.005
Neg logit contributions
es-0.005
 stains-0.005
 not-0.005
 rats-0.005
bes-0.005
Tokenates
Token ID689
Feature activation-3.80e-03

Pos logit contributions
 stains+0.118
 rats+0.116
 not+0.109
 accidents+0.109
 mice+0.104
Neg logit contributions
anna-0.268
ursion-0.267
 bet-0.249
 pad-0.242
 Sure-0.240
Token and
Token ID290
Feature activation-1.87e-02

Pos logit contributions
es+0.004
 rats+0.004
ts+0.004
 stains+0.004
adoes+0.004
Neg logit contributions
ursion-0.007
anna-0.006
 bet-0.006
 pleasure-0.006
Of-0.006
Token his
Token ID465
Feature activation-3.40e-02

Pos logit contributions
es+0.023
 rats+0.021
ts+0.020
 stains+0.020
 marks+0.020
Neg logit contributions
ursion-0.034
 bet-0.033
anna-0.033
 Sure-0.031
Of-0.031
Token friend
Token ID1545
Feature activation+2.13e-02

Pos logit contributions
es+0.045
 rats+0.038
ts+0.038
 stains+0.038
adoes+0.036
Neg logit contributions
 bet-0.058
ursion-0.058
anna-0.058
 pleasure-0.056
 Sure-0.055
Token learned
Token ID4499
Feature activation-6.66e-02

Pos logit contributions
ursion+0.033
 bet+0.032
anna+0.032
Of+0.030
 Sure+0.030
Neg logit contributions
es-0.031
 rats-0.029
ts-0.028
 stains-0.028
 marks-0.028
Token that
Token ID326
Feature activation-2.91e-02

Pos logit contributions
anna+0.033
Of+0.031
 pleasure+0.030
 ï¿½+0.030
 bet+0.029
Neg logit contributions
es-0.040
ts-0.040
isk-0.040
icer-0.040
bes-0.039
Token her
Token ID607
Feature activation-1.97e-03

Pos logit contributions
es+0.047
ts+0.045
bes+0.045
ings+0.044
arts+0.044
Neg logit contributions
Of-0.035
 bet-0.035
ursion-0.034
 Sure-0.033
anna-0.033
Token injury
Token ID5095
Feature activation-2.44e-02

Pos logit contributions
es+0.003
ts+0.002
 rats+0.002
 mice+0.002
isk+0.002
Neg logit contributions
anna-0.003
ursion-0.003
 bet-0.003
 pleasure-0.003
Of-0.003
Token was
Token ID373
Feature activation-4.74e-03

Pos logit contributions
es+0.030
 rats+0.030
ts+0.029
 mice+0.028
 stains+0.027
Neg logit contributions
ursion-0.041
anna-0.040
 bet-0.040
Of-0.038
 Sure-0.037
Token too
Token ID1165
Feature activation-4.22e-02

Pos logit contributions
es+0.006
ts+0.005
 rats+0.005
 marks+0.005
bes+0.005
Neg logit contributions
ursion-0.009
anna-0.009
 bet-0.008
Of-0.008
 pleasure-0.008
Token severe
Token ID6049
Feature activation-1.33e-01

Pos logit contributions
es+0.056
ts+0.051
 rats+0.049
 stains+0.047
 marks+0.046
Neg logit contributions
ursion-0.076
anna-0.072
 bet-0.070
Of-0.068
 Sure-0.066
Token and
Token ID290
Feature activation-1.32e-02

Pos logit contributions
ts+0.189
 stains+0.189
es+0.186
adoes+0.184
icer+0.180
Neg logit contributions
anna-0.182
 bet-0.173
ursion-0.172
 Sure-0.163
 pleasure-0.154
Token she
Token ID673
Feature activation+9.53e-03

Pos logit contributions
es+0.016
 rats+0.014
ts+0.014
 stains+0.014
 marks+0.014
Neg logit contributions
ursion-0.024
 bet-0.023
anna-0.023
Of-0.022
 Sure-0.022
Token would
Token ID561
Feature activation+2.42e-02

Pos logit contributions
ursion+0.013
anna+0.012
 bet+0.012
Of+0.011
 Sure+0.011
Neg logit contributions
es-0.016
 rats-0.015
ts-0.015
adoes-0.015
 stains-0.014
Token never
Token ID1239
Feature activation+2.93e-03

Pos logit contributions
 bet+0.039
ursion+0.039
anna+0.038
Of+0.037
 pleasure+0.036
Neg logit contributions
es-0.036
 rats-0.032
ts-0.031
 mice-0.030
 puzzles-0.029
Token be
Token ID307
Feature activation-4.29e-02

Pos logit contributions
ursion+0.005
anna+0.005
 bet+0.005
 Sure+0.005
Of+0.005
Neg logit contributions
es-0.004
 rats-0.004
 marks-0.004
 stains-0.004
 not-0.004
Token It
Token ID632
Feature activation-2.79e-02

Pos logit contributions
anna+0.008
den+0.008
 sur+0.008
ursion+0.008
 bet+0.007
Neg logit contributions
 not-0.005
adoes-0.005
es-0.005
 mice-0.004
 pictures-0.004
Token was
Token ID373
Feature activation-5.58e-04

Pos logit contributions
es+0.039
 rats+0.038
ts+0.037
adoes+0.037
 puzzles+0.036
Neg logit contributions
 bet-0.043
anna-0.041
Of-0.040
ursion-0.040
 Sure-0.039
Token sweet
Token ID6029
Feature activation-4.21e-02

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
adoes+0.001
bes+0.001
Neg logit contributions
 pleasure-0.001
 bet-0.001
anna-0.001
 Shall-0.001
ursion-0.001
Token,
Token ID11
Feature activation-1.20e-02

Pos logit contributions
es+0.048
 rats+0.043
ts+0.042
 stains+0.042
 marks+0.041
Neg logit contributions
ursion-0.080
 bet-0.078
anna-0.078
Of-0.074
 Sure-0.074
Token ch
Token ID442
Feature activation+1.00e-02

Pos logit contributions
es+0.016
 rats+0.015
ts+0.015
 stains+0.014
 marks+0.014
Neg logit contributions
ursion-0.020
 bet-0.020
anna-0.019
Of-0.019
 Sure-0.019
Tokenocol
Token ID4668
Feature activation-1.33e-01

Pos logit contributions
anna+0.015
ursion+0.015
 bet+0.014
 pleasure+0.013
 sur+0.013
Neg logit contributions
es-0.016
 puzzles-0.015
 rats-0.015
 not-0.015
ts-0.014
Tokenat
Token ID265
Feature activation-4.36e-02

Pos logit contributions
 rats+0.125
 not+0.119
 stains+0.115
 puzzles+0.114
 mice+0.114
Neg logit contributions
anna-0.258
ursion-0.256
 bet-0.240
 pad-0.234
 Sure-0.234
Tokeny
Token ID88
Feature activation-2.13e-02

Pos logit contributions
 rats+0.057
es+0.055
adoes+0.054
ts+0.054
 puzzles+0.052
Neg logit contributions
anna-0.071
ursion-0.067
 bet-0.066
 pleasure-0.065
 Sure-0.064
Token and
Token ID290
Feature activation+7.36e-04

Pos logit contributions
es+0.026
 rats+0.025
ts+0.024
 stains+0.023
 marks+0.023
Neg logit contributions
ursion-0.037
anna-0.037
 bet-0.036
 pleasure-0.035
 Sure-0.035
Token warm
Token ID5814
Feature activation-1.39e-02

Pos logit contributions
ursion+0.001
 bet+0.001
anna+0.001
Of+0.001
 Sure+0.001
Neg logit contributions
es-0.001
 rats-0.001
ts-0.001
 stains-0.001
 marks-0.001
Token,
Token ID11
Feature activation-1.43e-02

Pos logit contributions
es+0.016
 rats+0.015
ts+0.015
 stains+0.014
 marks+0.014
Neg logit contributions
ursion-0.026
anna-0.025
 bet-0.025
 Sure-0.024
Of-0.024
Token nice
Token ID3621
Feature activation-3.03e-02

Pos logit contributions
es+0.012
 rats+0.011
 stains+0.011
ts+0.010
 marks+0.010
Neg logit contributions
ursion-0.016
anna-0.015
 bet-0.015
 Sure-0.015
Of-0.014
Token,
Token ID11
Feature activation-2.79e-02

Pos logit contributions
es+0.035
 rats+0.033
ts+0.033
 stains+0.031
 mice+0.030
Neg logit contributions
ursion-0.055
 bet-0.054
anna-0.053
 Sure-0.051
 pleasure-0.050
Token but
Token ID475
Feature activation+5.44e-02

Pos logit contributions
es+0.049
 not+0.049
 rats+0.048
 stains+0.048
 marks+0.047
Neg logit contributions
ursion-0.038
anna-0.035
 bet-0.033
 sur-0.031
 Sure-0.030
Token it
Token ID340
Feature activation-3.23e-02

Pos logit contributions
ursion+0.086
 bet+0.085
Of+0.082
 Sure+0.081
anna+0.080
Neg logit contributions
es-0.077
 rats-0.070
ts-0.069
 stains-0.068
 mice-0.068
Token was
Token ID373
Feature activation-1.19e-02

Pos logit contributions
es+0.048
adoes+0.047
 mice+0.046
 rats+0.046
ados+0.045
Neg logit contributions
 bet-0.043
ursion-0.039
Of-0.039
 Sure-0.038
 sur-0.037
Token wrink
Token ID34866
Feature activation-1.33e-01

Pos logit contributions
es+0.017
ts+0.014
adoes+0.014
bes+0.014
ops+0.014
Neg logit contributions
 bet-0.018
ursion-0.018
 pleasure-0.018
 pad-0.017
Of-0.017
Tokenled
Token ID992
Feature activation-1.36e-02

Pos logit contributions
 rats+0.191
es+0.191
 puzzles+0.185
isk+0.183
ts+0.181
Neg logit contributions
anna-0.187
ursion-0.184
 bet-0.171
ya-0.160
ounded-0.159
Token and
Token ID290
Feature activation-1.65e-02

Pos logit contributions
es+0.019
ts+0.019
bes+0.018
 rats+0.017
ics+0.017
Neg logit contributions
 bet-0.020
ursion-0.019
anna-0.019
Of-0.019
 pad-0.019
Token dirty
Token ID11841
Feature activation-5.14e-02

Pos logit contributions
es+0.021
 rats+0.019
ts+0.018
 marks+0.018
adoes+0.017
Neg logit contributions
ursion-0.029
 bet-0.028
anna-0.027
Of-0.027
 Sure-0.027
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
es+0.067
ts+0.066
isk+0.065
 rats+0.064
lich+0.061
Neg logit contributions
 bet-0.074
anna-0.074
ursion-0.074
 sur-0.068
 pad-0.068
Token She
Token ID1375
Feature activation-1.98e-02

Pos logit contributions
es+0.016
 rats+0.015
 stains+0.015
 marks+0.015
 not+0.014
Neg logit contributions
ursion-0.021
anna-0.020
 bet-0.019
 sur-0.019
ya-0.019
Token and
Token ID290
Feature activation-4.49e-03

Pos logit contributions
es+0.022
 stains+0.018
 marks+0.017
 not+0.017
 rats+0.017
Neg logit contributions
ursion-0.053
 bet-0.051
anna-0.051
 pleasure-0.049
Of-0.049
Token dream
Token ID4320
Feature activation-3.12e-02

Pos logit contributions
es+0.008
 rats+0.007
 stains+0.007
ts+0.007
 marks+0.007
Neg logit contributions
ursion-0.006
 bet-0.006
anna-0.006
 Sure-0.005
Of-0.005
Token of
Token ID286
Feature activation-3.29e-02

Pos logit contributions
es+0.039
 rats+0.036
ts+0.035
 stains+0.035
 marks+0.034
Neg logit contributions
ursion-0.056
 bet-0.054
anna-0.054
Of-0.051
 Sure-0.051
Token horses
Token ID14260
Feature activation+1.05e-02

Pos logit contributions
es+0.040
adoes+0.033
 stains+0.033
bes+0.033
isk+0.033
Neg logit contributions
 bet-0.057
 pleasure-0.056
 sur-0.054
ursion-0.053
 Sure-0.052
Token and
Token ID290
Feature activation-7.10e-03

Pos logit contributions
ursion+0.018
 bet+0.018
anna+0.018
 sur+0.017
 Sure+0.017
Neg logit contributions
es-0.012
 rats-0.012
 stains-0.012
ts-0.011
adoes-0.011
Token ste
Token ID2876
Feature activation-1.32e-01

Pos logit contributions
es+0.007
 stains+0.006
 rats+0.006
ts+0.006
 marks+0.006
Neg logit contributions
 bet-0.013
ursion-0.013
anna-0.013
 pleasure-0.013
 Sure-0.013
Tokenaks
Token ID4730
Feature activation-1.46e-02

Pos logit contributions
 rats+0.198
 stains+0.193
 not+0.192
 accidents+0.185
es+0.184
Neg logit contributions
anna-0.182
ursion-0.181
 bet-0.168
 sur-0.154
ya-0.153
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
 rats+0.017
es+0.017
 stains+0.017
ts+0.017
 not+0.016
Neg logit contributions
anna-0.024
 bet-0.023
ursion-0.022
 sur-0.022
 Sure-0.021
Token They
Token ID1119
Feature activation-1.35e-02

Pos logit contributions
es+0.011
 mice+0.011
 rats+0.011
 not+0.010
 stains+0.010
Neg logit contributions
ursion-0.026
anna-0.025
ounded-0.024
 sur-0.024
ya-0.024
Token are
Token ID389
Feature activation-3.52e-02

Pos logit contributions
es+0.021
adoes+0.020
 rats+0.020
 accidents+0.020
 stains+0.019
Neg logit contributions
 bet-0.020
ursion-0.019
anna-0.018
 sur-0.017
 pleasure-0.017
Token good
Token ID922
Feature activation-1.47e-02

Pos logit contributions
es+0.058
 stains+0.053
 rats+0.052
 marks+0.051
ts+0.051
Neg logit contributions
 pleasure-0.046
 bet-0.045
anna-0.045
ursion-0.045
 sur-0.042
Token pride
Token ID11293
Feature activation+1.61e-02

Pos logit contributions
es+0.012
 rats+0.011
 stains+0.011
ts+0.011
 marks+0.011
Neg logit contributions
ursion-0.007
 bet-0.007
 pleasure-0.007
anna-0.007
Of-0.006
Token as
Token ID355
Feature activation+3.56e-02

Pos logit contributions
ursion+0.030
anna+0.029
 bet+0.029
Of+0.027
 Sure+0.027
Neg logit contributions
es-0.019
 rats-0.017
ts-0.017
 stains-0.017
 marks-0.016
Token they
Token ID484
Feature activation+1.92e-02

Pos logit contributions
ursion+0.067
anna+0.065
 bet+0.064
Of+0.061
 Sure+0.060
Neg logit contributions
es-0.044
 rats-0.040
ts-0.039
 marks-0.038
 not-0.038
Token watched
Token ID7342
Feature activation+3.50e-02

Pos logit contributions
ursion+0.028
anna+0.026
 bet+0.026
 Sure+0.025
Of+0.025
Neg logit contributions
es-0.031
 rats-0.029
ts-0.029
 stains-0.028
 marks-0.028
Token it
Token ID340
Feature activation-3.07e-02

Pos logit contributions
ursion+0.069
 bet+0.068
anna+0.068
 Sure+0.066
 pleasure+0.066
Neg logit contributions
es-0.035
 rats-0.032
 stains-0.030
ts-0.030
 marks-0.029
Token ste
Token ID2876
Feature activation-1.32e-01

Pos logit contributions
es+0.043
 rats+0.041
ts+0.039
 stains+0.039
 mice+0.037
Neg logit contributions
ursion-0.050
 bet-0.049
anna-0.048
 Sure-0.045
Of-0.045
Tokenaming
Token ID3723
Feature activation-1.69e-02

Pos logit contributions
 rats+0.191
es+0.185
 stains+0.179
 not+0.171
 snakes+0.169
Neg logit contributions
ursion-0.208
anna-0.196
 bet-0.196
Of-0.180
 sur-0.179
Token away
Token ID1497
Feature activation-1.77e-02

Pos logit contributions
es+0.019
 marks+0.017
 rats+0.017
 stains+0.017
ts+0.017
Neg logit contributions
ursion-0.033
 bet-0.031
anna-0.031
Of-0.030
 Sure-0.030
Token on
Token ID319
Feature activation-1.41e-02

Pos logit contributions
es+0.021
 rats+0.020
ts+0.019
 stains+0.019
isk+0.018
Neg logit contributions
 bet-0.031
ursion-0.030
anna-0.030
 pleasure-0.029
 sur-0.029
Token the
Token ID262
Feature activation+1.64e-02

Pos logit contributions
es+0.017
 rats+0.015
isk+0.015
ts+0.014
 stains+0.014
Neg logit contributions
 bet-0.025
 pleasure-0.025
 Sure-0.024
ursion-0.024
anna-0.023
Token stove
Token ID27635
Feature activation-1.62e-02

Pos logit contributions
ursion+0.031
 bet+0.030
anna+0.029
Of+0.029
 Sure+0.028
Neg logit contributions
es-0.019
 rats-0.018
 stains-0.018
 marks-0.017
ts-0.017
Token king
Token ID5822
Feature activation-3.27e-02

Pos logit contributions
es+0.001
 rats+0.001
 stains+0.001
ts+0.001
 marks+0.001
Neg logit contributions
ursion-0.002
 bet-0.002
anna-0.002
Of-0.002
 Sure-0.002
Token ate
Token ID15063
Feature activation-6.62e-02

Pos logit contributions
 rats+0.045
 stains+0.044
adoes+0.043
ts+0.043
es+0.043
Neg logit contributions
anna-0.050
ursion-0.050
 bet-0.049
Of-0.046
 sur-0.045
Token too
Token ID1165
Feature activation-2.97e-02

Pos logit contributions
es+0.082
bes+0.076
adoes+0.074
isk+0.073
iders+0.071
Neg logit contributions
 bet-0.109
 pleasure-0.104
Of-0.104
 Sure-0.104
 sur-0.100
Token many
Token ID867
Feature activation+3.86e-03

Pos logit contributions
es+0.048
adoes+0.047
 stains+0.046
 rats+0.045
ts+0.044
Neg logit contributions
ursion-0.039
 bet-0.038
anna-0.037
 Sure-0.037
 pleasure-0.037
Token ch
Token ID442
Feature activation+9.98e-03

Pos logit contributions
anna+0.007
 bet+0.007
ursion+0.007
Of+0.007
 pleasure+0.007
Neg logit contributions
es-0.004
adoes-0.004
 stains-0.004
 rats-0.003
 not-0.003
Tokenocol
Token ID4668
Feature activation-1.32e-01

Pos logit contributions
anna+0.015
ursion+0.014
 bet+0.014
 sur+0.013
uster+0.012
Neg logit contributions
 not-0.015
es-0.014
 stains-0.014
bes-0.014
 rats-0.014
Tokenates
Token ID689
Feature activation+5.20e-03

Pos logit contributions
 rats+0.127
 not+0.122
 stains+0.121
 accidents+0.120
 mess+0.112
Neg logit contributions
anna-0.255
ursion-0.252
 pad-0.231
 bet-0.229
 Sure-0.228
Token and
Token ID290
Feature activation-1.19e-02

Pos logit contributions
ursion+0.007
anna+0.007
 bet+0.007
 pleasure+0.007
 Sure+0.007
Neg logit contributions
 rats-0.007
adoes-0.007
ts-0.007
 stains-0.007
isk-0.007
Token his
Token ID465
Feature activation-2.77e-02

Pos logit contributions
es+0.017
 rats+0.016
 stains+0.016
ts+0.016
 marks+0.015
Neg logit contributions
ursion-0.018
 bet-0.018
anna-0.017
 Sure-0.017
Of-0.017
Token tum
Token ID11814
Feature activation-9.55e-02

Pos logit contributions
es+0.035
 stains+0.030
 rats+0.029
adoes+0.029
ts+0.029
Neg logit contributions
anna-0.048
 pleasure-0.048
 bet-0.048
ursion-0.046
 Sure-0.045
Tokenmy
Token ID1820
Feature activation-2.75e-02

Pos logit contributions
es+0.167
 rats+0.165
ts+0.161
 mice+0.158
 stains+0.156
Neg logit contributions
ursion-0.118
anna-0.113
 bet-0.103
Of-0.101
 Sure-0.100
Token so
Token ID523
Feature activation+5.04e-02

Pos logit contributions
ursion+0.000
anna+0.000
 bet+0.000
 Sure+0.000
 pleasure+0.000
Neg logit contributions
es-0.000
ts-0.000
 not-0.000
 rats-0.000
 stains-0.000
Token it
Token ID340
Feature activation-3.15e-02

Pos logit contributions
ursion+0.091
 Sure+0.084
anna+0.084
 bet+0.084
uster+0.083
Neg logit contributions
 not-0.069
es-0.057
 rats-0.054
ts-0.053
 all-0.053
Token wouldn
Token ID3636
Feature activation+2.61e-02

Pos logit contributions
es+0.046
 rats+0.041
 stains+0.041
ts+0.041
 marks+0.041
Neg logit contributions
ursion-0.051
 bet-0.048
anna-0.048
 Sure-0.046
Of-0.046
Token't
Token ID470
Feature activation-3.49e-02

Pos logit contributions
ursion+0.062
 bet+0.060
anna+0.060
 Sure+0.057
Of+0.057
Neg logit contributions
es-0.018
 rats-0.016
ts-0.015
 stains-0.014
 mice-0.013
Token get
Token ID651
Feature activation-2.78e-03

Pos logit contributions
es+0.041
 not+0.039
 rats+0.038
 marks+0.038
 stains+0.038
Neg logit contributions
ursion-0.065
anna-0.061
 bet-0.061
 Sure-0.061
Of-0.059
Token wrink
Token ID34866
Feature activation-1.31e-01

Pos logit contributions
es+0.003
 rats+0.003
 stains+0.003
ts+0.003
 marks+0.003
Neg logit contributions
ursion-0.005
 bet-0.005
anna-0.005
 Sure-0.005
Of-0.005
Tokenled
Token ID992
Feature activation-1.87e-02

Pos logit contributions
es+0.227
 rats+0.216
 not+0.206
ts+0.204
isk+0.204
Neg logit contributions
anna-0.165
ursion-0.160
 bet-0.153
 sur-0.142
ya-0.139
Token.
Token ID13
Feature activation+2.05e-02

Pos logit contributions
es+0.023
ts+0.020
 rats+0.020
 stains+0.019
 marks+0.019
Neg logit contributions
 bet-0.033
ursion-0.033
anna-0.032
 pleasure-0.031
Of-0.030
Token She
Token ID1375
Feature activation+1.95e-03

Pos logit contributions
ursion+0.036
ounded+0.034
 bet+0.034
anna+0.033
 sur+0.032
Neg logit contributions
es-0.025
 not-0.024
 mice-0.023
 rats-0.022
adoes-0.021
Token took
Token ID1718
Feature activation+2.04e-02

Pos logit contributions
ursion+0.003
 bet+0.003
anna+0.003
 Sure+0.003
Of+0.003
Neg logit contributions
es-0.003
 rats-0.003
 stains-0.002
ts-0.002
 marks-0.002
Token her
Token ID607
Feature activation-5.12e-03

Pos logit contributions
ursion+0.044
anna+0.043
 bet+0.043
Of+0.041
 Sure+0.041
Neg logit contributions
es-0.018
 rats-0.016
ts-0.015
 stains-0.015
 marks-0.015
Token,
Token ID11
Feature activation-2.46e-02

Pos logit contributions
es+0.051
 rats+0.048
ts+0.046
 stains+0.045
 marks+0.044
Neg logit contributions
ursion-0.086
anna-0.083
 bet-0.083
 Sure-0.079
Of-0.079
Token cup
Token ID6508
Feature activation-6.79e-02

Pos logit contributions
es+0.032
 rats+0.029
ts+0.028
 stains+0.028
 marks+0.028
Neg logit contributions
ursion-0.043
 bet-0.042
anna-0.041
Of-0.039
 Sure-0.039
Tokencakes
Token ID37263
Feature activation-5.19e-02

Pos logit contributions
es+0.086
 rats+0.085
ts+0.083
 mice+0.078
adoes+0.078
Neg logit contributions
ursion-0.111
anna-0.109
 bet-0.104
 Sure-0.103
Of-0.103
Token and
Token ID290
Feature activation-2.98e-03

Pos logit contributions
es+0.064
 rats+0.060
ts+0.057
 stains+0.056
 marks+0.055
Neg logit contributions
ursion-0.093
anna-0.090
 bet-0.090
Of-0.086
 Sure-0.086
Token ch
Token ID442
Feature activation+7.79e-03

Pos logit contributions
es+0.004
 rats+0.003
ts+0.003
 stains+0.003
 not+0.003
Neg logit contributions
ursion-0.006
 bet-0.005
anna-0.005
 Sure-0.005
ounded-0.005
Tokenocol
Token ID4668
Feature activation-1.30e-01

Pos logit contributions
ursion+0.014
anna+0.013
 bet+0.013
 sur+0.012
Of+0.012
Neg logit contributions
es-0.010
 rats-0.009
 stains-0.009
 marks-0.009
ts-0.009
Tokenates
Token ID689
Feature activation-5.15e-03

Pos logit contributions
 rats+0.111
 not+0.107
 stains+0.107
es+0.101
 accidents+0.101
Neg logit contributions
anna-0.267
ursion-0.262
 bet-0.247
 Sure-0.240
 pad-0.239
Token.
Token ID13
Feature activation-3.90e-04

Pos logit contributions
es+0.006
 rats+0.006
ts+0.005
 stains+0.005
 mice+0.005
Neg logit contributions
ursion-0.009
anna-0.009
 bet-0.009
 Sure-0.008
Of-0.008
Token
Token ID220
Feature activation+2.92e-02

Pos logit contributions
 not+0.000
es+0.000
 rats+0.000
 bones+0.000
 mice+0.000
Neg logit contributions
ursion-0.001
anna-0.001
 bet-0.001
ounded-0.001
ya-0.001
Token
Token ID198
Feature activation+6.49e-05

Pos logit contributions
ursion+0.045
 bet+0.043
anna+0.042
Of+0.040
 Sure+0.040
Neg logit contributions
es-0.045
 rats-0.041
ts-0.040
 stains-0.040
 marks-0.040
Token
Token ID198
Feature activation+2.36e-03

Pos logit contributions
ursion+0.000
 bet+0.000
anna+0.000
 pleasure+0.000
ounded+0.000
Neg logit contributions
es-0.000
 not-0.000
isk-0.000
oni-0.000
 rats-0.000
Tokenunes
Token ID4015
Feature activation-5.71e-02

Pos logit contributions
ts+0.048
 rats+0.047
 mice+0.046
bes+0.046
es+0.046
Neg logit contributions
ursion-0.052
anna-0.051
 bet-0.050
 pleasure-0.047
 Sure-0.047
Token.
Token ID13
Feature activation-6.39e-03

Pos logit contributions
es+0.067
 rats+0.064
ts+0.062
 mice+0.061
adoes+0.060
Neg logit contributions
ursion-0.102
anna-0.098
 bet-0.097
Of-0.091
 sur-0.090
Token They
Token ID1119
Feature activation-2.10e-02

Pos logit contributions
es+0.010
 rats+0.010
 mice+0.009
 not+0.009
 stains+0.009
Neg logit contributions
ursion-0.010
anna-0.009
 bet-0.009
 sur-0.009
ounded-0.009
Token are
Token ID389
Feature activation-3.99e-02

Pos logit contributions
es+0.031
adoes+0.029
 rats+0.029
bes+0.028
ts+0.028
Neg logit contributions
 bet-0.033
ursion-0.032
anna-0.030
Of-0.029
 pleasure-0.029
Token too
Token ID1165
Feature activation-2.98e-02

Pos logit contributions
es+0.052
bes+0.042
adoes+0.041
ts+0.041
isk+0.040
Neg logit contributions
 bet-0.068
 pleasure-0.067
anna-0.065
ursion-0.064
Of-0.063
Token wrink
Token ID34866
Feature activation-1.29e-01

Pos logit contributions
es+0.045
isk+0.040
ts+0.039
bes+0.038
adoes+0.038
Neg logit contributions
anna-0.045
ursion-0.044
 bet-0.044
 pleasure-0.041
Of-0.040
Tokenly
Token ID306
Feature activation+4.54e-02

Pos logit contributions
 rats+0.177
es+0.174
ts+0.167
bes+0.164
isk+0.164
Neg logit contributions
anna-0.199
ursion-0.195
 bet-0.187
ounded-0.173
ya-0.172
Token and
Token ID290
Feature activation-7.99e-03

Pos logit contributions
anna+0.073
 bet+0.071
ursion+0.069
 pad+0.064
 pleasure+0.063
Neg logit contributions
es-0.057
ts-0.055
isk-0.055
 rats-0.053
bes-0.050
Token sour
Token ID11348
Feature activation-7.26e-02

Pos logit contributions
es+0.010
 rats+0.009
ts+0.008
adoes+0.008
 marks+0.008
Neg logit contributions
ursion-0.014
 bet-0.014
anna-0.014
Of-0.013
 pleasure-0.013
Token for
Token ID329
Feature activation-8.23e-02

Pos logit contributions
es+0.089
ts+0.087
 rats+0.083
isk+0.082
bes+0.078
Neg logit contributions
anna-0.119
ursion-0.118
 bet-0.117
Of-0.109
 sur-0.108
Token cakes
Token ID30849
Feature activation-1.45e-02

Pos logit contributions
es+0.105
 rats+0.091
 stains+0.087
ts+0.086
adoes+0.086
Neg logit contributions
ursion-0.140
anna-0.139
 bet-0.139
 pleasure-0.135
Of-0.132
Tokeniled
Token ID3902
Feature activation-5.33e-02

Pos logit contributions
 bet+0.028
anna+0.027
ursion+0.026
 pleasure+0.025
 Sure+0.025
Neg logit contributions
es-0.026
ts-0.023
 stains-0.022
oni-0.022
arts-0.022
Token and
Token ID290
Feature activation-8.15e-04

Pos logit contributions
es+0.067
 rats+0.063
ts+0.060
bes+0.058
isk+0.058
Neg logit contributions
anna-0.090
 bet-0.089
ursion-0.087
 sur-0.081
 pleasure-0.081
Token po
Token ID745
Feature activation-1.14e-02

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 stains+0.001
 marks+0.001
Neg logit contributions
ursion-0.001
 bet-0.001
anna-0.001
 Sure-0.001
Of-0.001
Tokenached
Token ID2317
Feature activation+4.68e-02

Pos logit contributions
es+0.019
 rats+0.017
 stains+0.017
ts+0.017
 marks+0.017
Neg logit contributions
ursion-0.016
 bet-0.016
anna-0.015
 Sure-0.014
Of-0.014
Token and
Token ID290
Feature activation+1.27e-03

Pos logit contributions
anna+0.079
ursion+0.078
 bet+0.077
 pleasure+0.072
 Sure+0.072
Neg logit contributions
es-0.058
 rats-0.056
ts-0.055
 stains-0.052
bes-0.051
Token ste
Token ID2876
Feature activation-1.29e-01

Pos logit contributions
ursion+0.002
 bet+0.002
anna+0.002
 Sure+0.002
Of+0.002
Neg logit contributions
es-0.002
 rats-0.001
ts-0.001
 stains-0.001
 marks-0.001
Tokenamed
Token ID2434
Feature activation-7.33e-03

Pos logit contributions
 rats+0.172
es+0.167
 stains+0.162
 not+0.155
 puzzles+0.154
Neg logit contributions
ursion-0.214
anna-0.207
 bet-0.202
Of-0.187
 pleasure-0.186
Token and
Token ID290
Feature activation+4.98e-03

Pos logit contributions
es+0.009
 rats+0.008
 stains+0.008
ts+0.008
 marks+0.007
Neg logit contributions
anna-0.013
ursion-0.013
 bet-0.013
Of-0.012
 pleasure-0.012
Token microw
Token ID23479
Feature activation+1.79e-02

Pos logit contributions
ursion+0.009
anna+0.008
 bet+0.008
ounded+0.008
Of+0.008
Neg logit contributions
es-0.007
 not-0.006
 rats-0.006
ts-0.006
 stains-0.006
Tokenaved
Token ID9586
Feature activation+3.06e-02

Pos logit contributions
ursion+0.027
Of+0.027
 adventurer+0.026
ya+0.026
 pleasure+0.026
Neg logit contributions
es-0.027
isk-0.023
 stains-0.022
 marks-0.021
arts-0.021
Token and
Token ID290
Feature activation-6.12e-03

Pos logit contributions
ursion+0.058
 bet+0.056
anna+0.056
Of+0.054
 Sure+0.054
Neg logit contributions
es-0.035
 rats-0.032
ts-0.031
 stains-0.030
 marks-0.030
Token cakes
Token ID30849
Feature activation-1.98e-02

Pos logit contributions
es+0.033
isk+0.030
adoes+0.029
bes+0.028
ings+0.028
Neg logit contributions
 bet-0.039
 pleasure-0.039
anna-0.036
Of-0.036
ursion-0.035
Token and
Token ID290
Feature activation-1.54e-03

Pos logit contributions
 rats+0.032
ts+0.031
adoes+0.030
 mice+0.030
es+0.029
Neg logit contributions
ursion-0.022
anna-0.022
 bet-0.022
 pad-0.022
 Sure-0.021
Token cookies
Token ID14746
Feature activation-4.55e-02

Pos logit contributions
es+0.002
ings+0.002
isk+0.002
adoes+0.001
iders+0.001
Neg logit contributions
anna-0.003
 bet-0.003
Of-0.003
 pleasure-0.002
 piping-0.002
Token and
Token ID290
Feature activation+6.71e-04

Pos logit contributions
 rats+0.057
es+0.056
ts+0.054
adoes+0.053
 mice+0.051
Neg logit contributions
ursion-0.074
 bet-0.072
anna-0.071
 Sure-0.068
 sur-0.068
Token ch
Token ID442
Feature activation+7.95e-03

Pos logit contributions
 bet+0.001
ursion+0.001
anna+0.001
Of+0.001
 pleasure+0.001
Neg logit contributions
es-0.001
ts-0.001
isk-0.001
ings-0.001
 rats-0.000
Tokenocol
Token ID4668
Feature activation-1.29e-01

Pos logit contributions
anna+0.013
ursion+0.013
 bet+0.012
 pleasure+0.011
 sur+0.011
Neg logit contributions
es-0.011
 not-0.010
 rats-0.010
 puzzles-0.010
 stains-0.010
Tokenates
Token ID689
Feature activation+4.07e-03

Pos logit contributions
 not+0.134
 accidents+0.125
 rats+0.123
 stains+0.123
 blood+0.115
Neg logit contributions
anna-0.236
ursion-0.226
 pad-0.216
 bet-0.211
 pleasure-0.204
Token and
Token ID290
Feature activation-4.12e-03

Pos logit contributions
anna+0.006
 bet+0.006
ursion+0.006
 pad+0.006
 sur+0.005
Neg logit contributions
 rats-0.006
adoes-0.005
ts-0.005
isk-0.005
 mice-0.005
Token ice
Token ID4771
Feature activation-6.65e-02

Pos logit contributions
es+0.004
 rats+0.003
ts+0.003
 stains+0.003
 marks+0.003
Neg logit contributions
ursion-0.008
 bet-0.008
anna-0.008
Of-0.008
 Sure-0.008
Token cream
Token ID8566
Feature activation-1.86e-02

Pos logit contributions
 rats+0.081
adoes+0.078
es+0.077
 mice+0.077
 accidents+0.075
Neg logit contributions
anna-0.104
round-0.089
ursion-0.089
ya-0.089
 bet-0.088
Token.
Token ID13
Feature activation-4.38e-03

Pos logit contributions
es+0.022
 rats+0.022
ts+0.021
adoes+0.021
 stains+0.020
Neg logit contributions
ursion-0.031
 bet-0.030
anna-0.030
 Sure-0.029
 sur-0.029
Tokenoll
Token ID692
Feature activation-4.01e-02

Pos logit contributions
es+0.082
 rats+0.079
ts+0.078
 stains+0.076
adoes+0.076
Neg logit contributions
ursion-0.083
anna-0.078
 bet-0.078
Of-0.073
 Sure-0.072
Tokenip
Token ID541
Feature activation-3.42e-02

Pos logit contributions
es+0.066
 rats+0.066
 stains+0.065
adoes+0.065
 mice+0.064
Neg logit contributions
anna-0.050
ursion-0.050
 bet-0.045
 Sure-0.042
Of-0.042
Tokenops
Token ID2840
Feature activation-5.27e-02

Pos logit contributions
adoes+0.029
 rats+0.028
 mice+0.024
 snakes+0.024
 stains+0.024
Neg logit contributions
anna-0.072
ursion-0.067
 pad-0.065
ya-0.063
 bet-0.063
Token,
Token ID11
Feature activation-1.85e-02

Pos logit contributions
 rats+0.060
es+0.060
ts+0.058
adoes+0.057
 stains+0.055
Neg logit contributions
ursion-0.093
anna-0.091
 bet-0.087
 pad-0.084
 sur-0.082
Token ch
Token ID442
Feature activation+8.90e-03

Pos logit contributions
es+0.024
ts+0.022
 rats+0.022
 stains+0.022
 marks+0.021
Neg logit contributions
ursion-0.030
 bet-0.030
anna-0.030
Of-0.029
 Sure-0.029
Tokenocol
Token ID4668
Feature activation-1.28e-01

Pos logit contributions
anna+0.014
ursion+0.013
 bet+0.013
 sur+0.012
ya+0.012
Neg logit contributions
es-0.012
 not-0.012
 rats-0.012
adoes-0.012
 puzzles-0.012
Tokenates
Token ID689
Feature activation-3.30e-04

Pos logit contributions
 rats+0.121
 stains+0.120
 not+0.118
 accidents+0.117
 mice+0.112
Neg logit contributions
anna-0.250
ursion-0.240
 pad-0.232
 bet-0.223
 sur-0.219
Token,
Token ID11
Feature activation-1.78e-02

Pos logit contributions
 rats+0.000
adoes+0.000
ts+0.000
 mice+0.000
es+0.000
Neg logit contributions
anna-0.000
ursion-0.000
 bet-0.000
 pad-0.000
 sur-0.000
Token g
Token ID308
Feature activation-3.16e-02

Pos logit contributions
es+0.022
 rats+0.020
ts+0.020
 stains+0.019
 marks+0.019
Neg logit contributions
ursion-0.031
 bet-0.031
anna-0.030
Of-0.029
 Sure-0.029
Tokenummies
Token ID39578
Feature activation-5.30e-02

Pos logit contributions
es+0.045
 rats+0.044
ts+0.042
 stains+0.041
 puzzles+0.041
Neg logit contributions
anna-0.054
ursion-0.047
ya-0.045
 bet-0.044
 sur-0.044
Token,
Token ID11
Feature activation-1.87e-02

Pos logit contributions
ts+0.069
 rats+0.068
es+0.067
adoes+0.066
 stains+0.064
Neg logit contributions
anna-0.084
ursion-0.081
 bet-0.078
 pad-0.075
 sur-0.075
Token park
Token ID3952
Feature activation+4.78e-02

Pos logit contributions
ursion+0.016
 bet+0.015
anna+0.015
Of+0.014
 Sure+0.014
Neg logit contributions
es-0.017
 rats-0.015
ts-0.015
 stains-0.015
 marks-0.015
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
ursion+0.109
anna+0.107
 bet+0.105
 pleasure+0.101
Of+0.100
Neg logit contributions
es-0.039
 not-0.033
 rats-0.030
 marks-0.029
 stains-0.028
Token They
Token ID1119
Feature activation-5.86e-03

Pos logit contributions
anna+0.020
ursion+0.020
 sur+0.019
Of+0.018
 lifetime+0.018
Neg logit contributions
es-0.009
 mice-0.009
 not-0.009
 puzzles-0.008
adoes-0.008
Token had
Token ID550
Feature activation-1.52e-02

Pos logit contributions
es+0.008
ts+0.007
 rats+0.007
 stains+0.007
 not+0.007
Neg logit contributions
ursion-0.010
anna-0.010
 bet-0.009
 pleasure-0.009
 Sure-0.009
Token the
Token ID262
Feature activation+7.91e-04

Pos logit contributions
es+0.017
 rats+0.015
ts+0.014
 stains+0.014
 marks+0.014
Neg logit contributions
ursion-0.030
 bet-0.029
anna-0.029
Of-0.028
 Sure-0.027
Token best
Token ID1266
Feature activation+1.08e-01

Pos logit contributions
anna+0.001
ursion+0.001
 bet+0.001
 Sure+0.001
ounded+0.001
Neg logit contributions
 marks-0.001
 rats-0.001
 stains-0.001
 not-0.001
 cookies-0.001
Token time
Token ID640
Feature activation+6.76e-02

Pos logit contributions
ursion+0.178
anna+0.163
Of+0.160
ounded+0.160
 bet+0.160
Neg logit contributions
 marks-0.153
 rats-0.149
 stains-0.148
 sandwiches-0.148
es-0.147
Token playing
Token ID2712
Feature activation-3.58e-02

Pos logit contributions
ursion+0.146
 bet+0.139
anna+0.136
Of+0.136
 Sure+0.132
Neg logit contributions
es-0.072
 rats-0.059
 not-0.058
 marks-0.057
ts-0.056
Token together
Token ID1978
Feature activation+4.71e-02

Pos logit contributions
es+0.039
 rats+0.037
 stains+0.037
 marks+0.035
ts+0.034
Neg logit contributions
 bet-0.066
ursion-0.066
anna-0.062
 Sure-0.061
 sur-0.061
Token on
Token ID319
Feature activation-1.43e-02

Pos logit contributions
ursion+0.098
 bet+0.094
anna+0.094
Of+0.090
 Sure+0.090
Neg logit contributions
es-0.048
 rats-0.042
ts-0.040
 stains-0.040
 marks-0.039
Token the
Token ID262
Feature activation+1.53e-03

Pos logit contributions
es+0.016
 rats+0.014
 stains+0.013
isk+0.013
ts+0.013
Neg logit contributions
ursion-0.026
 bet-0.026
 Sure-0.025
 pleasure-0.025
 sur-0.025
Token then
Token ID788
Feature activation+6.07e-02

Pos logit contributions
ursion+0.021
anna+0.020
 bet+0.019
Of+0.019
 Sure+0.019
Neg logit contributions
es-0.016
 rats-0.014
 not-0.014
ts-0.014
 stains-0.014
Token Jack
Token ID3619
Feature activation+3.39e-02

Pos logit contributions
ursion+0.100
anna+0.095
 bet+0.095
Of+0.091
 Sure+0.090
Neg logit contributions
es-0.087
 rats-0.079
ts-0.077
 stains-0.077
 marks-0.077
Token said
Token ID531
Feature activation+3.98e-02

Pos logit contributions
ursion+0.053
 bet+0.049
anna+0.049
Of+0.048
 Sure+0.047
Neg logit contributions
es-0.053
 rats-0.047
 marks-0.047
 stains-0.046
ts-0.046
Token,
Token ID11
Feature activation+1.29e-02

Pos logit contributions
ursion+0.071
 bet+0.067
anna+0.067
 Sure+0.064
Of+0.063
Neg logit contributions
es-0.053
 rats-0.047
ts-0.046
 not-0.045
 stains-0.045
Token "
Token ID366
Feature activation+2.48e-02

Pos logit contributions
ursion+0.025
anna+0.023
 bet+0.023
ounded+0.022
 pleasure+0.021
Neg logit contributions
es-0.015
 not-0.015
 rats-0.012
 mice-0.012
 marks-0.012
TokenLet
Token ID5756
Feature activation+9.23e-02

Pos logit contributions
anna+0.042
ursion+0.042
ounded+0.040
 pleasure+0.040
 bet+0.039
Neg logit contributions
es-0.030
 marks-0.024
isk-0.024
 not-0.024
 mice-0.024
Token's
Token ID338
Feature activation+8.49e-03

Pos logit contributions
ursion+0.173
 bet+0.162
 Sure+0.161
anna+0.161
Of+0.157
Neg logit contributions
es-0.112
 marks-0.102
 not-0.101
 rats-0.098
 stains-0.096
Token race
Token ID3234
Feature activation+5.78e-02

Pos logit contributions
ursion+0.013
anna+0.013
 bet+0.012
Of+0.012
 Sure+0.012
Neg logit contributions
es-0.013
 rats-0.012
 marks-0.012
 not-0.012
ts-0.011
Token inside
Token ID2641
Feature activation+2.91e-02

Pos logit contributions
ursion+0.112
anna+0.109
 bet+0.106
Of+0.103
 Sure+0.103
Neg logit contributions
es-0.067
ts-0.058
 rats-0.057
 marks-0.057
 not-0.057
Token the
Token ID262
Feature activation+3.59e-02

Pos logit contributions
ursion+0.057
 bet+0.055
anna+0.055
Of+0.053
 Sure+0.052
Neg logit contributions
es-0.032
 rats-0.029
ts-0.027
 stains-0.027
 marks-0.027
Token tent
Token ID11105
Feature activation+3.29e-02

Pos logit contributions
anna+0.066
ursion+0.065
 bet+0.062
Of+0.062
 Sure+0.060
Neg logit contributions
es-0.042
 rats-0.042
 marks-0.041
 puzzles-0.040
 mice-0.040
Token smiled
Token ID13541
Feature activation-4.09e-03

Pos logit contributions
es+0.002
 rats+0.002
ts+0.002
 stains+0.002
 marks+0.002
Neg logit contributions
ursion-0.002
 bet-0.002
anna-0.002
Of-0.002
 Sure-0.002
Token and
Token ID290
Feature activation+4.64e-03

Pos logit contributions
es+0.004
 not+0.003
 marks+0.003
 rats+0.003
 stains+0.003
Neg logit contributions
ursion-0.009
anna-0.009
 bet-0.009
Of-0.008
 Sure-0.008
Token said
Token ID531
Feature activation+3.31e-02

Pos logit contributions
ursion+0.009
anna+0.009
 bet+0.008
 pleasure+0.008
uster+0.008
Neg logit contributions
 not-0.006
es-0.006
 all-0.005
ts-0.005
 cookies-0.005
Token,
Token ID11
Feature activation-4.69e-03

Pos logit contributions
ursion+0.069
anna+0.065
 bet+0.065
 pleasure+0.060
 Sure+0.060
Neg logit contributions
es-0.037
 not-0.032
ts-0.028
 rats-0.028
 marks-0.027
Token "
Token ID366
Feature activation+2.57e-03

Pos logit contributions
 not+0.005
es+0.004
oni+0.003
 mice+0.003
 rats+0.003
Neg logit contributions
ursion-0.010
 bet-0.010
anna-0.010
 pleasure-0.009
 sur-0.009
TokenOf
Token ID5189
Feature activation+9.02e-02

Pos logit contributions
anna+0.004
ursion+0.003
ird+0.003
 pleasure+0.003
 pad+0.003
Neg logit contributions
 not-0.004
es-0.004
 stains-0.003
 rats-0.003
't-0.003
Token course
Token ID1781
Feature activation+8.19e-02

Pos logit contributions
ursion+0.178
anna+0.176
 bet+0.172
 Sure+0.169
ounded+0.165
Neg logit contributions
es-0.091
 rats-0.086
 not-0.082
 marks-0.080
ts-0.078
Token you
Token ID345
Feature activation+4.53e-02

Pos logit contributions
ursion+0.180
 bet+0.170
anna+0.166
 sur+0.158
 Sure+0.157
Neg logit contributions
es-0.082
 not-0.076
 rats-0.072
 mice-0.066
ts-0.063
Token can
Token ID460
Feature activation+2.46e-02

Pos logit contributions
ursion+0.076
anna+0.074
 Sure+0.071
 bet+0.069
Of+0.069
Neg logit contributions
es-0.064
 marks-0.058
 not-0.057
 stains-0.055
 rats-0.054
Token!
Token ID0
Feature activation+2.37e-02

Pos logit contributions
ursion+0.050
anna+0.048
 bet+0.047
Of+0.046
 Sure+0.046
Neg logit contributions
es-0.026
 not-0.022
 marks-0.022
 stains-0.021
ts-0.021
Token But
Token ID887
Feature activation+6.37e-02

Pos logit contributions
ya+0.034
ursion+0.034
anna+0.033
 sur+0.032
den+0.031
Neg logit contributions
es-0.036
 not-0.033
isk-0.031
 mice-0.030
't-0.030
Token explore
Token ID7301
Feature activation-4.26e-03

Pos logit contributions
es+0.043
 rats+0.040
ts+0.040
 stains+0.039
 marks+0.039
Neg logit contributions
ursion-0.048
anna-0.045
 bet-0.044
 Sure-0.043
Of-0.042
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
es+0.005
 rats+0.004
 stains+0.004
ts+0.004
 marks+0.004
Neg logit contributions
ursion-0.008
 bet-0.008
anna-0.008
Of-0.008
 Sure-0.008
Token He
Token ID679
Feature activation-2.36e-02

Pos logit contributions
es+0.013
 not+0.013
 rats+0.013
 mice+0.013
 bones+0.012
Neg logit contributions
ursion-0.020
ya-0.019
anna-0.019
ounded-0.019
 bet-0.018
Token found
Token ID1043
Feature activation-6.83e-03

Pos logit contributions
es+0.033
 rats+0.031
ts+0.030
 stains+0.030
 marks+0.029
Neg logit contributions
ursion-0.038
 bet-0.037
anna-0.037
Of-0.035
 Sure-0.035
Token a
Token ID257
Feature activation+1.38e-03

Pos logit contributions
es+0.007
 rats+0.006
ts+0.006
 stains+0.005
 marks+0.005
Neg logit contributions
ursion-0.014
 bet-0.014
anna-0.014
 Sure-0.013
Of-0.013
Token way
Token ID835
Feature activation+1.29e-01

Pos logit contributions
anna+0.003
ursion+0.003
 bet+0.002
 Sure+0.002
ounded+0.002
Neg logit contributions
 not-0.002
 rats-0.001
 stains-0.001
 sandwiches-0.001
 marks-0.001
Token out
Token ID503
Feature activation+5.56e-02

Pos logit contributions
ursion+0.258
Of+0.256
 pleasure+0.250
anna+0.249
 bet+0.249
Neg logit contributions
 not-0.123
es-0.121
 rats-0.108
 marks-0.104
 stains-0.102
Token of
Token ID286
Feature activation-1.02e-02

Pos logit contributions
ursion+0.111
anna+0.108
Of+0.107
 bet+0.106
 Sure+0.104
Neg logit contributions
es-0.063
 rats-0.053
ts-0.052
 not-0.051
 marks-0.050
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
es+0.010
 rats+0.008
ts+0.008
 stains+0.008
 marks+0.008
Neg logit contributions
ursion-0.021
 bet-0.021
anna-0.020
 pleasure-0.020
 Sure-0.020
Token lake
Token ID13546
Feature activation+4.01e-02

Pos logit contributions
ursion+0.035
anna+0.035
 bet+0.033
 Sure+0.032
Of+0.032
Neg logit contributions
es-0.029
 rats-0.029
 marks-0.028
 stains-0.028
ts-0.028
Token on
Token ID319
Feature activation-5.55e-03

Pos logit contributions
ursion+0.078
 bet+0.076
anna+0.075
Of+0.072
 Sure+0.072
Neg logit contributions
es-0.044
 rats-0.040
ts-0.038
 stains-0.038
 marks-0.038
Token wet
Token ID9583
Feature activation-3.38e-02

Pos logit contributions
 bet+0.010
ursion+0.010
 pleasure+0.010
anna+0.009
 sur+0.009
Neg logit contributions
es-0.008
 rats-0.006
ts-0.006
adoes-0.006
bes-0.006
Token.
Token ID13
Feature activation+8.14e-03

Pos logit contributions
es+0.042
ts+0.038
 rats+0.038
isk+0.035
bes+0.035
Neg logit contributions
ursion-0.059
 bet-0.057
anna-0.056
 sur-0.054
 pleasure-0.053
Token
Token ID220
Feature activation+3.62e-02

Pos logit contributions
ursion+0.013
anna+0.013
 bet+0.012
 sur+0.012
Of+0.011
Neg logit contributions
es-0.012
 rats-0.011
 not-0.011
 mice-0.011
 stains-0.011
Token
Token ID198
Feature activation+4.23e-03

Pos logit contributions
ursion+0.054
 bet+0.052
anna+0.051
 Sure+0.048
Of+0.048
Neg logit contributions
es-0.056
 rats-0.053
ts-0.052
 stains-0.051
 marks-0.051
Token
Token ID198
Feature activation+5.40e-03

Pos logit contributions
ursion+0.008
anna+0.008
 bet+0.007
 pleasure+0.007
 sur+0.007
Neg logit contributions
es-0.005
 not-0.005
 rats-0.004
 mice-0.004
 marks-0.004
TokenConf
Token ID18546
Feature activation+8.95e-02

Pos logit contributions
ursion+0.009
 bet+0.009
anna+0.009
 Sure+0.008
Of+0.008
Neg logit contributions
es-0.007
 rats-0.007
ts-0.007
 stains-0.007
 marks-0.007
Tokenused
Token ID1484
Feature activation+6.67e-02

Pos logit contributions
anna+0.095
ursion+0.093
 bet+0.088
 pleasure+0.085
Of+0.084
Neg logit contributions
es-0.176
 not-0.164
 rats-0.161
ts-0.160
 marks-0.155
Token,
Token ID11
Feature activation-5.00e-03

Pos logit contributions
ursion+0.114
 bet+0.111
anna+0.109
 Sure+0.105
Of+0.104
Neg logit contributions
es-0.088
 rats-0.081
ts-0.080
 stains-0.079
 marks-0.077
Token they
Token ID484
Feature activation+1.68e-02

Pos logit contributions
es+0.007
 rats+0.006
ts+0.006
 stains+0.006
 marks+0.006
Neg logit contributions
ursion-0.009
anna-0.008
 bet-0.008
 Sure-0.008
Of-0.008
Token started
Token ID2067
Feature activation+5.55e-02

Pos logit contributions
ursion+0.026
anna+0.025
 bet+0.024
 Sure+0.024
 pleasure+0.024
Neg logit contributions
es-0.026
 rats-0.024
ts-0.023
 not-0.023
 marks-0.023
Token arguing
Token ID11810
Feature activation-2.90e-03

Pos logit contributions
ursion+0.079
 bet+0.079
anna+0.077
 Sure+0.073
 sur+0.073
Neg logit contributions
es-0.088
 rats-0.082
ts-0.080
 stains-0.078
 mice-0.076
Token
Token ID198
Feature activation-3.60e-03

Pos logit contributions
es+0.007
 rats+0.006
 not+0.006
ts+0.006
 marks+0.006
Neg logit contributions
ursion-0.009
anna-0.008
 bet-0.008
 pleasure-0.008
 sur-0.008
TokenWhen
Token ID2215
Feature activation+4.37e-02

Pos logit contributions
es+0.005
 rats+0.005
ts+0.005
 stains+0.005
 marks+0.005
Neg logit contributions
ursion-0.006
 bet-0.005
anna-0.005
Of-0.005
 Sure-0.005
Token they
Token ID484
Feature activation+2.41e-02

Pos logit contributions
ursion+0.063
 bet+0.061
anna+0.059
 Sure+0.057
Of+0.057
Neg logit contributions
es-0.070
 rats-0.065
ts-0.064
 stains-0.064
 marks-0.063
Token arrived
Token ID5284
Feature activation+2.50e-02

Pos logit contributions
ursion+0.047
anna+0.046
 pleasure+0.044
 Sure+0.043
Of+0.043
Neg logit contributions
es-0.024
 not-0.024
 all-0.023
ts-0.023
 stains-0.021
Token,
Token ID11
Feature activation-5.34e-03

Pos logit contributions
ursion+0.045
 bet+0.043
anna+0.043
 Sure+0.041
Of+0.041
Neg logit contributions
es-0.032
 rats-0.029
ts-0.029
 stains-0.028
 marks-0.028
Token Mia
Token ID32189
Feature activation+1.44e-02

Pos logit contributions
es+0.009
ts+0.008
 stains+0.008
 rats+0.008
 marks+0.008
Neg logit contributions
 bet-0.007
ursion-0.007
 Sure-0.006
anna-0.006
Of-0.006
Token was
Token ID373
Feature activation+9.36e-03

Pos logit contributions
ursion+0.025
 bet+0.023
Of+0.023
 pleasure+0.023
anna+0.023
Neg logit contributions
es-0.020
 rats-0.017
ts-0.017
 marks-0.017
 stains-0.017
Token very
Token ID845
Feature activation-7.15e-03

Pos logit contributions
ursion+0.014
 bet+0.013
anna+0.013
 sur+0.012
 pleasure+0.012
Neg logit contributions
es-0.015
 rats-0.014
 stains-0.014
ts-0.013
 marks-0.013
Token excited
Token ID6568
Feature activation-1.18e-02

Pos logit contributions
es+0.011
 not+0.010
 rats+0.010
ts+0.010
 stains+0.010
Neg logit contributions
ursion-0.011
anna-0.011
 bet-0.011
 Sure-0.010
Of-0.010
Token.
Token ID13
Feature activation+5.59e-03

Pos logit contributions
es+0.015
 rats+0.014
ts+0.013
 stains+0.013
 marks+0.013
Neg logit contributions
ursion-0.021
anna-0.021
 bet-0.020
 Sure-0.019
Of-0.019
Token She
Token ID1375
Feature activation-5.87e-03

Pos logit contributions
ursion+0.010
anna+0.010
 sur+0.009
 bet+0.009
ounded+0.009
Neg logit contributions
es-0.007
 rats-0.007
 mice-0.006
 not-0.006
 stains-0.006
Token blue
Token ID4171
Feature activation+1.50e-03

Pos logit contributions
es+0.029
 rats+0.025
ts+0.025
 stains+0.024
 mice+0.023
Neg logit contributions
ursion-0.040
 bet-0.039
anna-0.039
 pleasure-0.038
 Sure-0.037
Token snow
Token ID6729
Feature activation-3.35e-02

Pos logit contributions
anna+0.002
ursion+0.002
 bet+0.002
 Sure+0.002
 pleasure+0.002
Neg logit contributions
es-0.002
ts-0.002
 rats-0.002
 mice-0.002
 stains-0.002
Tokenman
Token ID805
Feature activation-5.03e-02

Pos logit contributions
 rats+0.034
ts+0.033
es+0.032
 stains+0.032
 mice+0.032
Neg logit contributions
anna-0.060
ursion-0.058
 bet-0.057
 Sure-0.057
 pleasure-0.055
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
es+0.057
 rats+0.054
ts+0.053
 stains+0.052
 marks+0.050
Neg logit contributions
ursion-0.091
anna-0.090
 bet-0.088
 pleasure-0.084
Of-0.083
Token But
Token ID887
Feature activation+5.23e-02

Pos logit contributions
es+0.017
 rats+0.016
 not+0.016
adoes+0.015
 stains+0.015
Neg logit contributions
ursion-0.017
anna-0.017
 bet-0.016
ya-0.016
ounded-0.016
Token you
Token ID345
Feature activation+3.96e-02

Pos logit contributions
ursion+0.081
 bet+0.078
anna+0.077
 Sure+0.073
Of+0.073
Neg logit contributions
es-0.079
 rats-0.073
ts-0.072
 stains-0.071
 marks-0.070
Token know
Token ID760
Feature activation+4.80e-03

Pos logit contributions
 bet+0.046
ursion+0.040
 pleasure+0.035
anna+0.035
Of+0.034
Neg logit contributions
es-0.075
ings-0.075
bes-0.075
adoes-0.073
 rats-0.070
Token,
Token ID11
Feature activation-2.55e-02

Pos logit contributions
anna+0.008
ursion+0.008
 bet+0.008
Of+0.007
 pleasure+0.007
Neg logit contributions
es-0.006
 rats-0.005
ts-0.005
bes-0.005
 stains-0.005
Token snow
Token ID6729
Feature activation-3.36e-02

Pos logit contributions
es+0.038
ts+0.034
 rats+0.034
 stains+0.034
 marks+0.033
Neg logit contributions
 bet-0.038
anna-0.037
ursion-0.037
Of-0.036
 pleasure-0.035
Tokenmen
Token ID3653
Feature activation-3.90e-03

Pos logit contributions
 rats+0.033
 puzzles+0.033
 mice+0.033
 stains+0.032
es+0.031
Neg logit contributions
anna-0.057
 bet-0.057
 Sure-0.055
 pleasure-0.054
ursion-0.054
Token are
Token ID389
Feature activation-4.55e-02

Pos logit contributions
es+0.005
 rats+0.005
ts+0.005
bes+0.005
 mice+0.005
Neg logit contributions
 bet-0.006
ursion-0.006
anna-0.006
 pleasure-0.006
 sur-0.005
Token in
Token ID287
Feature activation+2.43e-02

Pos logit contributions
es+0.008
 rats+0.008
 stains+0.007
 marks+0.007
ts+0.007
Neg logit contributions
ursion-0.012
 bet-0.011
anna-0.011
 Sure-0.011
Of-0.011
Token its
Token ID663
Feature activation-2.51e-02

Pos logit contributions
ursion+0.047
 bet+0.047
 Sure+0.045
 pleasure+0.045
anna+0.044
Neg logit contributions
es-0.025
 rats-0.022
ts-0.022
 stains-0.022
 marks-0.021
Token pocket
Token ID10000
Feature activation+1.20e-02

Pos logit contributions
es+0.035
 rats+0.032
 stains+0.031
ts+0.031
 marks+0.031
Neg logit contributions
ursion-0.042
 bet-0.040
anna-0.040
Of-0.038
 Sure-0.038
Token.
Token ID13
Feature activation+3.43e-03

Pos logit contributions
ursion+0.024
 bet+0.023
anna+0.023
 Sure+0.022
Of+0.022
Neg logit contributions
es-0.013
 rats-0.012
ts-0.011
 stains-0.011
 marks-0.011
Token It
Token ID632
Feature activation-2.18e-02

Pos logit contributions
anna+0.007
ursion+0.007
 sur+0.006
 bet+0.006
ya+0.006
Neg logit contributions
es-0.004
 mice-0.003
 bones-0.003
 not-0.003
 rats-0.003
Token me
Token ID502
Feature activation+2.66e-02

Pos logit contributions
es+0.034
 rats+0.033
 stains+0.032
 marks+0.032
adoes+0.032
Neg logit contributions
 bet-0.030
ursion-0.030
anna-0.029
Of-0.028
 Sure-0.028
Tokenowed
Token ID6972
Feature activation+2.00e-02

Pos logit contributions
ursion+0.038
anna+0.037
 bet+0.037
 Sure+0.034
Of+0.034
Neg logit contributions
es-0.042
 rats-0.040
 stains-0.039
 marks-0.039
ts-0.039
Token to
Token ID284
Feature activation-1.44e-02

Pos logit contributions
 bet+0.029
 pleasure+0.029
 Sure+0.029
anna+0.028
Of+0.028
Neg logit contributions
 rats-0.028
 stains-0.027
es-0.027
ts-0.027
 marks-0.027
Token let
Token ID1309
Feature activation+8.18e-02

Pos logit contributions
es+0.015
 rats+0.013
ts+0.013
 stains+0.013
 marks+0.013
Neg logit contributions
ursion-0.030
anna-0.028
 bet-0.028
Of-0.027
 Sure-0.027
Token the
Token ID262
Feature activation+2.27e-02

Pos logit contributions
ursion+0.165
 bet+0.162
anna+0.160
 Sure+0.154
Of+0.152
Neg logit contributions
es-0.083
 rats-0.074
 stains-0.073
ts-0.072
 marks-0.069
Token child
Token ID1200
Feature activation+5.90e-02

Pos logit contributions
ursion+0.030
 bet+0.028
anna+0.028
Of+0.027
 Sure+0.026
Neg logit contributions
es-0.040
ts-0.037
 rats-0.037
 stains-0.036
 marks-0.036
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
ursion+0.068
ounded+0.066
 bet+0.064
anna+0.064
 sur+0.064
Neg logit contributions
es-0.047
 not-0.042
 mice-0.041
 rats-0.040
adoes-0.038
Token
Token ID198
Feature activation+1.10e-02

Pos logit contributions
ursion+0.028
 bet+0.027
anna+0.027
 sur+0.026
 pleasure+0.026
Neg logit contributions
es-0.018
 rats-0.016
 not-0.016
 marks-0.015
ts-0.015
TokenThe
Token ID464
Feature activation+8.12e-03

Pos logit contributions
ursion+0.021
anna+0.020
 pleasure+0.020
 bet+0.020
ounded+0.019
Neg logit contributions
es-0.012
 rats-0.011
 not-0.011
ts-0.010
bes-0.010
Token peanut
Token ID26636
Feature activation-7.16e-02

Pos logit contributions
ursion+0.014
anna+0.014
 bet+0.013
 Sure+0.013
Of+0.013
Neg logit contributions
es-0.010
 rats-0.010
 marks-0.010
ts-0.010
 mice-0.010
Token stops
Token ID9911
Feature activation-2.12e-04

Pos logit contributions
isk+0.110
adoes+0.104
 rats+0.103
ings+0.100
 stains+0.099
Neg logit contributions
ursion-0.092
anna-0.090
 bet-0.087
 sur-0.083
ya-0.081
Token spinning
Token ID19493
Feature activation+1.92e-02

Pos logit contributions
es+0.000
 rats+0.000
ts+0.000
 stains+0.000
bes+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
anna-0.000
 Sure-0.000
 sur-0.000
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
ursion+0.033
 bet+0.032
anna+0.031
 Sure+0.030
 sur+0.030
Neg logit contributions
es-0.024
 rats-0.023
ts-0.022
 stains-0.022
 marks-0.021
Token It
Token ID632
Feature activation-2.74e-02

Pos logit contributions
ursion+0.021
ounded+0.020
anna+0.020
 bet+0.019
 sur+0.019
Neg logit contributions
es-0.011
 mice-0.010
 not-0.010
 rats-0.010
 puzzles-0.009
Token lands
Token ID8604
Feature activation-1.13e-02

Pos logit contributions
es+0.038
 rats+0.035
 stains+0.034
ts+0.034
 marks+0.034
Neg logit contributions
ursion-0.046
 bet-0.044
anna-0.044
Of-0.041
 Sure-0.041
Token on
Token ID319
Feature activation-6.12e-03

Pos logit contributions
 rats+0.013
es+0.012
 stains+0.012
ts+0.012
adoes+0.012
Neg logit contributions
ursion-0.020
 bet-0.019
anna-0.018
 Sure-0.018
 sur-0.018
Token the
Token ID262
Feature activation+1.55e-02

Pos logit contributions
es+0.007
 rats+0.006
ts+0.005
 stains+0.005
bes+0.005
Neg logit contributions
 bet-0.012
ursion-0.012
 Sure-0.012
 pleasure-0.011
anna-0.011
Token the
Token ID262
Feature activation+1.96e-02

Pos logit contributions
es+0.018
 rats+0.016
 stains+0.016
ts+0.016
isk+0.015
Neg logit contributions
anna-0.034
 bet-0.034
ursion-0.033
 pleasure-0.032
 Sure-0.032
Token stove
Token ID27635
Feature activation-1.60e-02

Pos logit contributions
 bet+0.029
ursion+0.029
anna+0.028
 Sure+0.027
 pleasure+0.027
Neg logit contributions
es-0.031
isk-0.028
ts-0.026
 rats-0.026
 stains-0.026
Token.
Token ID13
Feature activation+4.51e-03

Pos logit contributions
es+0.018
 rats+0.018
ts+0.017
 stains+0.016
 mice+0.016
Neg logit contributions
ursion-0.029
 bet-0.029
anna-0.028
 Sure-0.027
 pleasure-0.027
Token
Token ID198
Feature activation+2.72e-04

Pos logit contributions
ursion+0.007
 sur+0.007
anna+0.007
 bet+0.006
round+0.006
Neg logit contributions
es-0.007
 mice-0.006
 not-0.006
 stains-0.006
 marks-0.006
Token
Token ID198
Feature activation+1.64e-03

Pos logit contributions
ursion+0.000
 bet+0.000
anna+0.000
 Sure+0.000
Of+0.000
Neg logit contributions
es-0.000
 rats-0.000
ts-0.000
 stains-0.000
 marks-0.000
TokenEmily
Token ID48640
Feature activation+2.69e-02

Pos logit contributions
ursion+0.002
 bet+0.002
anna+0.002
Of+0.002
 Sure+0.002
Neg logit contributions
es-0.003
 rats-0.003
ts-0.003
 stains-0.002
 marks-0.002
Token learned
Token ID4499
Feature activation-4.16e-02

Pos logit contributions
ursion+0.042
anna+0.041
 bet+0.041
Of+0.038
 sur+0.038
Neg logit contributions
es-0.039
 rats-0.038
ts-0.036
 stains-0.036
 marks-0.035
Token an
Token ID281
Feature activation+2.69e-02

Pos logit contributions
es+0.044
 rats+0.040
ts+0.040
 stains+0.037
 mice+0.036
Neg logit contributions
ursion-0.080
Of-0.080
 bet-0.079
anna-0.078
 Sure-0.076
Token important
Token ID1593
Feature activation+1.79e-02

Pos logit contributions
ursion+0.050
 bet+0.048
 Sure+0.047
anna+0.046
 sur+0.046
Neg logit contributions
es-0.032
 rats-0.030
 marks-0.029
 stains-0.028
ts-0.028
Token lesson
Token ID11483
Feature activation+2.48e-02

Pos logit contributions
ursion+0.030
 bet+0.029
anna+0.029
 Sure+0.027
Of+0.027
Neg logit contributions
es-0.025
 rats-0.023
ts-0.022
 stains-0.022
 marks-0.022
Token that
Token ID326
Feature activation-3.95e-02

Pos logit contributions
ursion+0.050
anna+0.048
 bet+0.048
 Sure+0.046
Of+0.046
Neg logit contributions
es-0.026
 rats-0.023
ts-0.023
 stains-0.022
 marks-0.022
Token chest
Token ID7721
Feature activation+4.81e-03

Pos logit contributions
es+0.019
 rats+0.018
 marks+0.017
 stains+0.017
ts+0.017
Neg logit contributions
ursion-0.029
 bet-0.027
anna-0.026
Of-0.026
 Sure-0.026
Token.
Token ID13
Feature activation-2.49e-03

Pos logit contributions
ursion+0.009
anna+0.009
 bet+0.009
 Sure+0.008
Of+0.008
Neg logit contributions
es-0.005
 rats-0.005
ts-0.005
 stains-0.005
 marks-0.005
Token "
Token ID366
Feature activation-1.07e-02

Pos logit contributions
 not+0.002
es+0.002
 cookies+0.002
 stains+0.002
 mice+0.002
Neg logit contributions
ursion-0.005
anna-0.005
ya-0.005
 bet-0.005
 pleasure-0.005
TokenHmm
Token ID44217
Feature activation+3.77e-02

Pos logit contributions
es+0.012
 stains+0.011
 rats+0.011
ts+0.011
 marks+0.011
Neg logit contributions
ursion-0.020
anna-0.020
 pleasure-0.019
 sur-0.018
ounded-0.018
Token,
Token ID11
Feature activation+9.57e-05

Pos logit contributions
ursion+0.070
 bet+0.067
anna+0.066
Of+0.064
 Sure+0.064
Neg logit contributions
es-0.047
 rats-0.043
ts-0.042
 stains-0.040
 marks-0.040
Token it
Token ID340
Feature activation-1.50e-02

Pos logit contributions
ursion+0.000
 bet+0.000
anna+0.000
Of+0.000
 Sure+0.000
Neg logit contributions
es-0.000
 rats-0.000
ts-0.000
 stains-0.000
 marks-0.000
Token sounds
Token ID5238
Feature activation-1.48e-02

Pos logit contributions
es+0.020
 rats+0.019
ts+0.019
 stains+0.019
 mice+0.018
Neg logit contributions
ursion-0.024
 bet-0.024
anna-0.024
 Sure-0.021
Of-0.021
Token good
Token ID922
Feature activation-5.74e-03

Pos logit contributions
es+0.016
 not+0.016
 stains+0.016
 rats+0.015
ts+0.015
Neg logit contributions
ursion-0.029
anna-0.027
 bet-0.027
 Sure-0.027
 sur-0.026
Token.
Token ID13
Feature activation+1.50e-02

Pos logit contributions
es+0.007
 rats+0.006
 stains+0.006
ts+0.006
 marks+0.006
Neg logit contributions
ursion-0.011
 bet-0.011
anna-0.010
Of-0.010
 Sure-0.010
Token You
Token ID921
Feature activation+4.21e-02

Pos logit contributions
ursion+0.025
anna+0.023
ya+0.023
 sur+0.023
ounded+0.023
Neg logit contributions
es-0.022
 mice-0.020
 rats-0.020
 not-0.020
adoes-0.019
Token are
Token ID389
Feature activation-3.60e-02

Pos logit contributions
ursion+0.061
 bet+0.060
anna+0.057
Of+0.054
 pleasure+0.054
Neg logit contributions
es-0.067
 rats-0.063
 stains-0.061
ts-0.061
 marks-0.060
Token slide
Token ID10649
Feature activation+3.06e-02

Pos logit contributions
ursion+0.025
anna+0.024
 bet+0.024
 Sure+0.022
Of+0.022
Neg logit contributions
es-0.021
 rats-0.019
 stains-0.019
ts-0.018
 marks-0.018
Token and
Token ID290
Feature activation-7.65e-03

Pos logit contributions
anna+0.077
 pleasure+0.076
ursion+0.076
 bet+0.074
 Shall+0.073
Neg logit contributions
 not-0.018
es-0.017
 all-0.015
 marks-0.011
 with-0.011
Token Max
Token ID5436
Feature activation-5.10e-03

Pos logit contributions
 not+0.007
es+0.007
ts+0.007
 all+0.006
 rats+0.006
Neg logit contributions
ursion-0.016
anna-0.016
 pleasure-0.016
 bet-0.015
uster-0.015
Token climbed
Token ID19952
Feature activation+2.67e-02

Pos logit contributions
es+0.007
 not+0.006
ts+0.006
 rats+0.006
 marks+0.006
Neg logit contributions
ursion-0.009
 pleasure-0.009
 bet-0.009
anna-0.008
Of-0.008
Token up
Token ID510
Feature activation+2.95e-02

Pos logit contributions
ursion+0.056
anna+0.054
 bet+0.054
Of+0.052
 pleasure+0.051
Neg logit contributions
es-0.026
 rats-0.023
ts-0.022
 stains-0.022
 marks-0.022
Token to
Token ID284
Feature activation-1.04e-02

Pos logit contributions
ursion+0.062
 bet+0.060
anna+0.059
 Sure+0.058
Of+0.057
Neg logit contributions
es-0.028
 rats-0.025
ts-0.024
 stains-0.024
 marks-0.023
Token the
Token ID262
Feature activation+2.17e-02

Pos logit contributions
 all+0.002
 the+0.001
 not+0.001
ts+0.001
 rats+0.001
Neg logit contributions
anna-0.031
ursion-0.030
mber-0.029
enna-0.029
den-0.028
Token top
Token ID1353
Feature activation+4.88e-02

Pos logit contributions
ursion+0.038
 bet+0.037
anna+0.037
 Sure+0.035
Of+0.035
Neg logit contributions
es-0.028
 rats-0.026
ts-0.025
 stains-0.025
 marks-0.025
Token.
Token ID13
Feature activation-4.10e-03

Pos logit contributions
 pleasure+0.120
Of+0.117
anna+0.116
 bet+0.114
ursion+0.114
Neg logit contributions
es-0.030
 marks-0.028
 rats-0.026
 not-0.025
 stains-0.024
Token Tim
Token ID5045
Feature activation-1.40e-04

Pos logit contributions
 not+0.005
es+0.005
 mice+0.004
 stains+0.004
 bones+0.004
Neg logit contributions
ursion-0.008
anna-0.008
 bet-0.007
ya-0.007
 sur-0.007
Token watched
Token ID7342
Feature activation+3.08e-02

Pos logit contributions
es+0.000
 not+0.000
 rats+0.000
ts+0.000
 marks+0.000
Neg logit contributions
ursion-0.000
 bet-0.000
 pleasure-0.000
anna-0.000
 Sure-0.000
Token the
Token ID262
Feature activation-4.53e-03

Pos logit contributions
es+0.093
isk+0.087
bes+0.086
 rats+0.083
ts+0.078
Neg logit contributions
 bet-0.122
anna-0.118
 pleasure-0.117
Of-0.116
 sur-0.113
Token mint
Token ID21043
Feature activation-1.52e-02

Pos logit contributions
es+0.007
ts+0.006
isk+0.006
 rats+0.006
bes+0.006
Neg logit contributions
 bet-0.007
 pleasure-0.007
ursion-0.007
anna-0.007
ya-0.006
Token,
Token ID11
Feature activation-3.03e-02

Pos logit contributions
 rats+0.018
es+0.018
isk+0.018
ts+0.018
 blood+0.017
Neg logit contributions
 bet-0.024
anna-0.024
ursion-0.024
ya-0.022
Of-0.021
Token the
Token ID262
Feature activation+1.68e-03

Pos logit contributions
es+0.055
 rats+0.049
ts+0.049
 stains+0.047
 marks+0.047
Neg logit contributions
 bet-0.038
Of-0.036
ursion-0.035
anna-0.035
 pleasure-0.034
Token basil
Token ID37792
Feature activation-1.05e-02

Pos logit contributions
 bet+0.003
ursion+0.003
anna+0.003
Of+0.003
 pleasure+0.003
Neg logit contributions
es-0.002
ts-0.002
 rats-0.002
 stains-0.002
isk-0.002
Token,
Token ID11
Feature activation-2.17e-02

Pos logit contributions
 rats+0.014
es+0.014
ts+0.013
adoes+0.013
isk+0.013
Neg logit contributions
 bet-0.016
anna-0.016
ursion-0.016
 pleasure-0.015
Of-0.014
Token and
Token ID290
Feature activation-1.27e-03

Pos logit contributions
es+0.031
 rats+0.029
ts+0.028
bes+0.028
 marks+0.027
Neg logit contributions
 bet-0.033
Of-0.031
anna-0.030
 pleasure-0.030
 Shall-0.029
Token the
Token ID262
Feature activation+6.48e-03

Pos logit contributions
es+0.001
 rats+0.001
ts+0.001
 stains+0.001
 marks+0.001
Neg logit contributions
ursion-0.003
anna-0.003
 bet-0.003
 Sure-0.002
Of-0.002
Token rose
Token ID8278
Feature activation+2.66e-02

Pos logit contributions
ursion+0.012
 bet+0.012
anna+0.011
Of+0.011
 pleasure+0.011
Neg logit contributions
es-0.008
 rats-0.007
ts-0.007
 stains-0.007
 marks-0.006
Tokenmary
Token ID6874
Feature activation-2.22e-02

Pos logit contributions
 bet+0.044
ursion+0.043
anna+0.043
Of+0.040
 Sure+0.040
Neg logit contributions
es-0.034
 rats-0.033
ts-0.031
 stains-0.030
adoes-0.030
Token.
Token ID13
Feature activation-4.31e-03

Pos logit contributions
es+0.028
 rats+0.027
ts+0.026
adoes+0.026
 stains+0.025
Neg logit contributions
ursion-0.036
 bet-0.036
anna-0.036
Of-0.034
 Sure-0.033
Token so
Token ID523
Feature activation+3.25e-02

Pos logit contributions
anna+0.004
 bet+0.004
 pleasure+0.004
ursion+0.004
Of+0.004
Neg logit contributions
es-0.006
 rats-0.005
ts-0.005
 stains-0.005
adoes-0.005
Token lonely
Token ID21757
Feature activation-6.31e-02

Pos logit contributions
ursion+0.044
 bet+0.042
anna+0.042
Of+0.039
 pleasure+0.038
Neg logit contributions
es-0.057
 rats-0.053
ts-0.052
 stains-0.051
 marks-0.051
Token.
Token ID13
Feature activation-1.96e-03

Pos logit contributions
es+0.077
ts+0.072
 rats+0.072
 stains+0.070
 marks+0.069
Neg logit contributions
ursion-0.110
 bet-0.107
anna-0.107
 Sure-0.102
Of-0.101
Token
Token ID198
Feature activation-7.56e-03

Pos logit contributions
es+0.002
 not+0.002
 rats+0.002
 mice+0.002
 stains+0.002
Neg logit contributions
ursion-0.004
 sur-0.004
 bet-0.004
anna-0.004
ounded-0.004
Token
Token ID198
Feature activation-5.71e-03

Pos logit contributions
es+0.010
 not+0.008
 rats+0.008
 marks+0.008
ts+0.008
Neg logit contributions
ursion-0.014
 bet-0.013
anna-0.013
 sur-0.013
 pleasure-0.013
TokenThe
Token ID464
Feature activation+5.18e-03

Pos logit contributions
es+0.010
 rats+0.009
ts+0.009
 stains+0.009
 marks+0.009
Neg logit contributions
ursion-0.007
 bet-0.007
anna-0.007
Of-0.007
 Sure-0.007
Token little
Token ID1310
Feature activation+9.13e-02

Pos logit contributions
ursion+0.009
 bet+0.008
anna+0.008
 Sure+0.008
Of+0.008
Neg logit contributions
es-0.007
 rats-0.007
 stains-0.007
 marks-0.007
ts-0.007
Token girl
Token ID2576
Feature activation+5.32e-02

Pos logit contributions
ursion+0.123
anna+0.121
 Sure+0.113
 bet+0.112
ounded+0.108
Neg logit contributions
 rats-0.153
 mice-0.149
 marks-0.144
 stains-0.144
es-0.143
Token was
Token ID373
Feature activation+4.63e-03

Pos logit contributions
ursion+0.101
 pleasure+0.092
Of+0.091
 bet+0.091
 Sure+0.088
Neg logit contributions
es-0.070
 rats-0.060
 not-0.060
 marks-0.059
 mice-0.058
Token about
Token ID546
Feature activation-5.77e-02

Pos logit contributions
anna+0.007
ursion+0.007
 bet+0.007
 pleasure+0.007
Of+0.007
Neg logit contributions
es-0.007
 rats-0.006
ts-0.006
 stains-0.006
 marks-0.006
Token to
Token ID284
Feature activation-2.31e-02

Pos logit contributions
es+0.100
ts+0.090
 stains+0.087
 rats+0.087
bes+0.086
Neg logit contributions
 bet-0.075
ursion-0.074
anna-0.072
 Sure-0.072
Of-0.072
Token shady
Token ID36135
Feature activation-1.18e-02

Pos logit contributions
ursion+0.052
anna+0.050
 bet+0.049
 Sure+0.049
Of+0.048
Neg logit contributions
es-0.022
 rats-0.021
 stains-0.021
 not-0.020
 mice-0.020
Token rock
Token ID3881
Feature activation+2.70e-02

Pos logit contributions
es+0.016
 rats+0.015
 stains+0.015
ts+0.015
 marks+0.014
Neg logit contributions
ursion-0.020
anna-0.019
 bet-0.019
 Sure-0.018
 sur-0.018
Token and
Token ID290
Feature activation-4.05e-03

Pos logit contributions
ursion+0.055
 bet+0.053
anna+0.053
Of+0.051
 pleasure+0.051
Neg logit contributions
es-0.028
 rats-0.024
 stains-0.023
ts-0.023
 marks-0.023
Token watched
Token ID7342
Feature activation+2.75e-02

Pos logit contributions
es+0.006
 rats+0.005
ts+0.005
 not+0.005
 stains+0.005
Neg logit contributions
ursion-0.007
anna-0.006
 bet-0.006
 pleasure-0.006
Of-0.006
Token the
Token ID262
Feature activation+1.23e-02

Pos logit contributions
anna+0.050
ursion+0.050
 bet+0.050
 Sure+0.048
Of+0.048
Neg logit contributions
es-0.032
 rats-0.029
 stains-0.028
ts-0.028
 marks-0.027
Token fish
Token ID5916
Feature activation+3.49e-03

Pos logit contributions
 bet+0.019
ursion+0.018
 sur+0.018
Of+0.018
 pleasure+0.017
Neg logit contributions
es-0.020
adoes-0.017
ts-0.017
isk-0.017
 stains-0.016
Token swim
Token ID9422
Feature activation+1.11e-02

Pos logit contributions
ursion+0.005
 bet+0.005
anna+0.005
 Sure+0.005
Of+0.005
Neg logit contributions
es-0.005
 rats-0.005
 stains-0.005
ts-0.005
adoes-0.005
Token in
Token ID287
Feature activation+2.14e-02

Pos logit contributions
ursion+0.017
 bet+0.017
anna+0.016
 Sure+0.016
Of+0.016
Neg logit contributions
es-0.017
 rats-0.016
ts-0.015
 stains-0.015
 marks-0.015
Token the
Token ID262
Feature activation-3.43e-03

Pos logit contributions
ursion+0.043
 bet+0.043
 pleasure+0.041
anna+0.041
 Sure+0.041
Neg logit contributions
es-0.022
 rats-0.019
ts-0.019
 stains-0.018
 marks-0.017
Token water
Token ID1660
Feature activation+1.98e-02

Pos logit contributions
 marks+0.003
 stains+0.003
 rats+0.003
 mice+0.003
 blood+0.003
Neg logit contributions
ursion-0.007
anna-0.007
 Sure-0.006
 bet-0.006
Of-0.006
Token below
Token ID2174
Feature activation+6.01e-02

Pos logit contributions
ursion+0.040
 bet+0.038
anna+0.038
 Sure+0.037
Of+0.037
Neg logit contributions
es-0.021
 rats-0.019
ts-0.018
 stains-0.018
 marks-0.017
Token was
Token ID373
Feature activation-1.42e-02

Pos logit contributions
 rats+0.054
es+0.053
 sandwiches+0.051
ings+0.050
ts+0.050
Neg logit contributions
ursion-0.058
 bet-0.058
anna-0.054
Of-0.053
 sur-0.053
Token fun
Token ID1257
Feature activation-4.56e-03

Pos logit contributions
es+0.019
 rats+0.017
ts+0.017
 stains+0.017
 marks+0.016
Neg logit contributions
ursion-0.024
 bet-0.024
anna-0.023
 pleasure-0.023
Of-0.022
Token to
Token ID284
Feature activation-3.31e-02

Pos logit contributions
es+0.005
 rats+0.005
ts+0.005
 stains+0.005
 marks+0.005
Neg logit contributions
ursion-0.009
 bet-0.008
anna-0.008
 Sure-0.008
Of-0.008
Token learn
Token ID2193
Feature activation-6.62e-02

Pos logit contributions
es+0.046
 not+0.043
ts+0.043
 marks+0.042
 rats+0.042
Neg logit contributions
ursion-0.055
anna-0.052
 bet-0.051
 Sure-0.050
Of-0.050
Token.
Token ID13
Feature activation-4.93e-03

Pos logit contributions
es+0.075
 rats+0.068
ts+0.066
 stains+0.065
 marks+0.063
Neg logit contributions
ursion-0.125
 bet-0.122
anna-0.121
Of-0.116
 Sure-0.116
Token<|endoftext|>
Token ID50256
Feature activation-1.05e-01

Pos logit contributions
es+0.006
 mice+0.005
 not+0.005
 rats+0.004
isk+0.004
Neg logit contributions
ursion-0.009
ounded-0.009
 sur-0.009
anna-0.009
 bet-0.009
TokenOnce
Token ID7454
Feature activation-2.58e-02

Pos logit contributions
es+0.151
 rats+0.142
ts+0.138
 stains+0.137
 marks+0.135
Neg logit contributions
ursion-0.168
 bet-0.161
anna-0.159
 Sure-0.152
Of-0.151
Token upon
Token ID2402
Feature activation-6.29e-02

Pos logit contributions
es+0.033
 rats+0.030
ts+0.029
 not+0.029
 stains+0.029
Neg logit contributions
ursion-0.046
 bet-0.044
anna-0.044
Of-0.042
 Sure-0.041
Token a
Token ID257
Feature activation+1.48e-02

Pos logit contributions
es+0.073
adoes+0.068
 stains+0.065
 rats+0.064
isk+0.064
Neg logit contributions
 bet-0.112
ursion-0.109
 Sure-0.106
Of-0.106
anna-0.105
Token time
Token ID640
Feature activation+5.55e-02

Pos logit contributions
ursion+0.026
 bet+0.024
anna+0.024
 sur+0.023
Of+0.023
Neg logit contributions
es-0.019
 rats-0.018
 not-0.018
ts-0.017
 stains-0.017
Token there
Token ID612
Feature activation+3.24e-02

Pos logit contributions
ursion+0.091
 bet+0.088
anna+0.086
 Sure+0.084
Of+0.082
Neg logit contributions
es-0.077
 rats-0.072
ts-0.071
 stains-0.071
 marks-0.069
Token,
Token ID11
Feature activation-3.44e-02

Pos logit contributions
es+0.070
ts+0.069
 rats+0.068
adoes+0.065
isk+0.064
Neg logit contributions
ursion-0.100
anna-0.097
 bet-0.096
 Sure-0.093
 sur-0.092
Token a
Token ID257
Feature activation-2.18e-03

Pos logit contributions
es+0.034
ts+0.028
 rats+0.028
isk+0.028
adoes+0.027
Neg logit contributions
 bet-0.067
 Sure-0.065
ursion-0.065
anna-0.065
Of-0.065
Token page
Token ID2443
Feature activation-2.73e-02

Pos logit contributions
es+0.003
 rats+0.002
 stains+0.002
ts+0.002
 marks+0.002
Neg logit contributions
ursion-0.004
 bet-0.004
anna-0.004
Of-0.004
 Sure-0.004
Token with
Token ID351
Feature activation-2.11e-02

Pos logit contributions
es+0.035
ts+0.034
 rats+0.033
adoes+0.032
 stains+0.032
Neg logit contributions
ursion-0.045
anna-0.043
 bet-0.043
 Sure-0.041
 sur-0.040
Token a
Token ID257
Feature activation-5.19e-03

Pos logit contributions
es+0.023
isk+0.022
adoes+0.020
bes+0.020
ts+0.020
Neg logit contributions
 bet-0.038
 pleasure-0.037
ursion-0.036
anna-0.036
 Sure-0.036
Token pizza
Token ID14256
Feature activation-8.99e-02

Pos logit contributions
es+0.006
 rats+0.006
 stains+0.006
 marks+0.006
ts+0.006
Neg logit contributions
ursion-0.010
 bet-0.009
anna-0.009
Of-0.009
 Sure-0.009
Token,
Token ID11
Feature activation-3.35e-02

Pos logit contributions
es+0.106
ts+0.105
adoes+0.102
 rats+0.100
isk+0.099
Neg logit contributions
ursion-0.150
 bet-0.146
anna-0.144
 sur-0.141
 Sure-0.140
Token and
Token ID290
Feature activation-8.29e-03

Pos logit contributions
es+0.034
isk+0.031
ts+0.030
 rats+0.030
adoes+0.030
Neg logit contributions
 bet-0.061
 Sure-0.060
anna-0.059
 pleasure-0.059
Of-0.058
Token a
Token ID257
Feature activation+4.43e-04

Pos logit contributions
es+0.007
 rats+0.006
ts+0.005
 stains+0.005
 marks+0.005
Neg logit contributions
ursion-0.018
 bet-0.018
anna-0.018
Of-0.017
 Sure-0.017
Token page
Token ID2443
Feature activation-2.50e-02

Pos logit contributions
ursion+0.001
 bet+0.001
anna+0.001
Of+0.001
 Sure+0.001
Neg logit contributions
es-0.001
 rats-0.000
 stains-0.000
ts-0.000
 marks-0.000
Token with
Token ID351
Feature activation-2.06e-02

Pos logit contributions
es+0.028
ts+0.028
 rats+0.027
adoes+0.026
isk+0.026
Neg logit contributions
ursion-0.044
anna-0.043
 bet-0.042
 Sure-0.040
 sur-0.040
Token sorry
Token ID7926
Feature activation-6.19e-02

Pos logit contributions
es+0.065
 rats+0.060
isk+0.059
 stains+0.058
ts+0.058
Neg logit contributions
 bet-0.061
ursion-0.060
 pleasure-0.057
Of-0.056
 sur-0.056
Token.
Token ID13
Feature activation-1.80e-02

Pos logit contributions
es+0.077
ts+0.075
 rats+0.074
 stains+0.070
bes+0.070
Neg logit contributions
 bet-0.104
ursion-0.103
anna-0.100
 Sure-0.100
Of-0.100
Token They
Token ID1119
Feature activation-2.42e-02

Pos logit contributions
es+0.020
 mice+0.017
 rats+0.016
 not+0.016
 stains+0.016
Neg logit contributions
ursion-0.037
anna-0.037
ya-0.034
ounded-0.034
 bet-0.034
Token had
Token ID550
Feature activation-1.79e-02

Pos logit contributions
es+0.038
 rats+0.035
ts+0.035
 stains+0.035
 not+0.034
Neg logit contributions
ursion-0.037
anna-0.035
 bet-0.034
 Sure-0.033
 pleasure-0.032
Token been
Token ID587
Feature activation-2.49e-02

Pos logit contributions
es+0.028
iders+0.025
bes+0.024
adoes+0.024
ings+0.023
Neg logit contributions
 bet-0.028
ursion-0.027
 pleasure-0.026
Of-0.026
 sur-0.025
Token mean
Token ID1612
Feature activation-7.28e-02

Pos logit contributions
es+0.029
 rats+0.026
ts+0.025
 stains+0.024
 not+0.024
Neg logit contributions
ursion-0.049
 bet-0.047
anna-0.047
 Sure-0.046
Of-0.045
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
es+0.098
 rats+0.090
ts+0.089
 stains+0.087
 marks+0.085
Neg logit contributions
ursion-0.123
 bet-0.119
anna-0.118
 Sure-0.112
Of-0.112
Token greedy
Token ID31828
Feature activation-8.13e-02

Pos logit contributions
es+0.013
 rats+0.012
ts+0.012
 stains+0.012
 not+0.011
Neg logit contributions
ursion-0.022
anna-0.021
 bet-0.021
 Sure-0.020
 pleasure-0.020
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
es+0.089
 rats+0.081
ts+0.080
 stains+0.078
 marks+0.076
Neg logit contributions
ursion-0.155
 bet-0.152
anna-0.150
Of-0.143
 Sure-0.143
Token
Token ID198
Feature activation-2.28e-02

Pos logit contributions
es+0.017
 mice+0.015
 not+0.015
 rats+0.014
 stains+0.014
Neg logit contributions
ursion-0.033
anna-0.033
ounded-0.030
ya-0.030
 sur-0.030
Token
Token ID198
Feature activation-2.05e-02

Pos logit contributions
es+0.036
 rats+0.034
ts+0.033
 stains+0.033
 marks+0.032
Neg logit contributions
ursion-0.034
 bet-0.032
anna-0.032
 Sure-0.030
Of-0.030
Token,
Token ID11
Feature activation-2.94e-02

Pos logit contributions
es+0.013
 rats+0.011
 stains+0.011
ts+0.010
 marks+0.010
Neg logit contributions
ursion-0.026
 bet-0.025
anna-0.025
 Sure-0.024
Of-0.024
Token so
Token ID523
Feature activation+4.29e-02

Pos logit contributions
es+0.050
 not+0.047
 rats+0.047
 stains+0.046
 marks+0.045
Neg logit contributions
ursion-0.041
anna-0.038
 bet-0.037
 Sure-0.035
 sur-0.034
Token she
Token ID673
Feature activation+3.66e-04

Pos logit contributions
ursion+0.074
anna+0.070
 bet+0.070
 pleasure+0.066
 sur+0.065
Neg logit contributions
es-0.058
 not-0.055
 rats-0.055
 marks-0.053
 stains-0.052
Token set
Token ID900
Feature activation+5.29e-02

Pos logit contributions
ursion+0.001
 pleasure+0.001
 bet+0.001
 Sure+0.001
anna+0.001
Neg logit contributions
es-0.001
 not-0.001
ts-0.001
 rats-0.000
 marks-0.000
Token off
Token ID572
Feature activation+4.33e-02

Pos logit contributions
ursion+0.080
 bet+0.077
anna+0.076
 Sure+0.073
 sur+0.071
Neg logit contributions
es-0.080
 rats-0.077
 stains-0.073
ts-0.072
 mice-0.071
Token for
Token ID329
Feature activation-7.85e-02

Pos logit contributions
ursion+0.079
 bet+0.076
anna+0.076
 Sure+0.073
Of+0.072
Neg logit contributions
es-0.052
 rats-0.049
ts-0.047
 stains-0.046
 marks-0.045
Token a
Token ID257
Feature activation+1.55e-02

Pos logit contributions
es+0.067
 rats+0.057
 stains+0.054
ts+0.053
 marks+0.052
Neg logit contributions
ursion-0.173
 bet-0.169
anna-0.167
 Sure-0.161
Of-0.161
Token walk
Token ID2513
Feature activation+3.75e-02

Pos logit contributions
ursion+0.032
anna+0.030
 Shall+0.029
 bet+0.029
eal+0.028
Neg logit contributions
 not-0.015
 puzzles-0.015
 sandwiches-0.014
 cookies-0.014
 rats-0.013
Token.
Token ID13
Feature activation-7.93e-03

Pos logit contributions
ursion+0.088
 bet+0.086
anna+0.086
 pleasure+0.086
Of+0.084
Neg logit contributions
es-0.028
 not-0.019
ts-0.019
 marks-0.019
 rats-0.019
Token She
Token ID1375
Feature activation-1.80e-02

Pos logit contributions
es+0.008
 marks+0.007
 not+0.007
 pictures+0.007
 stains+0.007
Neg logit contributions
ursion-0.016
anna-0.015
 sur-0.015
ya-0.014
mber-0.014
Token passed
Token ID3804
Feature activation-6.36e-03

Pos logit contributions
es+0.024
ts+0.022
 not+0.021
 rats+0.021
 marks+0.020
Neg logit contributions
ursion-0.032
 pleasure-0.031
Of-0.029
anna-0.029
 bet-0.029
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
es+0.059
ts+0.055
 rats+0.054
 stains+0.051
 mice+0.050
Neg logit contributions
ursion-0.091
 bet-0.090
anna-0.088
 Sure-0.086
Of-0.086
Token He
Token ID679
Feature activation-2.30e-02

Pos logit contributions
es+0.012
 not+0.012
 rats+0.011
 mice+0.011
 blood+0.011
Neg logit contributions
ursion-0.021
anna-0.021
 bet-0.019
ounded-0.019
ya-0.019
Token wished
Token ID16555
Feature activation+2.37e-02

Pos logit contributions
es+0.039
 rats+0.036
ts+0.035
 stains+0.035
 marks+0.035
Neg logit contributions
ursion-0.032
 bet-0.030
anna-0.030
Of-0.028
 Sure-0.028
Token he
Token ID339
Feature activation+9.06e-04

Pos logit contributions
ursion+0.029
 Sure+0.028
 bet+0.028
anna+0.028
Of+0.028
Neg logit contributions
es-0.041
 rats-0.038
 stains-0.038
ts-0.037
 marks-0.037
Token was
Token ID373
Feature activation+2.66e-04

Pos logit contributions
Of+0.001
anna+0.001
ursion+0.001
 bet+0.001
 sur+0.001
Neg logit contributions
ings-0.002
es-0.002
 marks-0.002
adoes-0.002
 slices-0.002
Token not
Token ID407
Feature activation-6.98e-02

Pos logit contributions
ursion+0.000
anna+0.000
 bet+0.000
 pleasure+0.000
Of+0.000
Neg logit contributions
es-0.000
 stains-0.000
 rats-0.000
ings-0.000
bes-0.000
Token rude
Token ID22066
Feature activation-5.61e-02

Pos logit contributions
es+0.079
 rats+0.071
ts+0.069
 stains+0.068
 marks+0.067
Neg logit contributions
ursion-0.135
 bet-0.130
anna-0.130
Of-0.124
 Sure-0.124
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
es+0.064
ts+0.059
 rats+0.058
 stains+0.056
 marks+0.054
Neg logit contributions
ursion-0.104
 bet-0.102
anna-0.102
Of-0.096
 sur-0.096
Token mean
Token ID1612
Feature activation-6.06e-02

Pos logit contributions
es+0.013
 rats+0.012
ts+0.011
 stains+0.011
 marks+0.011
Neg logit contributions
ursion-0.022
 bet-0.021
anna-0.021
Of-0.020
 Sure-0.020
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
es+0.067
 rats+0.060
ts+0.060
 stains+0.058
 marks+0.056
Neg logit contributions
ursion-0.116
 bet-0.113
anna-0.112
Of-0.107
 Sure-0.107
Token He
Token ID679
Feature activation-2.53e-02

Pos logit contributions
es+0.018
 not+0.017
 rats+0.016
 marks+0.015
 bones+0.015
Neg logit contributions
ursion-0.029
anna-0.028
ya-0.026
ounded-0.026
 bet-0.026