TOP ACTIVATIONS
MAX = 12.480

belonged to your great - grand mother . She gave it
belong to their great - grand pa . He was an
chest was your great - grand ma 's . She left
That 's your great - grand ma ," her mom replied
parents and their great - grand pa 's picture . They
helpful . She took a bisc uit from her pocket and
cl ink their cups and say " che ers ".
belonged to his great - grand father , and he used
imagine what her great - grand ma was like . She
She imagined her great - grand ma wearing the same dress
water into the cups and say " che ers " to
was going on a special saf ari . He got to
, what does that sign say ?" she asked . "
frown s . Their moms say , " Hello . We
special place in Santa 's sle igh . <|endoftext|> Once upon
share and be kind . Say sorry to Tom and Lily
a voice inside the sack say , " Who 's there
, not your hands . Say sorry to each other and
Ben shake their heads and say , " No , thank
olded Tom and made him say sorry . She gave Lily

MIN ACTIVATIONS
MIN = -8.265

His mom went over to the net and tried
S ara felt a gust of wind . She saw
I have to start all over . â Lily quickly
. Tom rushed over and opened the buckle .
head low . He went over to his owner , who
John ran over to the rock and started
. He jumped around with gust o and spun in circles
the park . They went over to a tree with a
The two friends ran over to the wealthy game and
." Jack went over to the tap and pulled
They both went over and tried to decide which
Tim my went over to the kids and tried
John decided to go over to the child and ask
in time . They went over a big hill and down
cry . Mom my went over and told the other girl
! He went over to the frog , but
Emily happily ran over start playing with everyone else
. Tom went over and carefully looked around until
Suddenly , he felt a gust of wind ! He was
the angel felt a great gust of wind and her wings

INTERVAL 7.293 - 12.480
CONTAINS 0.518%

Mar ina 's mom said , " Oh , it
rice . The shop keeper said he was too young and
. But he did not say anything . He ate his
song was over , Bobby said , " Mom my ,
Danny was surprised and said

INTERVAL 2.107 - 7.293
CONTAINS 10.699%

she decided to take a nap . She found a cozy
Soon she realized that she would have to suffer
continued their walk around the harbor . <|endoftext|> Once upon a
searching for his favourite snack when he suddenly came across a
the mirror . She thought she looked very cool .

INTERVAL -3.079 - 2.107
CONTAINS 82.937%

His friends laughed and cl apped , they all thought it
boy was so happy that he forgot to be careful .
Tom my was a big boy who liked to play with
your daddy 's birthday !" M andy felt much
Daisy . Daisy lived in a very colorful room . One

INTERVAL -8.265 - -3.079
CONTAINS 5.847%

into trouble . He went outside to play and saw a
hug . Then she got back on her seat and continued
?" Her dad replied , " I 'm printing a recipe
Suddenly , a strange dizz y feeling came over her
She learned how to be less shy . She had the
Token belonged
Token ID19611
Feature activation+2.65e+00

Pos logit contributions
 different+0.015
 fast+0.014
 slow+0.013
 very+0.013
 really+0.013
Neg logit contributions
lor-0.026
ocket-0.024
urger-0.023
oll-0.021
card-0.021
Token to
Token ID284
Feature activation+6.88e-01

Pos logit contributions
lor+0.165
ocket+0.154
urger+0.149
oll+0.142
card+0.141
Neg logit contributions
 different-0.029
 fast-0.028
 slow-0.023
 very-0.021
 really-0.019
Token your
Token ID534
Feature activation+1.83e+00

Pos logit contributions
lor+0.035
ocket+0.032
urger+0.030
oll+0.029
card+0.028
Neg logit contributions
 fast-0.013
 different-0.013
 slow-0.012
 late-0.012
 very-0.011
Token great
Token ID1049
Feature activation-1.49e+00

Pos logit contributions
lor+0.082
ocket+0.072
urger+0.069
card+0.065
oll+0.065
Neg logit contributions
 different-0.056
 fast-0.055
 very-0.051
 slow-0.051
 really-0.048
Token-
Token ID12
Feature activation-3.56e+00

Pos logit contributions
 different+0.039
 fast+0.038
 slow+0.035
 very+0.034
 really+0.032
Neg logit contributions
lor-0.075
ocket-0.066
urger-0.062
card-0.060
oll-0.059
Tokengrand
Token ID23936
Feature activation+1.03e+01

Pos logit contributions
 fast+0.144
 different+0.144
 very+0.134
 slow+0.133
 really+0.131
Neg logit contributions
lor-0.117
ocket-0.102
urger-0.099
oll-0.088
anger-0.084
Tokenmother
Token ID13552
Feature activation+2.23e+00

Pos logit contributions
lor+0.367
ocket+0.323
urger+0.316
anger+0.312
isc+0.299
Neg logit contributions
 different-0.362
 very-0.334
 fast-0.324
 the-0.321
 slow-0.317
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
lor+0.135
ocket+0.125
urger+0.122
oll+0.115
card+0.114
Neg logit contributions
 different-0.029
 fast-0.028
 very-0.023
 slow-0.023
 really-0.021
Token She
Token ID1375
Feature activation+1.66e+00

Pos logit contributions
lor+0.034
ocket+0.031
urger+0.030
card+0.028
ster+0.028
Neg logit contributions
 different-0.014
 fast-0.013
 slow-0.012
 very-0.012
 late-0.012
Token gave
Token ID2921
Feature activation+3.42e+00

Pos logit contributions
lor+0.086
ocket+0.077
urger+0.076
anger+0.071
card+0.070
Neg logit contributions
 different-0.038
 fast-0.037
 very-0.035
 really-0.035
 slow-0.034
Token it
Token ID340
Feature activation-2.24e-01

Pos logit contributions
lor+0.194
ocket+0.180
urger+0.173
oll+0.164
card+0.163
Neg logit contributions
 different-0.057
 fast-0.056
 slow-0.049
 very-0.047
 really-0.044
Token belong
Token ID5594
Feature activation+1.22e+00

Pos logit contributions
lor+0.100
urger+0.089
oll+0.086
ocket+0.085
ogo+0.082
Neg logit contributions
 different-0.035
 fast-0.033
 very-0.032
 to-0.028
 slow-0.028
Token to
Token ID284
Feature activation-6.03e-02

Pos logit contributions
lor+0.077
ocket+0.071
urger+0.070
oll+0.066
anger+0.065
Neg logit contributions
 different-0.014
 fast-0.014
 very-0.011
 slow-0.011
 really-0.009
Token their
Token ID511
Feature activation+1.87e+00

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 very+0.001
 really+0.001
Neg logit contributions
lor-0.003
ocket-0.003
urger-0.003
oll-0.003
card-0.003
Token great
Token ID1049
Feature activation-2.36e+00

Pos logit contributions
lor+0.086
ocket+0.075
urger+0.071
oll+0.068
anger+0.066
Neg logit contributions
 different-0.057
 fast-0.056
 very-0.052
 slow-0.051
 really-0.048
Token-
Token ID12
Feature activation-4.34e+00

Pos logit contributions
 different+0.064
 fast+0.060
 very+0.055
 fun+0.055
 slow+0.054
Neg logit contributions
lor-0.122
ocket-0.099
urger-0.098
ogo-0.096
oll-0.096
Tokengrand
Token ID23936
Feature activation+1.03e+01

Pos logit contributions
 fast+0.178
 different+0.176
 very+0.165
 late+0.160
 slow+0.160
Neg logit contributions
lor-0.141
ocket-0.121
urger-0.118
oll-0.108
anger-0.102
Tokenpa
Token ID8957
Feature activation+2.38e+00

Pos logit contributions
lor+0.384
ocket+0.348
urger+0.337
anger+0.325
oll+0.321
Neg logit contributions
 different-0.336
 very-0.307
 fast-0.296
 the-0.294
 really-0.285
Token.
Token ID13
Feature activation+7.27e-01

Pos logit contributions
lor+0.156
ocket+0.143
urger+0.139
anger+0.135
oll+0.134
Neg logit contributions
 different-0.023
 fast-0.021
 very-0.018
 slow-0.016
 really-0.015
Token He
Token ID679
Feature activation+1.60e+00

Pos logit contributions
lor+0.044
ocket+0.041
urger+0.039
oll+0.037
card+0.037
Neg logit contributions
 different-0.009
 fast-0.009
 slow-0.008
 very-0.007
 really-0.007
Token was
Token ID373
Feature activation-1.41e-01

Pos logit contributions
lor+0.085
urger+0.074
ocket+0.072
anger+0.070
immer+0.068
Neg logit contributions
 different-0.042
 very-0.039
 really-0.039
 fast-0.038
 slow-0.035
Token an
Token ID281
Feature activation+9.28e-01

Pos logit contributions
 different+0.002
 fast+0.002
 slow+0.001
 very+0.001
 really+0.001
Neg logit contributions
lor-0.009
ocket-0.008
urger-0.008
oll-0.007
card-0.007
Token chest
Token ID7721
Feature activation+1.95e+00

Pos logit contributions
lor+0.052
ocket+0.050
urger+0.047
oll+0.045
card+0.044
Neg logit contributions
 different-0.020
 fast-0.019
 very-0.018
 slow-0.017
 really-0.017
Token was
Token ID373
Feature activation+6.33e-01

Pos logit contributions
lor+0.103
ocket+0.093
urger+0.090
oll+0.085
card+0.083
Neg logit contributions
 different-0.044
 fast-0.044
 very-0.042
 slow-0.039
 really-0.039
Token your
Token ID534
Feature activation+1.34e+00

Pos logit contributions
lor+0.040
ocket+0.036
urger+0.035
anger+0.034
oll+0.033
Neg logit contributions
 different-0.009
 fast-0.009
 very-0.008
 slow-0.007
 really-0.007
Token great
Token ID1049
Feature activation-2.13e+00

Pos logit contributions
lor+0.058
ocket+0.046
urger+0.046
oll+0.044
bridge+0.044
Neg logit contributions
 different-0.048
 fast-0.046
 very-0.045
 fun-0.042
 slow-0.041
Token-
Token ID12
Feature activation-4.15e+00

Pos logit contributions
 different+0.055
 fast+0.052
 fun+0.049
 very+0.048
 slow+0.046
Neg logit contributions
lor-0.109
ocket-0.097
urger-0.089
icking-0.087
oll-0.086
Tokengrand
Token ID23936
Feature activation+1.01e+01

Pos logit contributions
 fast+0.165
 different+0.160
 very+0.152
 slow+0.147
 really+0.147
Neg logit contributions
lor-0.139
ocket-0.117
urger-0.117
oll-0.105
icking-0.103
Tokenma
Token ID2611
Feature activation-6.44e-01

Pos logit contributions
lor+0.379
ocket+0.345
anger+0.330
urger+0.327
isc+0.316
Neg logit contributions
 different-0.285
 the-0.270
 very-0.263
 her-0.262
 care-0.252
Token's
Token ID338
Feature activation+2.05e+00

Pos logit contributions
 different+0.009
 fast+0.009
 very+0.009
 slow+0.008
 really+0.008
Neg logit contributions
lor-0.038
ocket-0.035
urger-0.034
anger-0.033
oll-0.032
Token.
Token ID13
Feature activation+4.02e-01

Pos logit contributions
lor+0.095
ocket+0.078
oll+0.078
urger+0.077
icking+0.076
Neg logit contributions
 different-0.064
 very-0.061
 fast-0.061
 fun-0.056
 really-0.054
Token She
Token ID1375
Feature activation+1.54e+00

Pos logit contributions
lor+0.022
ocket+0.021
urger+0.021
ogo+0.019
icking+0.019
Neg logit contributions
 fast-0.006
 She-0.006
 They-0.006
 different-0.006
 late-0.006
Token left
Token ID1364
Feature activation-6.64e-01

Pos logit contributions
lor+0.086
ocket+0.076
urger+0.075
anger+0.073
uit+0.071
Neg logit contributions
 different-0.029
 very-0.028
 really-0.028
 fast-0.027
 slow-0.025
TokenThat
Token ID2504
Feature activation+7.77e-01

Pos logit contributions
 different+0.052
 fast+0.051
 slow+0.045
 very+0.043
 really+0.040
Neg logit contributions
lor-0.168
ocket-0.153
urger-0.144
card-0.142
oll-0.139
Token's
Token ID338
Feature activation+1.81e+00

Pos logit contributions
lor+0.040
ocket+0.038
urger+0.036
oll+0.035
card+0.033
Neg logit contributions
 different-0.017
 fast-0.016
 slow-0.015
 very-0.015
 really-0.014
Token your
Token ID534
Feature activation+1.82e+00

Pos logit contributions
lor+0.106
ocket+0.099
urger+0.095
oll+0.090
card+0.090
Neg logit contributions
 different-0.027
 fast-0.027
 slow-0.023
 very-0.022
 really-0.020
Token great
Token ID1049
Feature activation-2.08e+00

Pos logit contributions
lor+0.089
ocket+0.078
urger+0.075
oll+0.073
bridge+0.071
Neg logit contributions
 different-0.057
 fast-0.051
 very-0.050
 slow-0.048
 really-0.046
Token-
Token ID12
Feature activation-3.99e+00

Pos logit contributions
 different+0.051
 fast+0.047
 very+0.045
 slow+0.043
 really+0.042
Neg logit contributions
lor-0.107
ocket-0.099
urger-0.091
oll-0.090
ster-0.085
Tokengrand
Token ID23936
Feature activation+9.90e+00

Pos logit contributions
 different+0.173
 fast+0.173
 very+0.162
 slow+0.160
 really+0.158
Neg logit contributions
lor-0.121
ocket-0.104
urger-0.099
oll-0.087
ster-0.082
Tokenma
Token ID2611
Feature activation-7.24e-01

Pos logit contributions
lor+0.387
urger+0.347
ocket+0.346
anger+0.326
oll+0.317
Neg logit contributions
 different-0.301
 very-0.275
 the-0.268
 really-0.262
 her-0.261
Token,"
Token ID553
Feature activation-2.17e+00

Pos logit contributions
 different+0.012
 fast+0.011
 very+0.010
 slow+0.010
 really+0.009
Neg logit contributions
lor-0.042
ocket-0.039
urger-0.037
anger-0.036
oll-0.036
Token her
Token ID607
Feature activation+5.16e-01

Pos logit contributions
 different+0.025
 fast+0.023
 slow+0.019
 very+0.018
 really+0.016
Neg logit contributions
lor-0.138
ocket-0.128
urger-0.124
oll-0.118
anger-0.116
Token mom
Token ID1995
Feature activation-2.41e+00

Pos logit contributions
lor+0.022
ocket+0.020
urger+0.019
oll+0.017
card+0.017
Neg logit contributions
 different-0.017
 fast-0.016
 slow-0.015
 very-0.015
 really-0.015
Token replied
Token ID8712
Feature activation+4.63e+00

Pos logit contributions
 different+0.071
 fast+0.068
 very+0.065
 slow+0.064
 really+0.063
Neg logit contributions
lor-0.110
ocket-0.100
urger-0.094
anger-0.088
oll-0.086
Token parents
Token ID3397
Feature activation-3.53e-01

Pos logit contributions
lor+0.052
oll+0.042
ocket+0.042
urger+0.040
immer+0.040
Neg logit contributions
 different-0.037
 fast-0.036
 very-0.034
 slow-0.032
 fun-0.031
Token and
Token ID290
Feature activation+8.30e-01

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 very+0.004
 really+0.003
Neg logit contributions
lor-0.021
ocket-0.020
urger-0.019
oll-0.018
card-0.018
Token their
Token ID511
Feature activation+1.49e+00

Pos logit contributions
lor+0.041
ocket+0.036
urger+0.035
anger+0.033
oll+0.033
Neg logit contributions
 different-0.023
 fast-0.023
 slow-0.021
 very-0.021
 really-0.019
Token great
Token ID1049
Feature activation-2.36e+00

Pos logit contributions
lor+0.068
ocket+0.055
urger+0.053
oll+0.052
anger+0.050
Neg logit contributions
 different-0.051
 fast-0.049
 very-0.046
 slow-0.045
 fun-0.043
Token-
Token ID12
Feature activation-4.62e+00

Pos logit contributions
 different+0.069
 fast+0.061
 fun+0.061
 to+0.058
 very+0.058
Neg logit contributions
lor-0.118
ocket-0.094
ancing-0.092
oll-0.092
uit-0.091
Tokengrand
Token ID23936
Feature activation+9.90e+00

Pos logit contributions
 different+0.191
 fast+0.191
 very+0.179
 slow+0.175
 late+0.173
Neg logit contributions
lor-0.149
ocket-0.128
urger-0.120
oll-0.111
anger-0.107
Tokenpa
Token ID8957
Feature activation+1.93e+00

Pos logit contributions
lor+0.335
ocket+0.301
urger+0.278
oll+0.268
anger+0.264
Neg logit contributions
 different-0.383
 fast-0.352
 very-0.352
 slow-0.338
 really-0.333
Token's
Token ID338
Feature activation+2.16e+00

Pos logit contributions
lor+0.131
ocket+0.119
urger+0.116
anger+0.114
oll+0.111
Neg logit contributions
 different-0.014
 fast-0.014
 very-0.012
 slow-0.008
 really-0.008
Token picture
Token ID4286
Feature activation+3.72e+00

Pos logit contributions
lor+0.107
oll+0.089
ogo+0.087
anger+0.085
urger+0.084
Neg logit contributions
 different-0.067
 very-0.064
 fast-0.063
 fun-0.061
 happy-0.058
Token.
Token ID13
Feature activation+4.44e-01

Pos logit contributions
lor+0.241
ocket+0.223
urger+0.216
oll+0.203
card+0.202
Neg logit contributions
 fast-0.038
 different-0.038
 very-0.031
 slow-0.028
 really-0.024
Token They
Token ID1119
Feature activation-1.16e-01

Pos logit contributions
lor+0.026
ocket+0.024
urger+0.023
oll+0.022
card+0.022
Neg logit contributions
 different-0.006
 fast-0.006
 slow-0.005
 very-0.005
 really-0.004
Token helpful
Token ID7613
Feature activation+4.24e-02

Pos logit contributions
lor+0.202
ocket+0.186
urger+0.179
oll+0.168
card+0.167
Neg logit contributions
 different-0.083
 fast-0.082
 slow-0.074
 very-0.071
 really-0.068
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
lor+0.002
ocket+0.002
urger+0.002
oll+0.002
card+0.002
Neg logit contributions
 different-0.001
 fast-0.001
 slow-0.001
 very-0.001
 really-0.001
Token She
Token ID1375
Feature activation+2.21e+00

Pos logit contributions
lor+0.094
ocket+0.088
urger+0.085
oll+0.080
card+0.080
Neg logit contributions
 different-0.024
 fast-0.023
 slow-0.020
 very-0.019
 really-0.017
Token took
Token ID1718
Feature activation+2.31e+00

Pos logit contributions
lor+0.116
ocket+0.108
urger+0.104
card+0.097
oll+0.097
Neg logit contributions
 different-0.047
 fast-0.045
 slow-0.041
 very-0.041
 really-0.039
Token a
Token ID257
Feature activation+1.25e+00

Pos logit contributions
lor+0.138
ocket+0.128
urger+0.124
oll+0.117
card+0.117
Neg logit contributions
 different-0.033
 fast-0.032
 slow-0.027
 very-0.025
 really-0.023
Token bisc
Token ID36228
Feature activation+9.90e+00

Pos logit contributions
lor+0.066
ocket+0.062
urger+0.059
card+0.056
oll+0.056
Neg logit contributions
 different-0.024
 fast-0.023
 slow-0.021
 very-0.020
 really-0.019
Tokenuit
Token ID5013
Feature activation+3.78e+00

Pos logit contributions
lor+0.208
ocket+0.204
 Majesty+0.188
urger+0.167
 passports+0.146
Neg logit contributions
 to-0.427
 very-0.426
B-0.423
 fast-0.418
-0.418
Token from
Token ID422
Feature activation+3.29e+00

Pos logit contributions
lor+0.244
ocket+0.229
urger+0.216
oll+0.212
 Majesty+0.211
Neg logit contributions
 fast-0.039
 very-0.034
 to-0.031
 different-0.030
 slow-0.028
Token her
Token ID607
Feature activation+2.31e+00

Pos logit contributions
lor+0.190
ocket+0.183
urger+0.173
card+0.165
oll+0.165
Neg logit contributions
 different-0.042
 fast-0.040
 slow-0.035
 very-0.032
 really-0.030
Token pocket
Token ID10000
Feature activation+1.43e+00

Pos logit contributions
lor+0.098
ocket+0.087
urger+0.082
oll+0.078
card+0.076
Neg logit contributions
 different-0.074
 fast-0.073
 very-0.070
 slow-0.069
 really-0.066
Token and
Token ID290
Feature activation+1.86e+00

Pos logit contributions
lor+0.088
ocket+0.084
urger+0.082
oll+0.077
card+0.075
Neg logit contributions
 different-0.017
 fast-0.017
 very-0.013
 slow-0.013
 really-0.011
Token cl
Token ID537
Feature activation+1.40e+00

Pos logit contributions
 different+0.012
 fast+0.011
 slow+0.011
Stop+0.011
 competitive+0.011
Neg logit contributions
lor-0.029
urger-0.027
ocket-0.027
ster-0.026
oll-0.026
Tokenink
Token ID676
Feature activation+5.97e+00

Pos logit contributions
lor+0.052
ocket+0.047
urger+0.044
oll+0.040
card+0.040
Neg logit contributions
 different-0.051
 fast-0.050
 slow-0.047
 very-0.046
 really-0.045
Token their
Token ID511
Feature activation+4.40e+00

Pos logit contributions
lor+0.267
ocket+0.248
urger+0.234
oll+0.217
card+0.214
Neg logit contributions
 fast-0.172
 different-0.172
 slow-0.159
 very-0.158
 really-0.149
Token cups
Token ID14180
Feature activation+5.00e+00

Pos logit contributions
lor+0.198
ocket+0.174
urger+0.163
oll+0.159
anger+0.152
Neg logit contributions
 different-0.137
 fast-0.134
 slow-0.124
 very-0.124
 really-0.117
Token and
Token ID290
Feature activation+3.08e+00

Pos logit contributions
lor+0.317
ocket+0.297
urger+0.286
card+0.269
oll+0.269
Neg logit contributions
 fast-0.052
 different-0.052
 very-0.044
 slow-0.041
 really-0.036
Token say
Token ID910
Feature activation+9.87e+00

Pos logit contributions
lor+0.162
ocket+0.144
urger+0.136
anger+0.131
oll+0.130
Neg logit contributions
 different-0.075
 fast-0.074
 slow-0.067
 very-0.067
 really-0.062
Token "
Token ID366
Feature activation-1.89e+00

Pos logit contributions
lor+0.545
ocket+0.511
urger+0.489
card+0.463
oll+0.462
Neg logit contributions
 different-0.187
 fast-0.183
 very-0.163
 slow-0.161
 really-0.149
Tokenche
Token ID2395
Feature activation+6.74e+00

Pos logit contributions
 different+0.039
 fast+0.038
 slow+0.034
 very+0.033
 really+0.032
Neg logit contributions
lor-0.099
ocket-0.092
urger-0.088
oll-0.083
card-0.082
Tokeners
Token ID364
Feature activation+3.70e-01

Pos logit contributions
lor+0.272
ocket+0.268
isc+0.234
oll+0.232
anger+0.230
Neg logit contributions
 fast-0.187
 slow-0.183
 different-0.182
 very-0.182
 really-0.172
Token".
Token ID1911
Feature activation-1.20e+00

Pos logit contributions
lor+0.019
ocket+0.018
urger+0.017
oll+0.017
card+0.016
Neg logit contributions
 different-0.007
 fast-0.007
 very-0.007
 slow-0.007
 really-0.007
Token
Token ID198
Feature activation-5.86e-02

Pos logit contributions
 different+0.016
 fast+0.016
 slow+0.014
 very+0.013
 late+0.012
Neg logit contributions
lor-0.071
ocket-0.068
urger-0.065
oll-0.062
card-0.061
Token belonged
Token ID19611
Feature activation+1.47e+00

Pos logit contributions
 different+0.015
 fast+0.015
 slow+0.013
 very+0.012
 really+0.012
Neg logit contributions
lor-0.041
ocket-0.038
urger-0.036
oll-0.034
card-0.034
Token to
Token ID284
Feature activation+1.00e-02

Pos logit contributions
lor+0.095
ocket+0.089
urger+0.086
oll+0.082
card+0.082
Neg logit contributions
 different-0.013
 fast-0.012
 slow-0.009
 very-0.008
 really-0.007
Token his
Token ID465
Feature activation+2.28e+00

Pos logit contributions
lor+0.001
ocket+0.001
urger+0.000
oll+0.000
card+0.000
Neg logit contributions
 different-0.000
 fast-0.000
 slow-0.000
 very-0.000
 really-0.000
Token great
Token ID1049
Feature activation-2.39e+00

Pos logit contributions
lor+0.100
ocket+0.091
urger+0.086
oll+0.080
card+0.080
Neg logit contributions
 different-0.067
 fast-0.066
 slow-0.062
 very-0.060
 really-0.058
Token-
Token ID12
Feature activation-4.52e+00

Pos logit contributions
 different+0.074
 fast+0.072
 slow+0.067
 very+0.066
 really+0.064
Neg logit contributions
lor-0.104
ocket-0.094
urger-0.089
card-0.082
oll-0.082
Tokengrand
Token ID23936
Feature activation+9.87e+00

Pos logit contributions
 different+0.141
 fast+0.140
 slow+0.129
 very+0.127
 really+0.124
Neg logit contributions
lor-0.191
ocket-0.173
urger-0.165
oll-0.152
card-0.149
Tokenfather
Token ID11358
Feature activation+2.12e+00

Pos logit contributions
lor+0.347
ocket+0.314
urger+0.296
anger+0.294
oll+0.279
Neg logit contributions
 different-0.349
 very-0.317
 really-0.311
 fast-0.302
 the-0.300
Token,
Token ID11
Feature activation-9.55e-01

Pos logit contributions
lor+0.132
ocket+0.122
urger+0.118
anger+0.114
oll+0.112
Neg logit contributions
 different-0.027
 fast-0.024
 very-0.023
 really-0.020
 slow-0.019
Token and
Token ID290
Feature activation+8.03e-01

Pos logit contributions
 different+0.018
 fast+0.017
 very+0.015
 slow+0.015
 really+0.014
Neg logit contributions
lor-0.054
ocket-0.050
urger-0.048
anger-0.045
card-0.045
Token he
Token ID339
Feature activation+5.34e-01

Pos logit contributions
lor+0.045
ocket+0.041
urger+0.039
anger+0.038
oll+0.037
Neg logit contributions
 different-0.017
 fast-0.016
 very-0.015
 really-0.014
 slow-0.014
Token used
Token ID973
Feature activation+6.67e-02

Pos logit contributions
lor+0.029
ocket+0.027
urger+0.026
anger+0.025
oll+0.025
Neg logit contributions
 different-0.010
 fast-0.010
 very-0.009
 slow-0.009
 really-0.009
Token imagine
Token ID5967
Feature activation+3.53e+00

Pos logit contributions
 fast+0.023
 different+0.022
 late+0.022
 slow+0.021
 very+0.021
Neg logit contributions
lor-0.033
ocket-0.031
urger-0.030
card-0.028
ster-0.026
Token what
Token ID644
Feature activation+1.05e+00

Pos logit contributions
lor+0.199
ocket+0.183
urger+0.181
oll+0.168
ster+0.165
Neg logit contributions
 different-0.070
 fast-0.066
 very-0.060
 slow-0.056
 really-0.053
Token her
Token ID607
Feature activation+2.47e+00

Pos logit contributions
lor+0.052
ocket+0.049
urger+0.045
card+0.045
oll+0.044
Neg logit contributions
 fast-0.021
 different-0.019
 slow-0.019
 late-0.018
 very-0.016
Token great
Token ID1049
Feature activation-2.69e+00

Pos logit contributions
lor+0.123
ocket+0.105
urger+0.102
oll+0.095
bridge+0.093
Neg logit contributions
 different-0.072
 fast-0.069
 very-0.066
 slow-0.063
 really-0.060
Token-
Token ID12
Feature activation-4.28e+00

Pos logit contributions
 different+0.067
 fast+0.060
 very+0.057
 slow+0.055
 really+0.055
Neg logit contributions
lor-0.143
ocket-0.129
urger-0.122
oll-0.119
ogo-0.113
Tokengrand
Token ID23936
Feature activation+9.84e+00

Pos logit contributions
 different+0.175
 fast+0.174
 very+0.163
 slow+0.162
 really+0.159
Neg logit contributions
lor-0.140
ocket-0.123
urger-0.118
oll-0.105
ster-0.100
Tokenma
Token ID2611
Feature activation-6.57e-01

Pos logit contributions
lor+0.342
urger+0.308
ocket+0.303
oll+0.279
anger+0.277
Neg logit contributions
 different-0.348
 very-0.316
 the-0.306
 her-0.306
 really-0.303
Token was
Token ID373
Feature activation+7.98e-02

Pos logit contributions
 different+0.011
 fast+0.010
 very+0.010
 really+0.010
 slow+0.009
Neg logit contributions
lor-0.039
ocket-0.034
urger-0.034
anger-0.032
oll-0.032
Token like
Token ID588
Feature activation+5.97e-02

Pos logit contributions
lor+0.004
ocket+0.004
urger+0.004
oll+0.004
anger+0.004
Neg logit contributions
 different-0.002
 fast-0.002
 very-0.001
 slow-0.001
 really-0.001
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
lor+0.004
ocket+0.003
urger+0.003
oll+0.003
ster+0.003
Neg logit contributions
 different-0.001
 fast-0.001
 very-0.001
 slow-0.001
 really-0.001
Token She
Token ID1375
Feature activation+8.15e-01

Pos logit contributions
 different+0.007
 fast+0.006
 slow+0.005
 very+0.005
 really+0.005
Neg logit contributions
lor-0.028
ocket-0.026
urger-0.025
oll-0.024
card-0.023
Token She
Token ID1375
Feature activation+9.42e-01

Pos logit contributions
 different+0.007
 fast+0.007
 slow+0.006
 very+0.005
 really+0.005
Neg logit contributions
lor-0.029
ocket-0.027
urger-0.026
oll-0.025
card-0.025
Token imagined
Token ID15758
Feature activation+4.49e+00

Pos logit contributions
lor+0.049
ocket+0.044
urger+0.043
card+0.040
anger+0.040
Neg logit contributions
 different-0.022
 fast-0.021
 very-0.019
 slow-0.019
 really-0.019
Token her
Token ID607
Feature activation+2.61e+00

Pos logit contributions
lor+0.248
urger+0.230
ocket+0.227
oll+0.209
anger+0.205
Neg logit contributions
 different-0.096
 fast-0.094
 very-0.086
 slow-0.076
 really-0.076
Token great
Token ID1049
Feature activation-1.79e+00

Pos logit contributions
lor+0.146
ocket+0.124
urger+0.123
oll+0.117
bridge+0.112
Neg logit contributions
 different-0.070
 fast-0.065
 very-0.064
 slow-0.059
 fun-0.056
Token-
Token ID12
Feature activation-3.82e+00

Pos logit contributions
 different+0.055
 fast+0.051
 very+0.050
 slow+0.047
 really+0.047
Neg logit contributions
lor-0.086
ocket-0.077
urger-0.071
oll-0.069
cher-0.067
Tokengrand
Token ID23936
Feature activation+9.81e+00

Pos logit contributions
 fast+0.131
 different+0.130
 very+0.120
 slow+0.120
 really+0.117
Neg logit contributions
lor-0.149
ocket-0.134
urger-0.131
oll-0.119
ster-0.115
Tokenma
Token ID2611
Feature activation-5.52e-01

Pos logit contributions
lor+0.341
ocket+0.309
urger+0.304
oll+0.275
anger+0.268
Neg logit contributions
 different-0.354
 very-0.322
 fast-0.316
 really-0.313
 fun-0.307
Token wearing
Token ID5762
Feature activation+1.01e+00

Pos logit contributions
 different+0.009
 fast+0.009
 very+0.009
 really+0.008
 slow+0.008
Neg logit contributions
lor-0.032
ocket-0.029
urger-0.029
anger-0.027
oll-0.027
Token the
Token ID262
Feature activation+1.01e+00

Pos logit contributions
lor+0.064
ocket+0.059
urger+0.058
oll+0.055
card+0.054
Neg logit contributions
 different-0.012
 fast-0.011
 slow-0.009
 very-0.009
 really-0.008
Token same
Token ID976
Feature activation-5.37e-01

Pos logit contributions
lor+0.055
urger+0.051
ocket+0.049
oll+0.047
icking+0.045
Neg logit contributions
 different-0.026
 fast-0.023
 very-0.021
 slow-0.021
 really-0.019
Token dress
Token ID6576
Feature activation+3.05e+00

Pos logit contributions
 different+0.020
 fast+0.019
 very+0.018
 slow+0.018
 really+0.017
Neg logit contributions
lor-0.021
ocket-0.019
urger-0.018
oll-0.017
icking-0.016
Token water
Token ID1660
Feature activation+4.71e+00

Pos logit contributions
ocket+0.043
lor+0.041
urger+0.039
card+0.039
ster+0.037
Neg logit contributions
 different-0.027
B-0.027
 fast-0.027
Da-0.026
 late-0.026
Token into
Token ID656
Feature activation-1.25e+00

Pos logit contributions
lor+0.256
ocket+0.238
urger+0.229
card+0.216
oll+0.216
Neg logit contributions
 different-0.083
 fast-0.081
 slow-0.072
 very-0.067
 really-0.064
Token the
Token ID262
Feature activation+9.93e-01

Pos logit contributions
 fast+0.015
 different+0.014
 slow+0.014
 very+0.013
 really+0.013
Neg logit contributions
lor-0.067
ocket-0.063
urger-0.059
bridge-0.056
anger-0.056
Token cups
Token ID14180
Feature activation+3.42e+00

Pos logit contributions
lor+0.042
ocket+0.039
urger+0.037
card+0.034
oll+0.034
Neg logit contributions
 different-0.029
 fast-0.029
 slow-0.027
 very-0.026
 really-0.025
Token and
Token ID290
Feature activation+2.77e+00

Pos logit contributions
lor+0.210
ocket+0.199
urger+0.191
oll+0.181
card+0.180
Neg logit contributions
 different-0.040
 fast-0.039
 very-0.033
 slow-0.032
 really-0.029
Token say
Token ID910
Feature activation+9.70e+00

Pos logit contributions
lor+0.144
ocket+0.129
urger+0.122
anger+0.115
oll+0.115
Neg logit contributions
 different-0.068
 fast-0.067
 slow-0.062
 very-0.060
 really-0.057
Token "
Token ID366
Feature activation-2.00e+00

Pos logit contributions
lor+0.525
ocket+0.489
urger+0.467
card+0.442
oll+0.440
Neg logit contributions
 different-0.194
 fast-0.189
 slow-0.168
 very-0.168
 really-0.156
Tokenche
Token ID2395
Feature activation+6.59e+00

Pos logit contributions
 different+0.040
 fast+0.039
 slow+0.035
 very+0.034
 really+0.032
Neg logit contributions
lor-0.107
ocket-0.099
urger-0.094
card-0.089
oll-0.089
Tokeners
Token ID364
Feature activation+2.44e-01

Pos logit contributions
lor+0.258
ocket+0.250
isc+0.214
anger+0.212
oll+0.208
Neg logit contributions
 fast-0.193
 slow-0.191
 different-0.191
 very-0.189
 really-0.183
Token"
Token ID1
Feature activation-8.67e-01

Pos logit contributions
lor+0.013
ocket+0.012
urger+0.011
oll+0.011
card+0.011
Neg logit contributions
 different-0.005
 fast-0.005
 very-0.004
 slow-0.004
 really-0.004
Token to
Token ID284
Feature activation+5.52e-01

Pos logit contributions
 different+0.017
 fast+0.017
 slow+0.015
 very+0.015
 really+0.014
Neg logit contributions
lor-0.046
ocket-0.042
urger-0.041
oll-0.038
card-0.038
Token was
Token ID373
Feature activation+1.46e+00

Pos logit contributions
lor+0.205
ocket+0.189
urger+0.182
card+0.172
oll+0.172
Neg logit contributions
 different-0.072
 fast-0.071
 slow-0.063
 very-0.062
 really-0.059
Token going
Token ID1016
Feature activation+1.84e+00

Pos logit contributions
lor+0.074
ocket+0.068
urger+0.065
oll+0.060
anger+0.060
Neg logit contributions
 different-0.035
 fast-0.035
 very-0.032
 slow-0.032
 really-0.030
Token on
Token ID319
Feature activation-1.40e+00

Pos logit contributions
lor+0.126
ocket+0.120
urger+0.115
oll+0.111
ster+0.108
Neg logit contributions
 fast-0.013
 different-0.013
 very-0.010
 slow-0.009
 really-0.008
Token a
Token ID257
Feature activation+9.91e-01

Pos logit contributions
 fast+0.023
 different+0.023
 slow+0.021
 very+0.018
B+0.018
Neg logit contributions
lor-0.076
ocket-0.068
urger-0.066
oll-0.062
card-0.061
Token special
Token ID2041
Feature activation+7.28e-01

Pos logit contributions
lor+0.041
ocket+0.037
urger+0.035
card+0.032
oll+0.032
Neg logit contributions
 different-0.029
 fast-0.029
 slow-0.027
 late-0.027
 very-0.026
Token saf
Token ID1932
Feature activation+9.57e+00

Pos logit contributions
lor+0.028
ocket+0.026
urger+0.024
oll+0.023
card+0.022
Neg logit contributions
 different-0.026
 fast-0.025
 slow-0.024
 very-0.024
 really-0.023
Tokenari
Token ID2743
Feature activation+5.37e+00

Pos logit contributions
ocket+0.192
lor+0.189
urger+0.176
oll+0.133
card+0.126
Neg logit contributions
 fast-0.491
 different-0.469
 very-0.458
 slow-0.454
 really-0.451
Token.
Token ID13
Feature activation+3.00e-01

Pos logit contributions
lor+0.329
ocket+0.317
urger+0.306
oll+0.294
anger+0.282
Neg logit contributions
 different-0.067
 fast-0.066
 very-0.056
 really-0.049
 slow-0.049
Token He
Token ID679
Feature activation+1.74e+00

Pos logit contributions
lor+0.018
ocket+0.017
urger+0.016
card+0.015
ster+0.015
Neg logit contributions
 different-0.004
 fast-0.004
 slow-0.003
 really-0.003
 very-0.003
Token got
Token ID1392
Feature activation-1.86e+00

Pos logit contributions
lor+0.096
ocket+0.089
urger+0.085
card+0.081
oll+0.081
Neg logit contributions
 different-0.034
 fast-0.033
 slow-0.029
 very-0.029
 really-0.029
Token to
Token ID284
Feature activation-3.03e-01

Pos logit contributions
 different+0.030
 fast+0.029
 very+0.026
 slow+0.025
 really+0.024
Neg logit contributions
lor-0.114
ocket-0.104
urger-0.100
oll-0.094
anger-0.094
Token,
Token ID11
Feature activation+2.16e+00

Pos logit contributions
 different+0.014
 fast+0.014
 slow+0.013
 very+0.012
 really+0.011
Neg logit contributions
lor-0.041
ocket-0.038
urger-0.037
oll-0.035
card-0.034
Token what
Token ID644
Feature activation+3.59e+00

Pos logit contributions
lor+0.118
ocket+0.109
urger+0.104
oll+0.099
card+0.098
Neg logit contributions
 different-0.042
 fast-0.042
 slow-0.037
 very-0.036
 really-0.034
Token does
Token ID857
Feature activation+2.73e+00

Pos logit contributions
lor+0.164
ocket+0.153
urger+0.144
oll+0.137
card+0.132
Neg logit contributions
 fast-0.092
 different-0.089
 slow-0.084
 late-0.078
 very-0.078
Token that
Token ID326
Feature activation+2.99e+00

Pos logit contributions
lor+0.142
ocket+0.133
urger+0.127
oll+0.121
card+0.119
Neg logit contributions
 different-0.062
 fast-0.060
 slow-0.054
 very-0.053
 really-0.050
Token sign
Token ID1051
Feature activation+2.59e+00

Pos logit contributions
lor+0.136
ocket+0.125
urger+0.119
oll+0.111
card+0.110
Neg logit contributions
 different-0.082
 fast-0.081
 slow-0.075
 very-0.073
 really-0.071
Token say
Token ID910
Feature activation+9.55e+00

Pos logit contributions
lor+0.122
ocket+0.112
urger+0.107
oll+0.100
card+0.099
Neg logit contributions
 different-0.067
 fast-0.066
 slow-0.060
 very-0.059
 really-0.057
Token?"
Token ID1701
Feature activation-1.39e+00

Pos logit contributions
lor+0.529
ocket+0.491
urger+0.478
oll+0.451
card+0.443
Neg logit contributions
 different-0.177
 fast-0.174
 very-0.157
 slow-0.152
 really-0.143
Token she
Token ID673
Feature activation-8.96e-02

Pos logit contributions
 different+0.026
 fast+0.025
 slow+0.022
 very+0.021
 really+0.020
Neg logit contributions
lor-0.072
ocket-0.067
urger-0.063
oll-0.060
ster-0.060
Token asked
Token ID1965
Feature activation+3.14e+00

Pos logit contributions
 different+0.002
 fast+0.002
 slow+0.002
 very+0.002
 really+0.002
Neg logit contributions
lor-0.004
ocket-0.004
urger-0.004
oll-0.004
card-0.004
Token.
Token ID13
Feature activation+1.00e+00

Pos logit contributions
lor+0.175
ocket+0.166
urger+0.159
oll+0.151
card+0.149
Neg logit contributions
 different-0.050
 fast-0.049
 slow-0.042
 late-0.039
 very-0.037
Token "
Token ID366
Feature activation-3.52e+00

Pos logit contributions
lor+0.055
ocket+0.050
urger+0.048
oll+0.046
anger+0.046
Neg logit contributions
 different-0.016
 fast-0.015
 slow-0.013
 very-0.013
 really-0.012
Token frown
Token ID22002
Feature activation+2.23e+00

Pos logit contributions
lor+0.168
ocket+0.160
urger+0.159
card+0.152
ster+0.144
Neg logit contributions
 fast-0.041
 late-0.039
 different-0.036
 slow-0.036
Stop-0.035
Tokens
Token ID82
Feature activation+4.93e+00

Pos logit contributions
lor+0.097
ocket+0.091
urger+0.088
oll+0.085
ster+0.082
Neg logit contributions
 fast-0.056
 different-0.055
 slow-0.052
 busy-0.047
 late-0.046
Token.
Token ID13
Feature activation+2.29e+00

Pos logit contributions
lor+0.209
ocket+0.188
urger+0.177
oll+0.165
card+0.165
Neg logit contributions
 different-0.155
 fast-0.152
 slow-0.143
 very-0.142
 really-0.137
Token Their
Token ID5334
Feature activation+4.94e+00

Pos logit contributions
lor+0.130
ocket+0.121
urger+0.115
oll+0.110
card+0.109
Neg logit contributions
 different-0.037
 fast-0.036
 slow-0.031
 very-0.029
 really-0.028
Token moms
Token ID34015
Feature activation+6.81e-01

Pos logit contributions
lor+0.203
ocket+0.179
urger+0.167
oll+0.156
card+0.155
Neg logit contributions
 different-0.167
 fast-0.164
 slow-0.154
 very-0.153
 really-0.147
Token say
Token ID910
Feature activation+9.46e+00

Pos logit contributions
lor+0.033
ocket+0.031
urger+0.029
oll+0.027
card+0.027
Neg logit contributions
 different-0.017
 fast-0.017
 slow-0.015
 very-0.015
 really-0.014
Token,
Token ID11
Feature activation+1.07e+00

Pos logit contributions
lor+0.519
ocket+0.482
urger+0.462
oll+0.435
card+0.434
Neg logit contributions
 different-0.190
 fast-0.185
 slow-0.165
 very-0.165
 really-0.152
Token "
Token ID366
Feature activation-2.45e+00

Pos logit contributions
lor+0.056
ocket+0.052
urger+0.049
oll+0.047
card+0.046
Neg logit contributions
 different-0.022
 fast-0.022
 slow-0.020
 very-0.019
 really-0.018
TokenHello
Token ID15496
Feature activation+2.77e+00

Pos logit contributions
 different+0.053
 fast+0.051
 very+0.049
 slow+0.046
 really+0.044
Neg logit contributions
lor-0.124
ocket-0.106
urger-0.101
card-0.100
ster-0.099
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
lor+0.159
ocket+0.148
urger+0.142
oll+0.135
card+0.134
Neg logit contributions
 different-0.045
 fast-0.044
 slow-0.038
 very-0.036
 really-0.034
Token We
Token ID775
Feature activation-1.13e+00

Pos logit contributions
lor+0.056
ocket+0.052
urger+0.050
oll+0.046
card+0.046
Neg logit contributions
 different-0.031
 fast-0.031
 slow-0.028
 very-0.027
 really-0.027
Token special
Token ID2041
Feature activation+2.91e+00

Pos logit contributions
lor+0.167
ocket+0.154
urger+0.147
oll+0.139
card+0.138
Neg logit contributions
 different-0.068
 fast-0.067
 slow-0.060
 very-0.058
 really-0.055
Token place
Token ID1295
Feature activation+3.05e+00

Pos logit contributions
lor+0.125
ocket+0.112
urger+0.107
oll+0.104
ogo+0.096
Neg logit contributions
 different-0.093
 fast-0.090
 very-0.085
 slow-0.083
 really-0.081
Token in
Token ID287
Feature activation-2.65e+00

Pos logit contributions
lor+0.179
ocket+0.167
urger+0.161
oll+0.154
card+0.151
Neg logit contributions
 different-0.046
 fast-0.045
 slow-0.038
 very-0.037
 really-0.034
Token Santa
Token ID8909
Feature activation+3.49e+00

Pos logit contributions
 different+0.027
 fast+0.025
 slow+0.020
 very+0.018
 really+0.016
Neg logit contributions
lor-0.168
ocket-0.158
urger-0.153
oll-0.146
card-0.145
Token's
Token ID338
Feature activation+3.05e+00

Pos logit contributions
lor+0.201
ocket+0.189
oll+0.179
urger+0.177
anger+0.174
Neg logit contributions
 different-0.056
 fast-0.056
 very-0.052
 slow-0.050
 really-0.047
Token sle
Token ID3133
Feature activation+9.43e+00

Pos logit contributions
lor+0.138
ocket+0.126
urger+0.119
oll+0.117
anger+0.113
Neg logit contributions
 different-0.092
 fast-0.088
 very-0.087
 slow-0.082
 quiet-0.078
Tokenigh
Token ID394
Feature activation+4.71e+00

Pos logit contributions
lor+0.216
ocket+0.171
urger+0.163
card+0.155
anger+0.154
Neg logit contributions
 fast-0.410
 very-0.398
 different-0.396
 to-0.381
 slow-0.380
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
lor+0.279
ocket+0.264
urger+0.252
oll+0.242
card+0.239
Neg logit contributions
 fast-0.064
 different-0.064
 slow-0.053
 very-0.053
 really-0.047
Token<|endoftext|>
Token ID50256
Feature activation+4.91e+00

Pos logit contributions
lor+0.061
ocket+0.060
urger+0.057
card+0.054
ster+0.053
Neg logit contributions
 different-0.014
 fast-0.014
 slow-0.012
 late-0.012
 very-0.011
TokenOnce
Token ID7454
Feature activation+4.95e+00

Pos logit contributions
lor+0.275
ocket+0.250
urger+0.235
oll+0.227
anger+0.224
Neg logit contributions
 different-0.084
 fast-0.081
 slow-0.073
 very-0.068
 really-0.063
Token upon
Token ID2402
Feature activation+2.91e+00

Pos logit contributions
lor+0.210
ocket+0.192
urger+0.181
oll+0.169
card+0.167
Neg logit contributions
 different-0.147
 fast-0.146
 slow-0.137
 very-0.132
 really-0.129
Token share
Token ID2648
Feature activation-1.83e+00

Pos logit contributions
lor+0.140
ocket+0.129
urger+0.123
oll+0.115
card+0.115
Neg logit contributions
 different-0.070
 fast-0.069
 slow-0.063
 very-0.062
 really-0.059
Token and
Token ID290
Feature activation+8.21e-01

Pos logit contributions
 fast+0.034
 late+0.034
Da+0.033
B+0.033
 slow+0.031
Neg logit contributions
lor-0.079
ocket-0.077
urger-0.074
card-0.069
ster-0.068
Token be
Token ID307
Feature activation-1.72e+00

Pos logit contributions
lor+0.034
ocket+0.032
urger+0.031
card+0.030
ster+0.028
Neg logit contributions
 fast-0.020
 different-0.019
 late-0.018
 slow-0.018
 very-0.017
Token kind
Token ID1611
Feature activation-2.05e+00

Pos logit contributions
 heavily+0.038
 wildly+0.033
 different+0.033
 panic+0.032
Da+0.032
Neg logit contributions
card-0.066
lor-0.065
urger-0.062
ocket-0.062
ster-0.058
Token.
Token ID13
Feature activation+8.91e-01

Pos logit contributions
 different+0.039
 fast+0.036
 slow+0.033
 really+0.030
 very+0.030
Neg logit contributions
lor-0.107
ocket-0.100
urger-0.097
card-0.091
ster-0.090
Token Say
Token ID13816
Feature activation+9.42e+00

Pos logit contributions
lor+0.039
ocket+0.035
urger+0.033
oll+0.031
card+0.031
Neg logit contributions
 different-0.026
 fast-0.026
 slow-0.024
 very-0.023
 really-0.023
Token sorry
Token ID7926
Feature activation-7.22e-01

Pos logit contributions
lor+0.416
ocket+0.376
urger+0.353
oll+0.329
card+0.326
Neg logit contributions
 different-0.288
 fast-0.287
 slow-0.268
 very-0.262
 really-0.250
Token to
Token ID284
Feature activation+7.39e-01

Pos logit contributions
 different+0.012
 fast+0.012
 slow+0.010
 very+0.009
 busy+0.009
Neg logit contributions
lor-0.038
ocket-0.035
urger-0.035
ster-0.033
oll-0.033
Token Tom
Token ID4186
Feature activation-6.42e-02

Pos logit contributions
lor+0.037
ocket+0.037
urger+0.036
card+0.033
ster+0.033
Neg logit contributions
 fast-0.009
 different-0.009
 late-0.009
B-0.008
 very-0.008
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 very+0.001
 really+0.001
Neg logit contributions
lor-0.004
ocket-0.003
urger-0.003
oll-0.003
card-0.003
Token Lily
Token ID20037
Feature activation-7.15e-01

Pos logit contributions
lor+0.090
ocket+0.089
urger+0.085
oll+0.080
card+0.080
Neg logit contributions
 different-0.029
 fast-0.029
 very-0.025
 slow-0.025
 really-0.025
Token a
Token ID257
Feature activation-2.54e-01

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 very+0.001
 really+0.001
Neg logit contributions
lor-0.003
ocket-0.003
urger-0.003
oll-0.003
card-0.003
Token voice
Token ID3809
Feature activation+2.27e-01

Pos logit contributions
 different+0.006
 fast+0.006
 late+0.006
 slow+0.005
 each+0.005
Neg logit contributions
lor-0.011
ocket-0.010
urger-0.010
ster-0.009
card-0.009
Token inside
Token ID2641
Feature activation-1.42e+00

Pos logit contributions
lor+0.012
ocket+0.011
urger+0.011
oll+0.010
anger+0.010
Neg logit contributions
 different-0.005
 fast-0.005
 very-0.005
 slow-0.005
 really-0.004
Token the
Token ID262
Feature activation+6.81e-01

Pos logit contributions
 different+0.016
 fast+0.016
 slow+0.013
 very+0.012
 late+0.011
Neg logit contributions
lor-0.086
ocket-0.081
urger-0.077
card-0.074
oll-0.073
Token sack
Token ID23704
Feature activation+2.67e+00

Pos logit contributions
lor+0.023
ocket+0.021
urger+0.019
card+0.017
oll+0.017
Neg logit contributions
 different-0.027
 fast-0.026
 slow-0.025
 very-0.024
 really-0.024
Token say
Token ID910
Feature activation+9.42e+00

Pos logit contributions
lor+0.170
urger+0.169
ocket+0.162
oll+0.156
 Majesty+0.154
Neg logit contributions
 different-0.027
 fast-0.024
 very-0.023
 slow-0.018
 really-0.018
Token,
Token ID11
Feature activation+8.45e-02

Pos logit contributions
lor+0.518
ocket+0.486
urger+0.472
oll+0.443
card+0.433
Neg logit contributions
 different-0.172
 fast-0.169
 very-0.153
 slow-0.148
 really-0.138
Token "
Token ID366
Feature activation-3.75e+00

Pos logit contributions
lor+0.004
ocket+0.004
urger+0.004
card+0.004
oll+0.003
Neg logit contributions
 different-0.002
 fast-0.002
 slow-0.002
 very-0.002
 late-0.002
TokenWho
Token ID8241
Feature activation+3.95e+00

Pos logit contributions
 different+0.066
 fast+0.065
 slow+0.057
 very+0.056
 really+0.051
Neg logit contributions
lor-0.210
ocket-0.193
urger-0.185
card-0.176
oll-0.174
Token's
Token ID338
Feature activation+2.96e+00

Pos logit contributions
lor+0.212
urger+0.194
ocket+0.193
card+0.184
anger+0.177
Neg logit contributions
 different-0.080
 fast-0.072
 really-0.068
 slow-0.067
 very-0.067
Token there
Token ID612
Feature activation+1.04e+00

Pos logit contributions
lor+0.175
urger+0.162
ocket+0.162
oll+0.149
isc+0.146
Neg logit contributions
 different-0.055
 fast-0.055
 the-0.052
 very-0.051
 slow-0.050
Token,
Token ID11
Feature activation-4.80e-01

Pos logit contributions
lor+0.102
ocket+0.096
urger+0.090
oll+0.087
card+0.086
Neg logit contributions
 different-0.035
 fast-0.033
 slow-0.030
B-0.029
 panic-0.028
Token not
Token ID407
Feature activation-8.37e-01

Pos logit contributions
 different+0.010
 fast+0.010
 slow+0.009
 very+0.009
 really+0.008
Neg logit contributions
lor-0.026
ocket-0.023
urger-0.022
oll-0.021
card-0.021
Token your
Token ID534
Feature activation+2.70e+00

Pos logit contributions
 fast+0.016
 different+0.016
 slow+0.014
 very+0.013
 late+0.013
Neg logit contributions
lor-0.042
ocket-0.040
urger-0.039
oll-0.036
card-0.036
Token hands
Token ID2832
Feature activation-4.52e-02

Pos logit contributions
lor+0.115
ocket+0.104
urger+0.096
oll+0.091
card+0.090
Neg logit contributions
 different-0.086
 fast-0.085
 slow-0.079
 very-0.078
 really-0.075
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 very+0.001
 late+0.001
Neg logit contributions
lor-0.002
ocket-0.002
urger-0.002
oll-0.002
card-0.002
Token Say
Token ID13816
Feature activation+9.40e+00

Pos logit contributions
lor+0.053
ocket+0.049
urger+0.046
card+0.043
oll+0.043
Neg logit contributions
 different-0.029
 fast-0.028
 slow-0.026
 very-0.025
 really-0.025
Token sorry
Token ID7926
Feature activation-7.16e-01

Pos logit contributions
lor+0.447
ocket+0.405
urger+0.379
oll+0.357
card+0.356
Neg logit contributions
 fast-0.261
 different-0.261
 slow-0.242
 very-0.237
 really-0.223
Token to
Token ID284
Feature activation+7.17e-01

Pos logit contributions
 different+0.010
 fast+0.010
 slow+0.008
 very+0.007
 late+0.007
Neg logit contributions
lor-0.041
ocket-0.038
urger-0.038
oll-0.035
ster-0.035
Token each
Token ID1123
Feature activation-4.03e+00

Pos logit contributions
lor+0.034
ocket+0.034
urger+0.033
card+0.030
oll+0.030
Neg logit contributions
 fast-0.011
 different-0.011
 late-0.011
 very-0.010
B-0.010
Token other
Token ID584
Feature activation-1.17e+00

Pos logit contributions
 fast+0.062
 different+0.061
 slow+0.055
 late+0.053
 very+0.049
Neg logit contributions
lor-0.216
ocket-0.203
urger-0.197
card-0.185
ster-0.183
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
 different+0.021
 fast+0.020
 slow+0.017
 very+0.016
 really+0.016
Neg logit contributions
lor-0.061
ocket-0.056
urger-0.055
card-0.052
ster-0.051
Token Ben
Token ID3932
Feature activation+3.21e+00

Pos logit contributions
lor+0.260
ocket+0.238
urger+0.228
oll+0.215
card+0.214
Neg logit contributions
 different-0.105
 fast-0.103
 slow-0.093
 very-0.090
 really-0.086
Token shake
Token ID13279
Feature activation-2.10e+00

Pos logit contributions
lor+0.167
ocket+0.154
urger+0.147
card+0.139
oll+0.138
Neg logit contributions
 different-0.069
 fast-0.068
 slow-0.062
 very-0.060
 really-0.058
Token their
Token ID511
Feature activation+3.28e+00

Pos logit contributions
 different+0.034
 fast+0.033
 late+0.031
Ste+0.030
 slow+0.030
Neg logit contributions
lor-0.100
urger-0.094
ocket-0.093
uit-0.086
ster-0.086
Token heads
Token ID6665
Feature activation-3.25e-01

Pos logit contributions
lor+0.121
ocket+0.112
urger+0.107
ster+0.096
oll+0.095
Neg logit contributions
 different-0.112
 fast-0.110
 slow-0.103
 late-0.102
 very-0.100
Token and
Token ID290
Feature activation+2.65e+00

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 late+0.004
 very+0.004
Neg logit contributions
lor-0.017
ocket-0.016
urger-0.015
oll-0.015
card-0.015
Token say
Token ID910
Feature activation+9.40e+00

Pos logit contributions
lor+0.132
ocket+0.121
urger+0.115
oll+0.108
card+0.107
Neg logit contributions
 different-0.065
 fast-0.064
 slow-0.059
 very-0.057
 really-0.054
Token,
Token ID11
Feature activation+1.25e+00

Pos logit contributions
lor+0.475
ocket+0.437
urger+0.419
oll+0.395
card+0.392
Neg logit contributions
 different-0.199
 fast-0.194
 slow-0.176
 late-0.166
 very-0.164
Token "
Token ID366
Feature activation-2.56e+00

Pos logit contributions
lor+0.065
ocket+0.060
urger+0.057
oll+0.054
card+0.054
Neg logit contributions
 different-0.026
 fast-0.026
 slow-0.023
 very-0.022
 really-0.022
TokenNo
Token ID2949
Feature activation+7.09e-01

Pos logit contributions
 different+0.055
 fast+0.054
 very+0.053
 slow+0.048
 hard+0.045
Neg logit contributions
lor-0.130
ocket-0.111
urger-0.108
bridge-0.103
oll-0.102
Token,
Token ID11
Feature activation-3.56e-01

Pos logit contributions
lor+0.037
ocket+0.033
urger+0.033
oll+0.030
anger+0.030
Neg logit contributions
 fast-0.014
 different-0.014
 slow-0.012
 late-0.012
 very-0.011
Token thank
Token ID5875
Feature activation+2.90e+00

Pos logit contributions
 different+0.008
 fast+0.008
 slow+0.007
 very+0.007
 the+0.007
Neg logit contributions
lor-0.020
ocket-0.018
urger-0.017
card-0.017
anger-0.016
Tokenolded
Token ID48959
Feature activation+3.63e+00

Pos logit contributions
lor+0.059
ocket+0.050
urger+0.048
ster+0.041
bridge+0.041
Neg logit contributions
 fast-0.071
 different-0.071
 very-0.067
 slow-0.066
 really-0.065
Token Tom
Token ID4186
Feature activation+5.00e-01

Pos logit contributions
lor+0.179
ocket+0.166
urger+0.160
oll+0.152
anger+0.148
Neg logit contributions
 different-0.079
 fast-0.077
 slow-0.070
 very-0.068
 really-0.066
Token and
Token ID290
Feature activation+1.79e+00

Pos logit contributions
lor+0.030
ocket+0.028
urger+0.027
oll+0.026
card+0.026
Neg logit contributions
 different-0.007
 fast-0.006
 slow-0.005
 very-0.005
 really-0.005
Token made
Token ID925
Feature activation+5.56e-01

Pos logit contributions
lor+0.098
ocket+0.090
urger+0.087
card+0.082
anger+0.081
Neg logit contributions
 different-0.036
 fast-0.035
 slow-0.032
 very-0.031
 really-0.029
Token him
Token ID683
Feature activation+1.41e+00

Pos logit contributions
lor+0.032
ocket+0.029
urger+0.028
card+0.026
ster+0.026
Neg logit contributions
 different-0.011
 fast-0.011
 slow-0.009
 very-0.009
 really-0.009
Token say
Token ID910
Feature activation+9.38e+00

Pos logit contributions
lor+0.075
ocket+0.070
urger+0.068
oll+0.064
card+0.064
Neg logit contributions
 different-0.025
 fast-0.025
 slow-0.022
 very-0.021
 really-0.020
Token sorry
Token ID7926
Feature activation+2.24e-02

Pos logit contributions
lor+0.413
ocket+0.377
urger+0.357
oll+0.332
card+0.330
Neg logit contributions
 different-0.276
 fast-0.273
 slow-0.254
 very-0.248
 really-0.240
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
lor+0.001
urger+0.001
ocket+0.001
oll+0.001
ster+0.001
Neg logit contributions
 fast-0.000
 different-0.000
 slow-0.000
 late-0.000
 busy-0.000
Token She
Token ID1375
Feature activation+2.13e+00

Pos logit contributions
lor+0.049
ocket+0.042
oll+0.041
anger+0.041
ster+0.040
Neg logit contributions
 different-0.028
 fast-0.024
 really-0.022
B-0.022
 fun-0.022
Token gave
Token ID2921
Feature activation+3.71e+00

Pos logit contributions
lor+0.106
ocket+0.097
urger+0.092
anger+0.085
card+0.085
Neg logit contributions
 different-0.055
 fast-0.053
 very-0.049
 slow-0.049
 really-0.047
Token Lily
Token ID20037
Feature activation+3.73e-01

Pos logit contributions
lor+0.203
ocket+0.188
urger+0.180
card+0.169
oll+0.169
Neg logit contributions
 different-0.073
 fast-0.071
 slow-0.063
 very-0.061
 really-0.058
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
 fast+0.032
 different+0.030
 slow+0.030
 very+0.028
 really+0.028
Neg logit contributions
lor-0.060
ocket-0.058
urger-0.054
oll-0.052
card-0.051
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
 different+0.013
 fast+0.012
 slow+0.010
 very+0.010
 really+0.008
Neg logit contributions
lor-0.071
ocket-0.065
urger-0.062
oll-0.060
card-0.059
TokenHis
Token ID6653
Feature activation+1.46e+00

Pos logit contributions
 different+0.026
 fast+0.025
 slow+0.022
 very+0.022
 really+0.020
Neg logit contributions
lor-0.074
ocket-0.065
urger-0.063
oll-0.061
card-0.060
Token mom
Token ID1995
Feature activation-1.76e+00

Pos logit contributions
lor+0.074
ocket+0.066
urger+0.059
bridge+0.057
card+0.057
Neg logit contributions
 fast-0.041
 different-0.040
 slow-0.038
 very-0.038
 really-0.035
Token went
Token ID1816
Feature activation-5.26e-01

Pos logit contributions
 different+0.037
 fast+0.036
 very+0.033
 slow+0.033
 really+0.033
Neg logit contributions
lor-0.096
ocket-0.090
urger-0.082
anger-0.079
card-0.078
Token over
Token ID625
Feature activation-8.27e+00

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 very+0.004
 really+0.003
Neg logit contributions
lor-0.034
ocket-0.032
urger-0.031
oll-0.029
ster-0.029
Token to
Token ID284
Feature activation-1.98e+00

Pos logit contributions
 different+0.107
 fast+0.104
 slow+0.088
 very+0.081
 really+0.075
Neg logit contributions
lor-0.490
ocket-0.458
urger-0.440
oll-0.420
card-0.416
Token the
Token ID262
Feature activation-1.72e+00

Pos logit contributions
 different+0.036
 fast+0.035
 slow+0.032
 very+0.029
 really+0.029
Neg logit contributions
lor-0.113
ocket-0.105
urger-0.101
oll-0.097
card-0.096
Token net
Token ID2010
Feature activation-5.63e-01

Pos logit contributions
 different+0.049
 fast+0.049
 slow+0.045
 very+0.044
 really+0.043
Neg logit contributions
lor-0.078
ocket-0.071
urger-0.067
oll-0.064
card-0.063
Token and
Token ID290
Feature activation+4.04e-01

Pos logit contributions
 different+0.007
 fast+0.007
 slow+0.006
 very+0.005
 really+0.005
Neg logit contributions
lor-0.034
ocket-0.032
urger-0.031
oll-0.030
card-0.029
Token tried
Token ID3088
Feature activation-6.29e-01

Pos logit contributions
lor+0.020
ocket+0.019
urger+0.018
card+0.017
oll+0.017
Neg logit contributions
 different-0.010
 fast-0.010
 slow-0.009
 very-0.009
 really-0.008
Token
Token ID198
Feature activation-7.23e-01

Pos logit contributions
 different+0.012
 fast+0.010
 slow+0.010
 competitive+0.010
 very+0.009
Neg logit contributions
lor-0.035
ocket-0.031
oll-0.030
urger-0.029
ogo-0.029
TokenS
Token ID50
Feature activation-4.92e-01

Pos logit contributions
 different+0.016
 fast+0.014
 slow+0.013
 very+0.013
 really+0.013
Neg logit contributions
lor-0.037
ocket-0.032
urger-0.031
oll-0.031
ster-0.030
Tokenara
Token ID3301
Feature activation-3.10e+00

Pos logit contributions
 different+0.015
 fast+0.015
 slow+0.014
 very+0.013
 late+0.013
Neg logit contributions
lor-0.021
ocket-0.020
urger-0.018
card-0.017
oll-0.016
Token felt
Token ID2936
Feature activation-1.53e+00

Pos logit contributions
 different+0.067
 fast+0.065
 slow+0.058
 late+0.056
 very+0.055
Neg logit contributions
lor-0.157
ocket-0.146
urger-0.139
oll-0.132
ster-0.130
Token a
Token ID257
Feature activation-6.41e-01

Pos logit contributions
 different+0.026
B+0.024
Lu+0.024
 fast+0.024
Stop+0.022
Neg logit contributions
ocket-0.072
lor-0.070
oll-0.065
urger-0.062
ster-0.060
Token gust
Token ID35253
Feature activation-8.08e+00

Pos logit contributions
 different+0.013
 late+0.013
 fast+0.012
 slow+0.011
 to+0.011
Neg logit contributions
lor-0.028
ocket-0.027
ster-0.025
urger-0.025
oll-0.025
Token of
Token ID286
Feature activation-6.93e-01

Pos logit contributions
 different+0.248
 fast+0.236
 slow+0.230
 very+0.212
 really+0.211
Neg logit contributions
lor-0.318
ocket-0.300
oll-0.277
urger-0.268
card-0.261
Token wind
Token ID2344
Feature activation-4.19e+00

Pos logit contributions
 different+0.013
 fast+0.011
 really+0.011
 very+0.010
 slow+0.010
Neg logit contributions
lor-0.034
ocket-0.033
urger-0.031
oll-0.031
card-0.029
Token.
Token ID13
Feature activation-4.27e-02

Pos logit contributions
 different+0.088
 fast+0.084
 slow+0.076
 very+0.072
 really+0.070
Neg logit contributions
lor-0.216
ocket-0.200
urger-0.191
card-0.181
oll-0.181
Token She
Token ID1375
Feature activation+1.20e+00

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 very+0.001
B+0.001
Neg logit contributions
lor-0.002
ocket-0.002
oll-0.002
anger-0.002
urger-0.002
Token saw
Token ID2497
Feature activation+1.29e+00

Pos logit contributions
lor+0.062
ocket+0.057
urger+0.055
oll+0.052
card+0.051
Neg logit contributions
 different-0.026
 fast-0.025
 slow-0.023
 very-0.022
 really-0.021
Token I
Token ID314
Feature activation-3.29e+00

Pos logit contributions
lor+0.067
ocket+0.065
urger+0.062
card+0.059
oll+0.057
Neg logit contributions
 fast-0.019
 different-0.019
 slow-0.017
 very-0.016
 the-0.016
Token have
Token ID423
Feature activation-1.73e+00

Pos logit contributions
 different+0.067
 fast+0.066
 really+0.062
 slow+0.062
 very+0.060
Neg logit contributions
lor-0.179
ocket-0.164
urger-0.159
card-0.151
ster-0.147
Token to
Token ID284
Feature activation-2.31e-02

Pos logit contributions
 different+0.027
 fast+0.026
 slow+0.022
 very+0.021
 really+0.020
Neg logit contributions
lor-0.100
ocket-0.093
urger-0.089
oll-0.085
card-0.084
Token start
Token ID923
Feature activation-4.47e+00

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 really+0.001
 very+0.001
Neg logit contributions
lor-0.001
ocket-0.001
urger-0.001
anger-0.001
card-0.001
Token all
Token ID477
Feature activation-5.88e+00

Pos logit contributions
 different+0.080
 fast+0.078
 slow+0.070
 very+0.066
 really+0.062
Neg logit contributions
lor-0.243
ocket-0.225
urger-0.216
oll-0.204
card-0.204
Token over
Token ID625
Feature activation-8.07e+00

Pos logit contributions
 fast+0.097
 different+0.091
 slow+0.089
 low+0.085
B+0.085
Neg logit contributions
lor-0.286
ocket-0.250
card-0.247
urger-0.240
icking-0.232
Token.
Token ID13
Feature activation-7.30e-01

Pos logit contributions
 different+0.144
 fast+0.141
 slow+0.126
 very+0.120
 really+0.113
Neg logit contributions
lor-0.438
ocket-0.407
urger-0.389
oll-0.368
card-0.366
Tokenâ
Token ID22940
Feature activation+4.86e-01

Pos logit contributions
 different+0.017
 fast+0.017
 slow+0.016
 very+0.015
 really+0.015
Neg logit contributions
lor-0.036
ocket-0.033
urger-0.032
card-0.030
ster-0.030
Token
Token ID26391
Feature activation-9.38e-01

Pos logit contributions
lor+0.023
ocket+0.021
urger+0.020
oll+0.019
card+0.019
Neg logit contributions
 fast-0.012
 different-0.012
 slow-0.011
 very-0.011
 really-0.011
Token Lily
Token ID20037
Feature activation-2.18e+00

Pos logit contributions
 fast+0.025
 different+0.024
 slow+0.023
 very+0.022
 really+0.022
Neg logit contributions
lor-0.043
ocket-0.041
urger-0.039
oll-0.036
card-0.036
Token quickly
Token ID2952
Feature activation-3.62e+00

Pos logit contributions
 different+0.052
 fast+0.051
 slow+0.047
 very+0.046
 really+0.044
Neg logit contributions
lor-0.107
ocket-0.099
urger-0.094
oll-0.088
card-0.088
Token.
Token ID13
Feature activation-7.88e-01

Pos logit contributions
 fast+0.026
 different+0.024
 slow+0.023
 very+0.022
 really+0.022
Neg logit contributions
lor-0.055
ocket-0.053
urger-0.050
card-0.047
oll-0.047
Token
Token ID198
Feature activation-1.16e+00

Pos logit contributions
 different+0.018
 fast+0.018
 slow+0.016
 very+0.016
 really+0.015
Neg logit contributions
lor-0.039
ocket-0.037
urger-0.035
card-0.033
ster-0.032
Token
Token ID198
Feature activation-1.32e+00

Pos logit contributions
 different+0.014
 fast+0.013
 slow+0.011
 very+0.011
 really+0.009
Neg logit contributions
lor-0.070
ocket-0.064
urger-0.061
oll-0.060
anger-0.058
TokenTom
Token ID13787
Feature activation-1.47e+00

Pos logit contributions
 different+0.026
 fast+0.025
 very+0.022
 slow+0.022
 really+0.020
Neg logit contributions
lor-0.071
ocket-0.063
urger-0.060
oll-0.059
card-0.057
Token rushed
Token ID13999
Feature activation-2.40e+00

Pos logit contributions
 different+0.029
 fast+0.029
 slow+0.026
 very+0.026
 really+0.025
Neg logit contributions
lor-0.079
ocket-0.074
urger-0.069
card-0.066
oll-0.066
Token over
Token ID625
Feature activation-8.06e+00

Pos logit contributions
 different+0.035
 fast+0.033
 slow+0.029
 very+0.027
 really+0.025
Neg logit contributions
lor-0.139
ocket-0.130
urger-0.125
card-0.119
oll-0.118
Token and
Token ID290
Feature activation+3.68e-02

Pos logit contributions
 different+0.094
 fast+0.091
 slow+0.074
 very+0.069
 really+0.063
Neg logit contributions
lor-0.498
ocket-0.467
urger-0.451
oll-0.428
card-0.427
Token opened
Token ID4721
Feature activation+1.67e+00

Pos logit contributions
lor+0.002
ocket+0.002
urger+0.002
oll+0.002
card+0.002
Neg logit contributions
 fast-0.001
 different-0.001
 slow-0.001
 very-0.001
 really-0.001
Token the
Token ID262
Feature activation+2.06e-01

Pos logit contributions
lor+0.110
ocket+0.104
urger+0.101
oll+0.096
card+0.095
Neg logit contributions
 different-0.014
 fast-0.013
 slow-0.009
 very-0.008
 really-0.007
Token buckle
Token ID44983
Feature activation+1.90e+00

Pos logit contributions
lor+0.008
ocket+0.007
urger+0.007
oll+0.006
card+0.006
Neg logit contributions
 different-0.008
 fast-0.007
 slow-0.007
 very-0.007
 really-0.007
Token.
Token ID13
Feature activation-8.66e-01

Pos logit contributions
lor+0.125
ocket+0.119
urger+0.116
oll+0.109
card+0.105
Neg logit contributions
 fast-0.017
 different-0.017
 very-0.013
 slow-0.012
 really-0.009
Token head
Token ID1182
Feature activation-3.63e-01

Pos logit contributions
lor+0.096
ocket+0.086
urger+0.079
oll+0.075
card+0.072
Neg logit contributions
 fast-0.074
 different-0.073
 slow-0.070
 very-0.069
 really-0.064
Token low
Token ID1877
Feature activation-4.63e+00

Pos logit contributions
 fast+0.006
 different+0.006
 slow+0.005
 very+0.005
 really+0.005
Neg logit contributions
lor-0.021
ocket-0.020
urger-0.019
oll-0.018
card-0.018
Token.
Token ID13
Feature activation-9.83e-01

Pos logit contributions
 different+0.059
 fast+0.058
 slow+0.049
 very+0.046
 really+0.042
Neg logit contributions
lor-0.280
ocket-0.263
urger-0.252
oll-0.240
card-0.239
Token He
Token ID679
Feature activation+9.38e-01

Pos logit contributions
 different+0.019
 fast+0.018
 slow+0.016
 very+0.016
 really+0.015
Neg logit contributions
lor-0.053
ocket-0.049
urger-0.047
oll-0.045
card-0.045
Token went
Token ID1816
Feature activation-2.79e-01

Pos logit contributions
lor+0.049
ocket+0.045
urger+0.043
card+0.040
oll+0.040
Neg logit contributions
 different-0.021
 fast-0.021
 slow-0.019
 very-0.018
 really-0.018
Token over
Token ID625
Feature activation-8.06e+00

Pos logit contributions
 different+0.004
 fast+0.004
 slow+0.003
 very+0.003
 really+0.003
Neg logit contributions
lor-0.017
ocket-0.016
urger-0.015
oll-0.014
card-0.014
Token to
Token ID284
Feature activation-1.77e+00

Pos logit contributions
 different+0.091
 fast+0.087
 slow+0.072
 very+0.065
 late+0.059
Neg logit contributions
lor-0.486
ocket-0.458
urger-0.437
oll-0.420
card-0.416
Token his
Token ID465
Feature activation+9.51e-01

Pos logit contributions
 different+0.027
 fast+0.026
 slow+0.023
 very+0.021
 really+0.020
Neg logit contributions
lor-0.107
ocket-0.100
urger-0.097
oll-0.092
card-0.092
Token owner
Token ID4870
Feature activation-1.54e+00

Pos logit contributions
lor+0.043
ocket+0.039
urger+0.036
oll+0.034
card+0.034
Neg logit contributions
 different-0.028
 fast-0.028
 slow-0.026
 very-0.026
 really-0.024
Token,
Token ID11
Feature activation-2.05e+00

Pos logit contributions
 different+0.015
 fast+0.013
 very+0.012
 slow+0.011
 really+0.010
Neg logit contributions
lor-0.103
ocket-0.094
urger-0.091
anger-0.087
bridge-0.086
Token who
Token ID508
Feature activation+9.22e-01

Pos logit contributions
 different+0.042
 fast+0.041
 slow+0.037
 very+0.035
 really+0.034
Neg logit contributions
lor-0.107
ocket-0.099
urger-0.095
card-0.089
oll-0.089
Token
Token ID220
Feature activation-9.34e-01

Pos logit contributions
 fast+0.024
 different+0.024
 slow+0.022
 very+0.021
 really+0.021
Neg logit contributions
lor-0.042
ocket-0.039
urger-0.037
oll-0.035
card-0.034
Token
Token ID198
Feature activation-7.12e-01

Pos logit contributions
 different+0.010
 fast+0.010
 slow+0.008
 very+0.007
 really+0.006
Neg logit contributions
lor-0.058
ocket-0.055
urger-0.053
oll-0.050
card-0.050
Token
Token ID198
Feature activation-9.58e-01

Pos logit contributions
 different+0.009
 fast+0.009
 slow+0.008
 very+0.007
 really+0.006
Neg logit contributions
lor-0.042
ocket-0.038
urger-0.036
oll-0.035
anger-0.034
TokenJohn
Token ID7554
Feature activation-3.45e+00

Pos logit contributions
 different+0.022
 fast+0.022
 very+0.020
 slow+0.020
 scared+0.019
Neg logit contributions
lor-0.047
ocket-0.038
urger-0.037
bridge-0.037
uit-0.037
Token ran
Token ID4966
Feature activation-2.64e-01

Pos logit contributions
 different+0.068
 fast+0.068
 slow+0.062
 very+0.060
 really+0.059
Neg logit contributions
lor-0.186
ocket-0.173
urger-0.163
card-0.155
oll-0.154
Token over
Token ID625
Feature activation-8.01e+00

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 late+0.004
 panic+0.004
Neg logit contributions
lor-0.013
ocket-0.012
urger-0.011
anger-0.011
card-0.011
Token to
Token ID284
Feature activation-1.92e+00

Pos logit contributions
 different+0.096
 fast+0.093
 slow+0.081
 late+0.073
 very+0.072
Neg logit contributions
lor-0.457
ocket-0.432
urger-0.409
anger-0.395
oll-0.394
Token the
Token ID262
Feature activation-1.35e+00

Pos logit contributions
 different+0.022
 fast+0.020
 slow+0.017
 very+0.015
 really+0.014
Neg logit contributions
lor-0.125
ocket-0.116
urger-0.113
card-0.108
oll-0.107
Token rock
Token ID3881
Feature activation-1.85e+00

Pos logit contributions
 different+0.039
 fast+0.038
 slow+0.035
 late+0.034
 very+0.034
Neg logit contributions
lor-0.058
ocket-0.053
urger-0.050
ster-0.047
card-0.047
Token and
Token ID290
Feature activation+3.93e-01

Pos logit contributions
 fast+0.022
 different+0.021
 very+0.018
 slow+0.017
 really+0.015
Neg logit contributions
lor-0.114
ocket-0.108
urger-0.105
oll-0.099
card-0.097
Token started
Token ID2067
Feature activation-3.89e+00

Pos logit contributions
lor+0.019
ocket+0.018
urger+0.017
oll+0.016
card+0.016
Neg logit contributions
 different-0.010
 fast-0.009
 slow-0.009
 very-0.008
 really-0.008
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
 different+0.103
 fast+0.100
 slow+0.089
 very+0.085
 really+0.081
Neg logit contributions
lor-0.308
ocket-0.286
urger-0.274
oll-0.260
card-0.258
Token He
Token ID679
Feature activation+8.47e-01

Pos logit contributions
 different+0.020
 fast+0.020
 slow+0.018
 very+0.017
 really+0.016
Neg logit contributions
lor-0.058
ocket-0.054
urger-0.052
oll-0.049
card-0.049
Token jumped
Token ID11687
Feature activation+1.30e+00

Pos logit contributions
lor+0.043
ocket+0.040
urger+0.038
oll+0.036
card+0.035
Neg logit contributions
 different-0.019
 fast-0.019
 slow-0.017
 very-0.017
 really-0.016
Token around
Token ID1088
Feature activation-6.23e+00

Pos logit contributions
lor+0.069
ocket+0.064
urger+0.061
oll+0.058
card+0.058
Neg logit contributions
 different-0.024
 fast-0.023
 slow-0.021
 very-0.020
 late-0.019
Token with
Token ID351
Feature activation-8.75e-01

Pos logit contributions
 different+0.093
 fast+0.091
 slow+0.080
 very+0.073
 late+0.073
Neg logit contributions
lor-0.346
ocket-0.326
urger-0.310
card-0.295
oll-0.293
Token gust
Token ID35253
Feature activation-7.98e+00

Pos logit contributions
 different+0.019
 fast+0.019
 slow+0.017
 very+0.016
 really+0.016
Neg logit contributions
lor-0.045
ocket-0.041
urger-0.040
oll-0.037
card-0.037
Tokeno
Token ID78
Feature activation-7.11e-02

Pos logit contributions
 different+0.213
 fast+0.205
 slow+0.192
 very+0.183
 late+0.180
Neg logit contributions
lor-0.360
ocket-0.325
urger-0.314
oll-0.299
ster-0.296
Token and
Token ID290
Feature activation+8.01e-01

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 very+0.001
 really+0.001
Neg logit contributions
lor-0.004
ocket-0.003
urger-0.003
oll-0.003
card-0.003
Token spun
Token ID26843
Feature activation-8.54e-01

Pos logit contributions
lor+0.036
ocket+0.034
urger+0.032
card+0.031
ster+0.030
Neg logit contributions
 different-0.018
 fast-0.017
 late-0.016
 slow-0.016
 really-0.015
Token in
Token ID287
Feature activation-4.11e+00

Pos logit contributions
 different+0.015
 late+0.014
 fast+0.014
 slow+0.013
 upset+0.013
Neg logit contributions
lor-0.041
ocket-0.037
urger-0.036
bridge-0.035
anger-0.035
Token circles
Token ID13332
Feature activation-2.38e-03

Pos logit contributions
 fast+0.065
 different+0.062
 late+0.061
 slow+0.059
 very+0.055
Neg logit contributions
lor-0.206
ocket-0.195
urger-0.187
card-0.176
uit-0.174
Token the
Token ID262
Feature activation-9.22e-01

Pos logit contributions
 fast+0.056
 different+0.053
 slow+0.046
 late+0.045
 very+0.042
Neg logit contributions
lor-0.291
ocket-0.277
urger-0.261
card-0.252
oll-0.248
Token park
Token ID3952
Feature activation-1.64e-01

Pos logit contributions
 fast+0.025
 different+0.024
 late+0.023
 slow+0.023
B+0.022
Neg logit contributions
lor-0.037
ocket-0.033
card-0.031
urger-0.031
 suitcase-0.030
Token.
Token ID13
Feature activation-5.66e-01

Pos logit contributions
 different+0.002
 fast+0.002
 slow+0.002
 late+0.002
 very+0.002
Neg logit contributions
lor-0.009
ocket-0.009
urger-0.008
card-0.008
oll-0.008
Token They
Token ID1119
Feature activation-6.55e-01

Pos logit contributions
 different+0.012
 fast+0.011
 slow+0.010
 very+0.010
 hurt+0.009
Neg logit contributions
lor-0.029
ocket-0.027
urger-0.025
oll-0.024
card-0.024
Token went
Token ID1816
Feature activation-2.68e-01

Pos logit contributions
 different+0.015
 fast+0.015
 late+0.014
 slow+0.013
 very+0.013
Neg logit contributions
lor-0.031
ocket-0.029
urger-0.027
oll-0.026
card-0.026
Token over
Token ID625
Feature activation-7.96e+00

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 late+0.004
 very+0.004
Neg logit contributions
lor-0.014
ocket-0.013
urger-0.012
card-0.012
anger-0.012
Token to
Token ID284
Feature activation-1.69e+00

Pos logit contributions
 different+0.103
 fast+0.102
 late+0.095
 slow+0.092
 upset+0.084
Neg logit contributions
lor-0.418
ocket-0.401
urger-0.375
card-0.362
anger-0.359
Token a
Token ID257
Feature activation-6.17e-01

Pos logit contributions
 fast+0.021
 different+0.020
 late+0.017
 slow+0.017
 very+0.016
Neg logit contributions
lor-0.097
ocket-0.092
urger-0.088
card-0.083
oll-0.082
Token tree
Token ID5509
Feature activation-1.85e+00

Pos logit contributions
 fast+0.012
 late+0.012
 different+0.012
 slow+0.011
Stop+0.011
Neg logit contributions
lor-0.029
ocket-0.027
urger-0.025
card-0.025
ster-0.024
Token with
Token ID351
Feature activation-5.14e-01

Pos logit contributions
 different+0.027
 fast+0.026
 slow+0.023
 very+0.022
 really+0.020
Neg logit contributions
lor-0.109
ocket-0.102
urger-0.098
oll-0.093
card-0.092
Token a
Token ID257
Feature activation+6.33e-01

Pos logit contributions
 different+0.008
 fast+0.008
 slow+0.007
 very+0.006
 really+0.006
Neg logit contributions
lor-0.030
ocket-0.028
urger-0.027
oll-0.025
card-0.025
Token
Token ID198
Feature activation-1.06e+00

Pos logit contributions
 different+0.007
 fast+0.007
 slow+0.006
 very+0.005
 really+0.004
Neg logit contributions
lor-0.054
ocket-0.052
urger-0.050
oll-0.048
card-0.047
TokenThe
Token ID464
Feature activation+1.35e-01

Pos logit contributions
 different+0.020
 fast+0.019
 slow+0.017
 very+0.017
 really+0.016
Neg logit contributions
lor-0.058
ocket-0.052
urger-0.050
oll-0.048
card-0.048
Token two
Token ID734
Feature activation-1.66e+00

Pos logit contributions
lor+0.007
ocket+0.006
urger+0.006
oll+0.006
card+0.006
Neg logit contributions
 different-0.003
 fast-0.003
 slow-0.003
 very-0.003
 really-0.003
Token friends
Token ID2460
Feature activation-2.06e+00

Pos logit contributions
 different+0.041
 fast+0.040
 slow+0.036
 very+0.036
 really+0.035
Neg logit contributions
lor-0.086
ocket-0.079
urger-0.075
card-0.071
anger-0.068
Token ran
Token ID4966
Feature activation-3.06e-01

Pos logit contributions
 different+0.044
 fast+0.041
 slow+0.038
 really+0.038
 very+0.037
Neg logit contributions
lor-0.113
ocket-0.101
urger-0.098
card-0.092
ster-0.091
Token over
Token ID625
Feature activation-7.96e+00

Pos logit contributions
 different+0.004
 fast+0.004
 slow+0.004
 late+0.003
 very+0.003
Neg logit contributions
lor-0.016
ocket-0.015
urger-0.015
card-0.014
anger-0.014
Token to
Token ID284
Feature activation-1.82e+00

Pos logit contributions
 different+0.094
 fast+0.093
 slow+0.080
 late+0.072
 very+0.070
Neg logit contributions
lor-0.465
ocket-0.436
urger-0.418
oll-0.398
card-0.397
Token the
Token ID262
Feature activation-1.45e+00

Pos logit contributions
 different+0.025
 fast+0.025
 slow+0.021
 very+0.020
 really+0.018
Neg logit contributions
lor-0.108
ocket-0.101
urger-0.098
oll-0.093
card-0.092
Token wealthy
Token ID11574
Feature activation-2.63e+00

Pos logit contributions
 fast+0.041
 different+0.041
 slow+0.038
 late+0.037
 very+0.036
Neg logit contributions
lor-0.061
ocket-0.056
urger-0.053
card-0.050
ster-0.049
Token game
Token ID983
Feature activation-1.36e-01

Pos logit contributions
 different+0.076
 fast+0.076
 slow+0.070
 very+0.069
 late+0.068
Neg logit contributions
lor-0.109
ocket-0.100
urger-0.095
ster-0.089
card-0.088
Token and
Token ID290
Feature activation+5.73e-01

Pos logit contributions
 different+0.002
 fast+0.002
 very+0.001
 slow+0.001
 really+0.001
Neg logit contributions
lor-0.008
ocket-0.008
urger-0.008
oll-0.007
card-0.007
Token."
Token ID526
Feature activation-3.07e+00

Pos logit contributions
 different+0.040
 fast+0.039
 slow+0.035
 very+0.034
 really+0.032
Neg logit contributions
lor-0.101
ocket-0.093
urger-0.089
oll-0.084
card-0.084
Token
Token ID198
Feature activation-1.58e+00

Pos logit contributions
 fast+0.066
 different+0.065
 slow+0.059
 very+0.054
 quiet+0.051
Neg logit contributions
lor-0.154
ocket-0.140
urger-0.133
oll-0.127
card-0.126
Token
Token ID198
Feature activation-1.47e+00

Pos logit contributions
 fast+0.024
 different+0.023
 slow+0.021
 very+0.019
 late+0.016
Neg logit contributions
lor-0.089
ocket-0.081
urger-0.077
oll-0.074
card-0.072
TokenJack
Token ID14295
Feature activation-3.21e+00

Pos logit contributions
 fast+0.033
 different+0.031
 slow+0.030
 very+0.029
 hurt+0.027
Neg logit contributions
lor-0.073
ocket-0.063
urger-0.060
ster-0.057
oll-0.057
Token went
Token ID1816
Feature activation-2.00e-01

Pos logit contributions
 different+0.070
 fast+0.069
 slow+0.062
 very+0.060
 really+0.058
Neg logit contributions
lor-0.165
ocket-0.153
urger-0.145
oll-0.137
card-0.136
Token over
Token ID625
Feature activation-7.95e+00

Pos logit contributions
 fast+0.002
 different+0.002
 slow+0.002
 very+0.002
 really+0.001
Neg logit contributions
lor-0.013
ocket-0.012
urger-0.012
oll-0.011
card-0.011
Token to
Token ID284
Feature activation-1.79e+00

Pos logit contributions
 different+0.101
 fast+0.096
 slow+0.083
 late+0.074
 very+0.072
Neg logit contributions
lor-0.436
ocket-0.418
urger-0.392
card-0.380
anger-0.378
Token the
Token ID262
Feature activation-1.12e+00

Pos logit contributions
 different+0.021
 fast+0.021
 slow+0.017
 very+0.016
 really+0.014
Neg logit contributions
lor-0.109
ocket-0.103
urger-0.099
oll-0.094
card-0.094
Token tap
Token ID9814
Feature activation-1.52e+00

Pos logit contributions
 different+0.032
 fast+0.032
 slow+0.029
 very+0.028
 late+0.028
Neg logit contributions
lor-0.047
ocket-0.044
urger-0.041
card-0.039
ster-0.039
Token and
Token ID290
Feature activation+7.69e-01

Pos logit contributions
 different+0.019
 fast+0.019
 slow+0.016
 very+0.016
 really+0.014
Neg logit contributions
lor-0.093
ocket-0.088
urger-0.084
oll-0.080
card-0.079
Token pulled
Token ID5954
Feature activation-3.03e-01

Pos logit contributions
lor+0.036
ocket+0.033
urger+0.032
card+0.030
oll+0.030
Neg logit contributions
 different-0.019
 fast-0.018
 slow-0.017
 very-0.016
 late-0.016
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
 different+0.016
 fast+0.016
 slow+0.013
 very+0.012
 really+0.010
Neg logit contributions
lor-0.094
ocket-0.087
urger-0.084
oll-0.081
card-0.080
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
 different+0.015
 fast+0.014
 slow+0.013
 very+0.012
 late+0.011
Neg logit contributions
lor-0.059
ocket-0.051
urger-0.049
anger-0.048
card-0.048
TokenThey
Token ID2990
Feature activation-1.44e-01

Pos logit contributions
 different+0.025
 fast+0.024
 slow+0.022
 very+0.022
 late+0.021
Neg logit contributions
lor-0.052
ocket-0.044
urger-0.043
card-0.041
ster-0.040
Token both
Token ID1111
Feature activation-4.71e+00

Pos logit contributions
 different+0.003
 fast+0.003
 very+0.003
 really+0.003
 slow+0.003
Neg logit contributions
lor-0.008
ocket-0.007
urger-0.007
anger-0.007
card-0.007
Token went
Token ID1816
Feature activation-1.29e-01

Pos logit contributions
 different+0.120
 fast+0.120
 slow+0.110
 late+0.107
 very+0.105
Neg logit contributions
lor-0.217
ocket-0.203
urger-0.192
oll-0.182
card-0.177
Token over
Token ID625
Feature activation-7.95e+00

Pos logit contributions
 fast+0.002
 different+0.002
 very+0.002
 slow+0.002
 really+0.002
Neg logit contributions
lor-0.007
ocket-0.007
urger-0.007
oll-0.006
ster-0.006
Token and
Token ID290
Feature activation+3.43e-01

Pos logit contributions
 fast+0.091
 different+0.090
 slow+0.082
 late+0.078
 quiet+0.065
Neg logit contributions
lor-0.442
ocket-0.426
urger-0.400
card-0.384
oll-0.380
Token tried
Token ID3088
Feature activation-7.02e-01

Pos logit contributions
lor+0.018
ocket+0.016
urger+0.015
oll+0.015
card+0.014
Neg logit contributions
 different-0.008
 fast-0.007
 slow-0.007
 very-0.007
 really-0.006
Token to
Token ID284
Feature activation+2.78e-01

Pos logit contributions
 fast+0.010
 late+0.009
B+0.009
Stop+0.009
 different+0.009
Neg logit contributions
lor-0.037
urger-0.034
ocket-0.034
card-0.032
uit-0.031
Token decide
Token ID5409
Feature activation+1.44e+00

Pos logit contributions
lor+0.012
ocket+0.012
urger+0.011
card+0.010
oll+0.010
Neg logit contributions
 different-0.007
 fast-0.007
 late-0.007
 slow-0.007
 very-0.007
Token which
Token ID543
Feature activation+1.66e+00

Pos logit contributions
lor+0.073
ocket+0.068
urger+0.065
oll+0.061
card+0.060
Neg logit contributions
 different-0.033
 fast-0.032
 slow-0.029
 very-0.028
 really-0.027
Token
Token ID198
Feature activation-3.97e-01

Pos logit contributions
 fast+0.008
 different+0.008
 slow+0.007
 very+0.007
 really+0.006
Neg logit contributions
lor-0.023
ocket-0.020
urger-0.020
card-0.019
oll-0.019
Token
Token ID198
Feature activation-5.49e-01

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 very+0.004
 late+0.004
Neg logit contributions
lor-0.023
ocket-0.021
urger-0.020
card-0.019
anger-0.019
TokenTim
Token ID14967
Feature activation-2.16e+00

Pos logit contributions
 different+0.011
 fast+0.010
 very+0.009
 slow+0.009
 really+0.008
Neg logit contributions
lor-0.029
ocket-0.025
urger-0.025
card-0.024
oll-0.023
Tokenmy
Token ID1820
Feature activation-1.78e+00

Pos logit contributions
 different+0.045
 fast+0.044
 slow+0.040
 very+0.038
 really+0.037
Neg logit contributions
lor-0.114
ocket-0.105
urger-0.100
oll-0.095
card-0.094
Token went
Token ID1816
Feature activation-9.56e-03

Pos logit contributions
 different+0.041
 fast+0.040
 slow+0.036
 late+0.036
 very+0.034
Neg logit contributions
lor-0.086
ocket-0.078
urger-0.077
ster-0.071
oll-0.071
Token over
Token ID625
Feature activation-7.94e+00

Pos logit contributions
 different+0.000
 fast+0.000
 slow+0.000
 very+0.000
 late+0.000
Neg logit contributions
lor-0.001
ocket-0.001
urger-0.000
card-0.000
anger-0.000
Token to
Token ID284
Feature activation-1.65e+00

Pos logit contributions
 different+0.108
 fast+0.098
 slow+0.088
 late+0.086
 very+0.080
Neg logit contributions
lor-0.413
ocket-0.396
urger-0.372
anger-0.364
uit-0.361
Token the
Token ID262
Feature activation-1.38e+00

Pos logit contributions
 different+0.020
 fast+0.020
 slow+0.016
 very+0.016
 late+0.015
Neg logit contributions
lor-0.098
ocket-0.092
urger-0.088
card-0.084
oll-0.083
Token kids
Token ID3988
Feature activation-3.26e+00

Pos logit contributions
 different+0.035
 fast+0.034
 late+0.033
 slow+0.032
 very+0.031
Neg logit contributions
lor-0.061
ocket-0.056
urger-0.053
card-0.051
anger-0.050
Token and
Token ID290
Feature activation+3.04e-01

Pos logit contributions
 different+0.044
 fast+0.042
 slow+0.036
 very+0.036
 really+0.033
Neg logit contributions
lor-0.201
ocket-0.186
urger-0.179
oll-0.169
card-0.169
Token tried
Token ID3088
Feature activation-2.73e-01

Pos logit contributions
lor+0.014
ocket+0.013
urger+0.013
card+0.012
oll+0.012
Neg logit contributions
 different-0.007
 fast-0.007
 slow-0.007
 very-0.006
 late-0.006
Token
Token ID198
Feature activation-9.80e-01

Pos logit contributions
 different+0.016
 gloomy+0.014
 very+0.014
 fast+0.014
 muddy+0.013
Neg logit contributions
lor-0.045
ocket-0.037
urger-0.036
card-0.035
glass-0.035
TokenJohn
Token ID7554
Feature activation-3.50e+00

Pos logit contributions
 different+0.022
 fast+0.019
 very+0.019
 slow+0.018
 fun+0.018
Neg logit contributions
lor-0.048
ocket-0.040
urger-0.039
card-0.039
glass-0.038
Token decided
Token ID3066
Feature activation+3.20e+00

Pos logit contributions
 different+0.071
 fast+0.070
 slow+0.063
 very+0.060
 really+0.057
Neg logit contributions
lor-0.184
ocket-0.171
urger-0.163
oll-0.154
card-0.153
Token to
Token ID284
Feature activation-4.40e-01

Pos logit contributions
lor+0.207
ocket+0.195
urger+0.188
oll+0.180
card+0.178
Neg logit contributions
 different-0.029
 fast-0.029
 slow-0.022
 very-0.020
 really-0.018
Token go
Token ID467
Feature activation-1.85e+00

Pos logit contributions
 different+0.011
 fast+0.011
 slow+0.011
 very+0.010
 really+0.010
Neg logit contributions
lor-0.021
ocket-0.020
urger-0.019
oll-0.018
card-0.017
Token over
Token ID625
Feature activation-7.94e+00

Pos logit contributions
 fast+0.028
 different+0.025
 slow+0.023
 very+0.022
 really+0.020
Neg logit contributions
lor-0.117
ocket-0.109
urger-0.107
oll-0.101
bridge-0.098
Token to
Token ID284
Feature activation-1.62e+00

Pos logit contributions
 different+0.097
 fast+0.092
 slow+0.077
 very+0.071
 really+0.065
Neg logit contributions
lor-0.478
ocket-0.449
urger-0.430
card-0.410
oll-0.409
Token the
Token ID262
Feature activation-1.53e+00

Pos logit contributions
 different+0.021
 fast+0.021
 slow+0.017
 very+0.016
 really+0.015
Neg logit contributions
lor-0.097
ocket-0.091
urger-0.087
card-0.083
oll-0.082
Token child
Token ID1200
Feature activation-1.07e+00

Pos logit contributions
 different+0.046
 fast+0.046
 slow+0.043
 late+0.041
 very+0.041
Neg logit contributions
lor-0.063
ocket-0.057
urger-0.054
card-0.052
ster-0.050
Token and
Token ID290
Feature activation+6.14e-01

Pos logit contributions
 different+0.013
 fast+0.012
 very+0.011
 slow+0.010
 really+0.010
Neg logit contributions
lor-0.067
ocket-0.063
urger-0.060
oll-0.057
anger-0.057
Token ask
Token ID1265
Feature activation+3.62e+00

Pos logit contributions
lor+0.033
ocket+0.030
urger+0.029
oll+0.027
card+0.027
Neg logit contributions
 different-0.013
 fast-0.013
 slow-0.012
 very-0.011
 really-0.011
Token in
Token ID287
Feature activation-4.61e+00

Pos logit contributions
 different+0.007
 fast+0.007
 slow+0.006
 very+0.006
 really+0.006
Neg logit contributions
lor-0.019
ocket-0.018
urger-0.017
oll-0.016
card-0.016
Token time
Token ID640
Feature activation-1.74e+00

Pos logit contributions
 different+0.067
 fast+0.065
 slow+0.056
 very+0.053
 really+0.050
Neg logit contributions
lor-0.262
ocket-0.245
urger-0.234
card-0.223
oll-0.222
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
 different+0.024
 fast+0.023
 slow+0.019
 very+0.018
 really+0.017
Neg logit contributions
lor-0.103
ocket-0.096
urger-0.092
oll-0.088
card-0.088
Token They
Token ID1119
Feature activation-4.80e-01

Pos logit contributions
 different+0.006
 fast+0.006
 slow+0.006
 very+0.005
 really+0.005
Neg logit contributions
lor-0.019
ocket-0.017
urger-0.017
oll-0.016
card-0.016
Token went
Token ID1816
Feature activation-2.39e-01

Pos logit contributions
 different+0.012
 fast+0.012
 slow+0.011
 very+0.011
 really+0.010
Neg logit contributions
lor-0.023
ocket-0.021
urger-0.020
oll-0.019
card-0.019
Token over
Token ID625
Feature activation-7.93e+00

Pos logit contributions
 different+0.004
 fast+0.004
 slow+0.004
 very+0.004
 really+0.003
Neg logit contributions
lor-0.013
ocket-0.012
urger-0.012
card-0.011
oll-0.011
Token a
Token ID257
Feature activation-6.94e-01

Pos logit contributions
 different+0.107
 fast+0.097
 late+0.088
 slow+0.088
 upset+0.086
Neg logit contributions
lor-0.397
ocket-0.380
urger-0.359
anger-0.354
glass-0.352
Token big
Token ID1263
Feature activation-1.91e+00

Pos logit contributions
 fast+0.014
 late+0.014
 different+0.014
Stop+0.014
 each+0.013
Neg logit contributions
lor-0.031
ocket-0.028
urger-0.027
card-0.026
 suitcase-0.026
Token hill
Token ID12788
Feature activation-1.89e+00

Pos logit contributions
 different+0.055
 fast+0.054
 late+0.052
 very+0.049
 really+0.049
Neg logit contributions
lor-0.073
ocket-0.067
urger-0.065
card-0.061
 suitcase-0.059
Token and
Token ID290
Feature activation+8.32e-01

Pos logit contributions
 different+0.033
 fast+0.030
Stop+0.028
 slow+0.028
B+0.027
Neg logit contributions
lor-0.097
ocket-0.087
urger-0.084
card-0.084
anger-0.081
Token down
Token ID866
Feature activation-3.87e+00

Pos logit contributions
lor+0.039
ocket+0.037
urger+0.035
card+0.034
oll+0.033
Neg logit contributions
 different-0.018
 fast-0.017
 slow-0.015
 very-0.015
 late-0.014
Token cry
Token ID3960
Feature activation-1.10e+00

Pos logit contributions
 fast+0.017
 different+0.017
 late+0.017
B+0.016
 very+0.015
Neg logit contributions
lor-0.031
ocket-0.029
urger-0.029
icking-0.026
card-0.026
Token.
Token ID13
Feature activation-5.82e-01

Pos logit contributions
 different+0.020
 fast+0.018
 slow+0.017
Stop+0.017
 late+0.016
Neg logit contributions
lor-0.056
ocket-0.052
urger-0.051
oll-0.049
ster-0.048
Token Mom
Token ID11254
Feature activation-1.97e+00

Pos logit contributions
 fast+0.014
 different+0.014
 slow+0.012
B+0.012
 competitive+0.012
Neg logit contributions
lor-0.027
ocket-0.023
urger-0.022
card-0.021
anger-0.021
Tokenmy
Token ID1820
Feature activation-1.49e+00

Pos logit contributions
 different+0.042
 fast+0.041
 slow+0.037
 very+0.036
 really+0.034
Neg logit contributions
lor-0.102
ocket-0.095
urger-0.091
oll-0.085
card-0.085
Token went
Token ID1816
Feature activation-1.14e-01

Pos logit contributions
 different+0.033
 fast+0.032
 slow+0.029
 very+0.028
 really+0.027
Neg logit contributions
lor-0.077
ocket-0.071
urger-0.068
oll-0.064
card-0.064
Token over
Token ID625
Feature activation-7.93e+00

Pos logit contributions
 different+0.002
 fast+0.001
 slow+0.001
 very+0.001
 really+0.001
Neg logit contributions
lor-0.007
ocket-0.006
urger-0.006
card-0.006
oll-0.006
Token and
Token ID290
Feature activation+7.93e-01

Pos logit contributions
 different+0.126
 fast+0.120
 slow+0.111
 very+0.099
 late+0.097
Neg logit contributions
lor-0.405
ocket-0.387
urger-0.359
uit-0.349
card-0.349
Token told
Token ID1297
Feature activation+4.18e+00

Pos logit contributions
lor+0.037
ocket+0.034
urger+0.032
card+0.031
ster+0.030
Neg logit contributions
 different-0.019
 fast-0.019
 slow-0.017
 very-0.016
 late-0.016
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
lor+0.232
ocket+0.218
urger+0.209
oll+0.199
card+0.197
Neg logit contributions
 fast-0.067
 different-0.067
 slow-0.059
 late-0.054
 very-0.054
Token other
Token ID584
Feature activation-2.01e+00

Pos logit contributions
 different+0.002
 fast+0.002
 slow+0.002
 very+0.002
 really+0.002
Neg logit contributions
lor-0.007
ocket-0.007
urger-0.006
card-0.006
oll-0.006
Token girl
Token ID2576
Feature activation-1.62e+00

Pos logit contributions
 different+0.052
 fast+0.048
 very+0.045
 slow+0.044
 really+0.043
Neg logit contributions
lor-0.105
ocket-0.093
urger-0.088
card-0.082
oll-0.081
Token!
Token ID0
Feature activation-9.58e-01

Pos logit contributions
 fast+0.001
 different+0.001
 slow+0.001
 late+0.001
B+0.001
Neg logit contributions
lor-0.003
ocket-0.003
urger-0.003
oll-0.002
ster-0.002
Token
Token ID198
Feature activation-5.51e-01

Pos logit contributions
 different+0.018
 fast+0.017
 very+0.014
 slow+0.014
 busy+0.013
Neg logit contributions
lor-0.051
ocket-0.044
urger-0.044
oll-0.042
ster-0.041
Token
Token ID198
Feature activation-6.64e-01

Pos logit contributions
 different+0.008
 fast+0.007
 slow+0.007
 very+0.007
 competitive+0.006
Neg logit contributions
lor-0.031
ocket-0.027
urger-0.026
oll-0.025
ogo-0.025
TokenHe
Token ID1544
Feature activation+1.48e+00

Pos logit contributions
 different+0.013
 fast+0.012
 very+0.012
 upset+0.011
 slow+0.011
Neg logit contributions
lor-0.034
urger-0.029
ocket-0.028
uit-0.027
ster-0.027
Token went
Token ID1816
Feature activation-1.08e-01

Pos logit contributions
lor+0.068
ocket+0.064
urger+0.061
ster+0.056
card+0.056
Neg logit contributions
 different-0.035
 fast-0.034
 late-0.032
 slow-0.031
 very-0.030
Token over
Token ID625
Feature activation-7.91e+00

Pos logit contributions
 different+0.001
 fast+0.001
 slow+0.001
 late+0.001
Stop+0.001
Neg logit contributions
lor-0.006
ocket-0.006
urger-0.005
card-0.005
anger-0.005
Token to
Token ID284
Feature activation-1.80e+00

Pos logit contributions
 different+0.115
 fast+0.109
 upset+0.105
 slow+0.103
Ste+0.101
Neg logit contributions
ocket-0.368
lor-0.366
urger-0.335
ster-0.330
glass-0.326
Token the
Token ID262
Feature activation-1.43e+00

Pos logit contributions
 fast+0.020
 different+0.020
 late+0.016
 slow+0.016
 very+0.015
Neg logit contributions
lor-0.104
ocket-0.100
urger-0.096
ster-0.090
card-0.090
Token frog
Token ID21264
Feature activation-2.36e+00

Pos logit contributions
 different+0.038
 fast+0.037
 late+0.035
 slow+0.034
 very+0.033
Neg logit contributions
lor-0.060
ocket-0.055
ster-0.051
urger-0.051
oll-0.048
Token,
Token ID11
Feature activation-1.88e+00

Pos logit contributions
 different+0.029
 fast+0.027
 very+0.023
 slow+0.022
 really+0.020
Neg logit contributions
lor-0.148
ocket-0.138
urger-0.133
oll-0.127
card-0.125
Token but
Token ID475
Feature activation+2.15e+00

Pos logit contributions
 different+0.037
 fast+0.036
 slow+0.032
 late+0.032
Stop+0.031
Neg logit contributions
lor-0.088
ocket-0.084
urger-0.080
ster-0.075
card-0.075
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
 different+0.012
 fast+0.012
 slow+0.009
 very+0.008
 really+0.007
Neg logit contributions
lor-0.092
ocket-0.087
urger-0.084
oll-0.080
card-0.079
Token
Token ID198
Feature activation-1.13e+00

Pos logit contributions
 different+0.014
 fast+0.014
 slow+0.012
 very+0.012
 hurt+0.010
Neg logit contributions
lor-0.058
ocket-0.052
urger-0.048
card-0.047
oll-0.047
TokenEmily
Token ID48640
Feature activation-1.03e+00

Pos logit contributions
 different+0.025
 fast+0.024
 slow+0.022
 very+0.021
 late+0.020
Neg logit contributions
lor-0.057
ocket-0.051
urger-0.047
card-0.046
ster-0.045
Token happily
Token ID18177
Feature activation-4.47e+00

Pos logit contributions
 different+0.022
 fast+0.021
 slow+0.019
 very+0.019
 really+0.018
Neg logit contributions
lor-0.053
ocket-0.049
urger-0.047
oll-0.044
card-0.044
Token ran
Token ID4966
Feature activation-3.77e-01

Pos logit contributions
 different+0.108
 fast+0.106
 slow+0.099
 very+0.097
 really+0.095
Neg logit contributions
lor-0.226
ocket-0.207
urger-0.196
oll-0.182
anger-0.182
Token over
Token ID625
Feature activation-7.91e+00

Pos logit contributions
 different+0.006
 fast+0.006
 slow+0.005
 late+0.005
Stop+0.005
Neg logit contributions
lor-0.019
ocket-0.018
urger-0.017
card-0.017
anger-0.017
Token start
Token ID923
Feature activation-5.22e+00

Pos logit contributions
 different+0.085
 fast+0.081
 slow+0.069
 late+0.064
 very+0.060
Neg logit contributions
lor-0.464
ocket-0.441
urger-0.416
card-0.404
anger-0.401
Token playing
Token ID2712
Feature activation-1.58e+00

Pos logit contributions
 different+0.073
 fast+0.071
 slow+0.061
 very+0.057
 really+0.053
Neg logit contributions
lor-0.306
ocket-0.286
urger-0.275
card-0.261
oll-0.261
Token with
Token ID351
Feature activation-1.16e+00

Pos logit contributions
 different+0.026
 fast+0.025
 slow+0.022
 very+0.020
 late+0.020
Neg logit contributions
lor-0.087
ocket-0.082
urger-0.078
card-0.074
oll-0.074
Token everyone
Token ID2506
Feature activation-5.06e+00

Pos logit contributions
 different+0.012
 fast+0.012
 slow+0.010
 very+0.009
 really+0.008
Neg logit contributions
lor-0.072
ocket-0.068
urger-0.065
oll-0.062
card-0.062
Token else
Token ID2073
Feature activation-4.18e+00

Pos logit contributions
 different+0.092
 fast+0.092
 slow+0.084
 late+0.079
 very+0.074
Neg logit contributions
lor-0.264
ocket-0.247
urger-0.235
card-0.226
oll-0.226
Token.
Token ID13
Feature activation-4.38e-01

Pos logit contributions
lor+0.127
ocket+0.120
urger+0.115
oll+0.109
card+0.107
Neg logit contributions
 different-0.026
 fast-0.026
 slow-0.021
 very-0.021
 really-0.018
Token
Token ID198
Feature activation-6.18e-01

Pos logit contributions
 different+0.008
 fast+0.008
 slow+0.007
 very+0.007
 really+0.006
Neg logit contributions
lor-0.024
ocket-0.022
urger-0.021
oll-0.020
card-0.020
Token
Token ID198
Feature activation-7.72e-01

Pos logit contributions
 different+0.007
 fast+0.006
 slow+0.005
 very+0.005
 really+0.004
Neg logit contributions
lor-0.038
ocket-0.035
urger-0.034
oll-0.032
card-0.032
TokenTom
Token ID13787
Feature activation-1.71e+00

Pos logit contributions
 different+0.015
 fast+0.014
 slow+0.012
 very+0.012
 really+0.011
Neg logit contributions
lor-0.042
ocket-0.038
urger-0.037
oll-0.035
card-0.035
Token went
Token ID1816
Feature activation-3.24e-02

Pos logit contributions
 different+0.037
 fast+0.036
 slow+0.033
 very+0.032
 really+0.030
Neg logit contributions
lor-0.089
ocket-0.083
urger-0.079
oll-0.075
card-0.074
Token over
Token ID625
Feature activation-7.91e+00

Pos logit contributions
 different+0.000
 fast+0.000
 slow+0.000
 very+0.000
 really+0.000
Neg logit contributions
lor-0.002
ocket-0.002
urger-0.002
oll-0.002
card-0.002
Token and
Token ID290
Feature activation+4.06e-01

Pos logit contributions
 different+0.093
 fast+0.086
 slow+0.075
 very+0.067
 late+0.065
Neg logit contributions
lor-0.451
ocket-0.431
urger-0.409
card-0.391
anger-0.390
Token carefully
Token ID7773
Feature activation-1.78e+00

Pos logit contributions
lor+0.020
ocket+0.019
urger+0.018
card+0.017
ster+0.017
Neg logit contributions
 different-0.009
 fast-0.008
 slow-0.008
 very-0.007
 late-0.007
Token looked
Token ID3114
Feature activation+1.36e+00

Pos logit contributions
 different+0.044
 fast+0.043
 slow+0.040
 very+0.039
 really+0.037
Neg logit contributions
lor-0.090
ocket-0.082
urger-0.079
oll-0.074
card-0.072
Token around
Token ID1088
Feature activation-5.20e+00

Pos logit contributions
lor+0.064
ocket+0.062
urger+0.058
card+0.054
oll+0.054
Neg logit contributions
 different-0.029
 fast-0.029
 slow-0.027
 late-0.025
 very-0.024
Token until
Token ID1566
Feature activation+1.68e+00

Pos logit contributions
 different+0.082
 fast+0.082
 slow+0.075
B+0.068
 late+0.066
Neg logit contributions
lor-0.258
ocket-0.251
urger-0.237
card-0.223
ster-0.223
Token Suddenly
Token ID24975
Feature activation+4.60e-01

Pos logit contributions
 fast+0.007
 different+0.007
 slow+0.006
 very+0.006
 really+0.005
Neg logit contributions
lor-0.022
ocket-0.021
urger-0.020
card-0.019
oll-0.019
Token,
Token ID11
Feature activation-1.59e+00

Pos logit contributions
lor+0.025
ocket+0.024
urger+0.023
oll+0.021
card+0.021
Neg logit contributions
 different-0.008
 fast-0.008
 slow-0.007
 very-0.007
 really-0.006
Token he
Token ID339
Feature activation+5.75e-01

Pos logit contributions
 different+0.032
 fast+0.031
 slow+0.028
 very+0.027
 really+0.025
Neg logit contributions
lor-0.087
ocket-0.081
urger-0.078
oll-0.073
card-0.073
Token felt
Token ID2936
Feature activation-1.82e+00

Pos logit contributions
lor+0.032
ocket+0.030
urger+0.028
card+0.028
oll+0.027
Neg logit contributions
 different-0.010
 fast-0.010
 slow-0.009
 very-0.009
 really-0.008
Token a
Token ID257
Feature activation-6.34e-01

Pos logit contributions
 fast+0.031
 different+0.030
 slow+0.027
B+0.026
Stop+0.025
Neg logit contributions
lor-0.092
ocket-0.090
urger-0.083
oll-0.081
ster-0.078
Token gust
Token ID35253
Feature activation-7.90e+00

Pos logit contributions
 different+0.013
 fast+0.012
 late+0.012
 slow+0.011
B+0.010
Neg logit contributions
lor-0.030
ocket-0.029
urger-0.028
ster-0.026
oll-0.026
Token of
Token ID286
Feature activation-7.75e-01

Pos logit contributions
 different+0.216
 fast+0.210
 slow+0.196
 very+0.187
 really+0.182
Neg logit contributions
lor-0.356
ocket-0.329
urger-0.308
oll-0.296
card-0.291
Token wind
Token ID2344
Feature activation-4.01e+00

Pos logit contributions
 different+0.014
 fast+0.013
 slow+0.012
 really+0.011
 very+0.011
Neg logit contributions
lor-0.037
ocket-0.037
urger-0.035
oll-0.034
card-0.033
Token!
Token ID0
Feature activation-1.01e+00

Pos logit contributions
 different+0.090
 fast+0.089
 slow+0.081
 very+0.079
 really+0.075
Neg logit contributions
lor-0.203
ocket-0.188
urger-0.179
oll-0.168
card-0.167
Token He
Token ID679
Feature activation+1.03e+00

Pos logit contributions
 different+0.020
 fast+0.019
 slow+0.017
 very+0.017
 really+0.015
Neg logit contributions
lor-0.054
ocket-0.048
urger-0.046
oll-0.045
anger-0.044
Token was
Token ID373
Feature activation-5.20e-01

Pos logit contributions
lor+0.049
ocket+0.046
urger+0.044
oll+0.041
ster+0.041
Neg logit contributions
 different-0.024
 fast-0.023
 slow-0.021
 late-0.021
 very-0.020
Token the
Token ID262
Feature activation+2.22e-02

Pos logit contributions
 different+0.004
 fast+0.004
 slow+0.004
 very+0.004
 really+0.004
Neg logit contributions
lor-0.014
ocket-0.013
urger-0.012
oll-0.012
anger-0.011
Token angel
Token ID18304
Feature activation-2.09e+00

Pos logit contributions
lor+0.001
ocket+0.001
urger+0.001
card+0.001
oll+0.001
Neg logit contributions
 different-0.001
 fast-0.001
 slow-0.001
 late-0.001
 really-0.001
Token felt
Token ID2936
Feature activation-1.81e+00

Pos logit contributions
 different+0.048
 fast+0.047
 slow+0.043
 very+0.042
 really+0.041
Neg logit contributions
lor-0.108
ocket-0.099
urger-0.095
oll-0.091
card-0.088
Token a
Token ID257
Feature activation-5.91e-01

Pos logit contributions
 fast+0.028
 different+0.027
 slow+0.024
B+0.023
Stop+0.022
Neg logit contributions
lor-0.093
ocket-0.091
urger-0.082
oll-0.082
bridge-0.078
Token great
Token ID1049
Feature activation-3.14e+00

Pos logit contributions
 different+0.012
 fast+0.012
 late+0.012
 slow+0.010
B+0.010
Neg logit contributions
lor-0.027
ocket-0.026
urger-0.024
ster-0.023
oll-0.023
Token gust
Token ID35253
Feature activation-7.90e+00

Pos logit contributions
 different+0.079
 fast+0.079
 slow+0.072
 very+0.069
 late+0.068
Neg logit contributions
lor-0.144
ocket-0.133
urger-0.126
oll-0.119
anger-0.117
Token of
Token ID286
Feature activation-9.40e-01

Pos logit contributions
 different+0.220
 fast+0.213
 slow+0.201
 very+0.191
 really+0.186
Neg logit contributions
lor-0.353
ocket-0.326
urger-0.301
oll-0.293
card-0.288
Token wind
Token ID2344
Feature activation-3.96e+00

Pos logit contributions
 different+0.017
 fast+0.016
 really+0.014
 very+0.014
 slow+0.014
Neg logit contributions
lor-0.045
ocket-0.045
urger-0.041
oll-0.041
card-0.039
Token and
Token ID290
Feature activation+1.16e+00

Pos logit contributions
 different+0.086
 fast+0.085
 slow+0.077
 very+0.075
 really+0.071
Neg logit contributions
lor-0.204
ocket-0.189
urger-0.180
oll-0.170
card-0.168
Token her
Token ID607
Feature activation+1.99e+00

Pos logit contributions
lor+0.064
ocket+0.059
urger+0.057
oll+0.054
card+0.054
Neg logit contributions
 different-0.020
 fast-0.020
 slow-0.018
 very-0.017
 really-0.016
Token wings
Token ID12098
Feature activation-3.69e-02

Pos logit contributions
lor+0.081
ocket+0.073
urger+0.069
oll+0.064
card+0.063
Neg logit contributions
 different-0.065
 fast-0.064
 slow-0.060
 very-0.059
 really-0.057
Token
Token ID198
Feature activation-5.13e-01

Pos logit contributions
 different+0.006
 fast+0.006
 slow+0.005
 very+0.005
 late+0.005
Neg logit contributions
lor-0.027
ocket-0.024
urger-0.023
anger-0.022
card-0.022
TokenMar
Token ID7676
Feature activation+1.51e+00

Pos logit contributions
 different+0.010
 fast+0.010
 slow+0.009
 very+0.008
 late+0.008
Neg logit contributions
lor-0.028
ocket-0.025
urger-0.024
card-0.023
oll-0.023
Tokenina
Token ID1437
Feature activation+1.20e+00

Pos logit contributions
lor+0.050
ocket+0.045
urger+0.043
oll+0.040
bridge+0.038
Neg logit contributions
 different-0.059
 fast-0.059
 slow-0.056
 very-0.055
 really-0.053
Token's
Token ID338
Feature activation+2.39e+00

Pos logit contributions
lor+0.065
ocket+0.061
urger+0.058
oll+0.055
card+0.055
Neg logit contributions
 fast-0.023
 different-0.023
 slow-0.021
 very-0.021
 really-0.020
Token mom
Token ID1995
Feature activation-9.47e-01

Pos logit contributions
lor+0.126
ocket+0.108
urger+0.104
oll+0.097
card+0.096
Neg logit contributions
 fast-0.066
 different-0.061
 very-0.060
 slow-0.060
 hard-0.053
Token said
Token ID531
Feature activation+8.09e+00

Pos logit contributions
 fast+0.018
 different+0.018
 slow+0.016
 very+0.016
 really+0.016
Neg logit contributions
lor-0.052
ocket-0.049
urger-0.046
oll-0.044
anger-0.044
Token,
Token ID11
Feature activation+3.64e-02

Pos logit contributions
lor+0.434
ocket+0.402
urger+0.383
card+0.364
oll+0.364
Neg logit contributions
 different-0.154
 fast-0.150
 slow-0.134
 very-0.125
 late-0.122
Token "
Token ID366
Feature activation-3.51e+00

Pos logit contributions
lor+0.002
ocket+0.002
urger+0.002
card+0.001
oll+0.001
Neg logit contributions
 different-0.001
 fast-0.001
 slow-0.001
 very-0.001
 late-0.001
TokenOh
Token ID5812
Feature activation+3.01e+00

Pos logit contributions
 different+0.065
 fast+0.063
 slow+0.056
 very+0.055
 really+0.050
Neg logit contributions
lor-0.193
ocket-0.174
urger-0.167
card-0.161
oll-0.157
Token,
Token ID11
Feature activation-4.02e-01

Pos logit contributions
lor+0.169
ocket+0.162
urger+0.156
oll+0.146
card+0.146
Neg logit contributions
 different-0.051
 fast-0.049
 very-0.046
 slow-0.043
 really-0.041
Token it
Token ID340
Feature activation-9.90e-01

Pos logit contributions
 different+0.010
 the+0.009
 fast+0.009
 very+0.009
 slow+0.009
Neg logit contributions
lor-0.020
ocket-0.020
urger-0.019
bridge-0.018
oll-0.018
Token rice
Token ID11464
Feature activation+2.63e+00

Pos logit contributions
lor+0.016
ocket+0.014
urger+0.013
oll+0.013
ogo+0.013
Neg logit contributions
 different-0.011
 fast-0.010
 very-0.010
 slow-0.010
 really-0.009
Token.
Token ID13
Feature activation-5.60e-01

Pos logit contributions
lor+0.165
ocket+0.154
urger+0.148
oll+0.140
card+0.140
Neg logit contributions
 different-0.031
 fast-0.030
 very-0.025
 slow-0.024
 really-0.022
Token The
Token ID383
Feature activation+7.60e-01

Pos logit contributions
 different+0.012
 fast+0.012
 slow+0.011
 very+0.010
B+0.010
Neg logit contributions
lor-0.026
ocket-0.024
urger-0.024
anger-0.022
oll-0.022
Token shop
Token ID6128
Feature activation+4.97e-01

Pos logit contributions
lor+0.043
ocket+0.040
urger+0.038
oll+0.036
card+0.036
Neg logit contributions
 different-0.014
 fast-0.014
 slow-0.012
 very-0.012
 really-0.011
Tokenkeeper
Token ID13884
Feature activation-2.50e+00

Pos logit contributions
lor+0.018
ocket+0.016
urger+0.015
oll+0.014
anger+0.013
Neg logit contributions
 different-0.019
 fast-0.018
 slow-0.017
 very-0.017
 really-0.017
Token said
Token ID531
Feature activation+7.55e+00

Pos logit contributions
 different+0.048
 fast+0.046
 slow+0.041
 very+0.041
 really+0.040
Neg logit contributions
lor-0.138
ocket-0.128
urger-0.122
oll-0.116
anger-0.115
Token he
Token ID339
Feature activation+2.55e+00

Pos logit contributions
lor+0.405
ocket+0.376
urger+0.360
oll+0.340
card+0.338
Neg logit contributions
 different-0.147
 fast-0.145
 slow-0.129
 very-0.123
 really-0.118
Token was
Token ID373
Feature activation+3.69e-01

Pos logit contributions
lor+0.145
ocket+0.131
urger+0.125
anger+0.120
card+0.120
Neg logit contributions
 different-0.046
 fast-0.046
 very-0.044
 really-0.043
 slow-0.041
Token too
Token ID1165
Feature activation-4.68e+00

Pos logit contributions
lor+0.021
ocket+0.019
urger+0.018
oll+0.017
card+0.017
Neg logit contributions
 different-0.006
 fast-0.006
 slow-0.005
 very-0.005
 really-0.005
Token young
Token ID1862
Feature activation-3.66e+00

Pos logit contributions
Stop+0.080
B+0.080
 different+0.079
 fast+0.070
 opposite+0.069
Neg logit contributions
lor-0.220
ocket-0.214
urger-0.212
ster-0.197
oll-0.196
Token and
Token ID290
Feature activation+1.18e+00

Pos logit contributions
 different+0.037
 fast+0.036
 slow+0.029
 very+0.026
 really+0.023
Neg logit contributions
lor-0.230
ocket-0.216
urger-0.208
oll-0.198
card-0.198
Token.
Token ID13
Feature activation+6.05e-01

Pos logit contributions
lor+0.033
ocket+0.031
urger+0.030
card+0.029
oll+0.027
Neg logit contributions
 different-0.005
 fast-0.004
 very-0.004
 slow-0.003
 really-0.003
Token But
Token ID887
Feature activation+2.03e+00

Pos logit contributions
lor+0.031
ocket+0.029
oll+0.027
urger+0.026
ster+0.025
Neg logit contributions
 different-0.012
 fast-0.012
 slow-0.011
 very-0.010
 really-0.010
Token he
Token ID339
Feature activation+1.55e+00

Pos logit contributions
lor+0.107
ocket+0.096
urger+0.094
card+0.088
anger+0.087
Neg logit contributions
 different-0.047
 fast-0.046
 very-0.042
 slow-0.042
 really-0.039
Token did
Token ID750
Feature activation+2.44e+00

Pos logit contributions
lor+0.081
ocket+0.076
urger+0.072
oll+0.068
card+0.068
Neg logit contributions
 different-0.031
 fast-0.031
 slow-0.027
 very-0.026
 late-0.025
Token not
Token ID407
Feature activation-1.25e+00

Pos logit contributions
lor+0.126
ocket+0.115
urger+0.110
card+0.104
oll+0.103
Neg logit contributions
 different-0.058
 fast-0.057
 slow-0.052
 very-0.051
 really-0.048
Token say
Token ID910
Feature activation+8.35e+00

Pos logit contributions
 fast+0.029
 different+0.029
 slow+0.025
 late+0.025
 very+0.025
Neg logit contributions
lor-0.057
ocket-0.056
urger-0.053
oll-0.050
ster-0.048
Token anything
Token ID1997
Feature activation-3.92e-01

Pos logit contributions
lor+0.401
ocket+0.367
urger+0.352
card+0.327
oll+0.323
Neg logit contributions
 different-0.227
 fast-0.220
 slow-0.203
 very-0.202
 really-0.188
Token.
Token ID13
Feature activation+7.63e-01

Pos logit contributions
 fast+0.007
 different+0.007
 slow+0.006
 late+0.006
 panic+0.006
Neg logit contributions
lor-0.020
ocket-0.019
oll-0.018
urger-0.017
ster-0.017
Token He
Token ID679
Feature activation+2.13e+00

Pos logit contributions
lor+0.040
ocket+0.037
oll+0.035
urger+0.035
ster+0.033
Neg logit contributions
 different-0.014
 fast-0.014
 slow-0.012
 very-0.012
 really-0.011
Token ate
Token ID15063
Feature activation+2.99e+00

Pos logit contributions
lor+0.114
ocket+0.104
urger+0.100
card+0.095
anger+0.094
Neg logit contributions
 different-0.044
 fast-0.043
 slow-0.039
 very-0.038
 really-0.037
Token his
Token ID465
Feature activation+2.92e+00

Pos logit contributions
lor+0.163
ocket+0.155
urger+0.147
oll+0.142
ster+0.138
Neg logit contributions
 different-0.046
 fast-0.046
 slow-0.041
 late-0.037
 very-0.036
Token song
Token ID3496
Feature activation+9.54e-01

Pos logit contributions
lor+0.003
ocket+0.002
urger+0.002
oll+0.002
ogo+0.002
Neg logit contributions
 fast-0.001
 different-0.001
 slow-0.001
 very-0.001
 fun-0.001
Token was
Token ID373
Feature activation-4.69e-01

Pos logit contributions
lor+0.047
ocket+0.043
urger+0.041
card+0.039
oll+0.039
Neg logit contributions
 different-0.021
 fast-0.021
 slow-0.019
 very-0.018
 late-0.018
Token over
Token ID625
Feature activation-7.02e+00

Pos logit contributions
 different+0.008
 fast+0.008
B+0.008
 slow+0.007
Stop+0.007
Neg logit contributions
lor-0.022
ocket-0.020
urger-0.020
card-0.020
icking-0.019
Token,
Token ID11
Feature activation-1.68e+00

Pos logit contributions
 different+0.140
 fast+0.139
 slow+0.124
 very+0.119
 really+0.114
Neg logit contributions
lor-0.345
ocket-0.320
urger-0.309
anger-0.292
ster-0.291
Token Bobby
Token ID17155
Feature activation-1.38e+00

Pos logit contributions
 different+0.027
 fast+0.026
 slow+0.023
 very+0.021
 really+0.020
Neg logit contributions
lor-0.095
ocket-0.089
urger-0.085
oll-0.081
card-0.080
Token said
Token ID531
Feature activation+7.35e+00

Pos logit contributions
 different+0.031
 fast+0.030
 slow+0.027
 very+0.026
 late+0.026
Neg logit contributions
lor-0.069
ocket-0.063
urger-0.061
oll-0.057
card-0.057
Token,
Token ID11
Feature activation-4.91e-01

Pos logit contributions
lor+0.385
ocket+0.356
urger+0.341
card+0.322
oll+0.322
Neg logit contributions
 different-0.147
 fast-0.143
 slow-0.128
 late-0.120
 very-0.120
Token "
Token ID366
Feature activation-3.91e+00

Pos logit contributions
 different+0.010
 fast+0.010
 slow+0.009
 very+0.009
 really+0.009
Neg logit contributions
lor-0.025
ocket-0.023
urger-0.022
oll-0.021
card-0.021
TokenMom
Token ID29252
Feature activation-7.16e-01

Pos logit contributions
 different+0.068
 fast+0.067
 slow+0.058
 very+0.056
 really+0.052
Neg logit contributions
lor-0.219
ocket-0.202
urger-0.195
card-0.184
oll-0.184
Tokenmy
Token ID1820
Feature activation-6.81e-01

Pos logit contributions
 different+0.012
 fast+0.011
 slow+0.010
 very+0.010
 really+0.010
Neg logit contributions
lor-0.042
ocket-0.040
urger-0.036
oll-0.035
anger-0.035
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
 different+0.009
 fast+0.009
 slow+0.008
 very+0.008
 really+0.007
Neg logit contributions
lor-0.042
ocket-0.039
urger-0.037
oll-0.035
card-0.035
Token
Token ID198
Feature activation-3.64e-01

Pos logit contributions
 different+0.004
 fast+0.004
 very+0.003
 slow+0.003
 late+0.003
Neg logit contributions
lor-0.019
ocket-0.017
urger-0.016
oll-0.016
anger-0.015
TokenDanny
Token ID45478
Feature activation-6.41e-01

Pos logit contributions
 different+0.009
 fast+0.009
 very+0.008
 slow+0.008
 really+0.007
Neg logit contributions
lor-0.017
ocket-0.015
urger-0.015
oll-0.014
ster-0.013
Token was
Token ID373
Feature activation+1.50e-01

Pos logit contributions
 different+0.014
 fast+0.014
 late+0.013
 slow+0.013
 very+0.012
Neg logit contributions
lor-0.031
ocket-0.029
urger-0.028
ster-0.026
oll-0.026
Token surprised
Token ID6655
Feature activation-2.18e+00

Pos logit contributions
lor+0.007
ocket+0.007
urger+0.007
card+0.006
oll+0.006
Neg logit contributions
 different-0.002
B-0.002
 fast-0.002
Stop-0.002
 late-0.002
Token and
Token ID290
Feature activation+1.75e+00

Pos logit contributions
 fast+0.036
 different+0.036
 slow+0.032
 very+0.029
 late+0.028
Neg logit contributions
lor-0.118
ocket-0.110
urger-0.107
oll-0.101
ster-0.100
Token said
Token ID531
Feature activation+7.82e+00

Pos logit contributions
lor+0.080
ocket+0.076
urger+0.072
ster+0.069
card+0.068
Neg logit contributions
 different-0.038
 fast-0.036
 slow-0.033
 late-0.032
 very-0.031
Token
Token ID6184
Feature activation+3.42e+00

Pos logit contributions
lor+0.393
ocket+0.364
urger+0.344
ster+0.334
card+0.329
Neg logit contributions
 different-0.157
 fast-0.152
 late-0.138
 slow-0.138
 busy-0.124
Token
Token ID95
Feature activation+1.92e+00

Pos logit contributions
lor+0.127
ocket+0.115
urger+0.107
oll+0.098
ster+0.097
Neg logit contributions
 different-0.123
 fast-0.119
 slow-0.112
 very-0.111
 late-0.108
Token
Token ID26391
Feature activation+3.49e-01

Pos logit contributions
lor+0.077
ocket+0.069
urger+0.065
card+0.060
oll+0.059
Neg logit contributions
 different-0.065
 fast-0.063
 slow-0.058
 very-0.058
 really-0.055
Token
Token ID129
Feature activation+1.33e+00

Pos logit contributions
lor+0.016
ocket+0.015
urger+0.014
oll+0.013
card+0.013
Neg logit contributions
 fast-0.010
 different-0.009
 slow-0.009
 very-0.009
 really-0.008
Token
Token ID241
Feature activation-3.04e+00

Pos logit contributions
lor+0.055
ocket+0.050
urger+0.048
card+0.044
oll+0.043
Neg logit contributions
 different-0.041
 fast-0.040
 slow-0.037
 very-0.036
 late-0.036
Token she
Token ID673
Feature activation+1.29e+00

Pos logit contributions
lor+0.109
ocket+0.101
urger+0.098
oll+0.092
card+0.092
Neg logit contributions
 different-0.035
 fast-0.035
 slow-0.031
 very-0.030
 really-0.028
Token decided
Token ID3066
Feature activation+4.78e+00

Pos logit contributions
lor+0.060
ocket+0.055
urger+0.052
oll+0.049
ster+0.048
Neg logit contributions
 different-0.034
 fast-0.033
 slow-0.030
 very-0.029
 late-0.028
Token to
Token ID284
Feature activation+9.91e-01

Pos logit contributions
lor+0.296
ocket+0.275
urger+0.265
card+0.252
oll+0.251
Neg logit contributions
 different-0.048
 fast-0.046
 slow-0.036
 very-0.031
 late-0.029
Token take
Token ID1011
Feature activation+2.51e+00

Pos logit contributions
lor+0.047
ocket+0.044
urger+0.042
card+0.040
oll+0.039
Neg logit contributions
 different-0.026
 fast-0.026
 slow-0.025
 very-0.024
 really-0.023
Token a
Token ID257
Feature activation+7.31e-01

Pos logit contributions
lor+0.134
ocket+0.125
urger+0.116
oll+0.116
anger+0.108
Neg logit contributions
 different-0.043
 fast-0.041
 slow-0.037
 late-0.033
 competitive-0.032
Token nap
Token ID25422
Feature activation+2.60e+00

Pos logit contributions
lor+0.034
ocket+0.031
urger+0.030
card+0.028
oll+0.028
Neg logit contributions
 different-0.021
 fast-0.021
 slow-0.019
 very-0.019
 really-0.018
Token.
Token ID13
Feature activation-1.41e-01

Pos logit contributions
lor+0.155
ocket+0.146
urger+0.142
card+0.134
oll+0.132
Neg logit contributions
 fast-0.036
 different-0.036
 very-0.031
 slow-0.030
 really-0.027
Token She
Token ID1375
Feature activation+1.70e+00

Pos logit contributions
 fast+0.003
 different+0.003
 slow+0.003
 competitive+0.003
 late+0.003
Neg logit contributions
lor-0.007
ocket-0.006
urger-0.006
anger-0.006
oll-0.006
Token found
Token ID1043
Feature activation+1.94e+00

Pos logit contributions
lor+0.080
ocket+0.073
urger+0.069
card+0.066
anger+0.065
Neg logit contributions
 different-0.046
 fast-0.045
 slow-0.042
 very-0.042
 really-0.041
Token a
Token ID257
Feature activation+1.67e+00

Pos logit contributions
lor+0.111
ocket+0.104
urger+0.099
oll+0.096
card+0.094
Neg logit contributions
 different-0.028
 fast-0.028
 slow-0.025
 very-0.022
 really-0.021
Token cozy
Token ID37438
Feature activation+1.66e+00

Pos logit contributions
lor+0.083
ocket+0.077
urger+0.074
oll+0.069
ster+0.069
Neg logit contributions
 different-0.035
 fast-0.034
 slow-0.031
 late-0.030
 very-0.029
Token
Token ID198
Feature activation-5.40e-01

Pos logit contributions
 different+0.009
 fast+0.009
 slow+0.008
 late+0.008
 competitive+0.007
Neg logit contributions
lor-0.016
ocket-0.014
anger-0.013
urger-0.013
oll-0.013
Token
Token ID198
Feature activation-5.61e-01

Pos logit contributions
 different+0.009
 fast+0.008
 slow+0.008
 very+0.007
 competitive+0.007
Neg logit contributions
lor-0.029
ocket-0.026
oll-0.023
anger-0.023
urger-0.023
TokenSoon
Token ID28093
Feature activation+6.47e-01

Pos logit contributions
 different+0.014
 fast+0.013
 slow+0.011
 very+0.011
 each+0.011
Neg logit contributions
lor-0.026
ocket-0.022
card-0.020
oll-0.020
ster-0.020
Token she
Token ID673
Feature activation+1.05e+00

Pos logit contributions
lor+0.036
ocket+0.033
urger+0.032
oll+0.030
card+0.030
Neg logit contributions
 different-0.011
 fast-0.011
 slow-0.010
 very-0.009
 really-0.009
Token realized
Token ID6939
Feature activation+4.02e+00

Pos logit contributions
lor+0.057
ocket+0.053
urger+0.051
card+0.048
oll+0.048
Neg logit contributions
 different-0.021
 fast-0.020
 slow-0.018
 very-0.018
 really-0.017
Token that
Token ID326
Feature activation+2.70e+00

Pos logit contributions
lor+0.196
ocket+0.180
urger+0.172
oll+0.161
card+0.160
Neg logit contributions
 different-0.099
 fast-0.098
 slow-0.089
 very-0.087
 really-0.084
Token she
Token ID673
Feature activation+1.88e+00

Pos logit contributions
lor+0.143
ocket+0.136
urger+0.125
oll+0.123
card+0.123
Neg logit contributions
 fast-0.043
 different-0.042
 slow-0.037
 really-0.034
 very-0.034
Token would
Token ID561
Feature activation+1.74e+00

Pos logit contributions
lor+0.101
ocket+0.094
urger+0.090
oll+0.085
card+0.085
Neg logit contributions
 different-0.037
 fast-0.036
 slow-0.032
 very-0.031
 really-0.029
Token have
Token ID423
Feature activation-1.34e+00

Pos logit contributions
lor+0.085
ocket+0.078
urger+0.074
oll+0.070
card+0.069
Neg logit contributions
 different-0.042
 fast-0.041
 slow-0.038
 very-0.037
 really-0.035
Token to
Token ID284
Feature activation+1.27e+00

Pos logit contributions
 fast+0.029
 different+0.026
 slow+0.025
 low+0.024
 wildly+0.024
Neg logit contributions
lor-0.063
ocket-0.055
urger-0.053
oll-0.050
icking-0.048
Token suffer
Token ID8659
Feature activation-1.15e+00

Pos logit contributions
lor+0.063
ocket+0.059
urger+0.055
oll+0.053
card+0.052
Neg logit contributions
 different-0.032
 fast-0.031
 slow-0.030
 very-0.028
 really-0.027
Token continued
Token ID3767
Feature activation-2.20e+00

Pos logit contributions
 different+0.001
 fast+0.001
 very+0.001
 slow+0.001
 really+0.001
Neg logit contributions
lor-0.004
ocket-0.004
urger-0.003
anger-0.003
card-0.003
Token their
Token ID511
Feature activation+1.34e+00

Pos logit contributions
 different+0.036
 fast+0.036
Stop+0.032
 slow+0.032
 really+0.030
Neg logit contributions
lor-0.113
ocket-0.104
urger-0.103
card-0.098
oll-0.095
Token walk
Token ID2513
Feature activation+1.33e+00

Pos logit contributions
lor+0.058
ocket+0.053
urger+0.050
oll+0.046
card+0.046
Neg logit contributions
 different-0.041
 fast-0.040
 slow-0.037
 very-0.036
 really-0.035
Token around
Token ID1088
Feature activation-5.83e+00

Pos logit contributions
lor+0.058
card+0.052
ocket+0.052
anger+0.050
urger+0.049
Neg logit contributions
Stop-0.030
Enough-0.027
 different-0.026
 panic-0.024
Acc-0.024
Token the
Token ID262
Feature activation-2.52e-01

Pos logit contributions
Stop+0.106
umpy+0.100
Enough+0.099
Girls+0.096
 late+0.095
Neg logit contributions
ocket-0.228
lor-0.227
glass-0.209
ster-0.208
 suitcase-0.201
Token harbor
Token ID25451
Feature activation+2.30e+00

Pos logit contributions
 different+0.009
 fast+0.009
 slow+0.008
 very+0.008
 really+0.008
Neg logit contributions
lor-0.009
ocket-0.008
urger-0.008
card-0.007
ster-0.007
Token.
Token ID13
Feature activation+2.88e-02

Pos logit contributions
lor+0.131
ocket+0.121
urger+0.117
card+0.112
oll+0.110
Neg logit contributions
 different-0.035
 fast-0.034
 slow-0.029
 very-0.027
 really-0.027
Token<|endoftext|>
Token ID50256
Feature activation+4.62e+00

Pos logit contributions
lor+0.002
ocket+0.002
urger+0.001
oll+0.001
card+0.001
Neg logit contributions
 different-0.000
 fast-0.000
 slow-0.000
 very-0.000
 really-0.000
TokenOnce
Token ID7454
Feature activation+4.62e+00

Pos logit contributions
lor+0.261
ocket+0.235
urger+0.217
oll+0.217
anger+0.213
Neg logit contributions
 different-0.069
 fast-0.065
 slow-0.060
 very-0.052
 competitive-0.051
Token upon
Token ID2402
Feature activation+3.06e+00

Pos logit contributions
lor+0.209
ocket+0.191
urger+0.181
oll+0.169
card+0.168
Neg logit contributions
 different-0.128
 fast-0.126
 slow-0.117
 very-0.114
 really-0.110
Token a
Token ID257
Feature activation+7.00e-01

Pos logit contributions
lor+0.156
ocket+0.147
urger+0.139
oll+0.134
bridge+0.131
Neg logit contributions
 different-0.051
 fast-0.050
 slow-0.047
Stop-0.041
 late-0.039
Token searching
Token ID10342
Feature activation+5.22e+00

Pos logit contributions
 different+0.009
 fast+0.008
 slow+0.008
 very+0.008
 really+0.007
Neg logit contributions
lor-0.012
ocket-0.011
urger-0.011
oll-0.010
card-0.010
Token for
Token ID329
Feature activation+2.39e+00

Pos logit contributions
lor+0.264
ocket+0.248
urger+0.235
oll+0.221
card+0.220
Neg logit contributions
 fast-0.107
 different-0.107
 slow-0.098
 very-0.091
 late-0.088
Token his
Token ID465
Feature activation+4.35e+00

Pos logit contributions
lor+0.128
ocket+0.118
urger+0.114
card+0.108
oll+0.107
Neg logit contributions
 different-0.050
 fast-0.048
 slow-0.043
 very-0.042
 really-0.040
Token favourite
Token ID12507
Feature activation+2.89e+00

Pos logit contributions
lor+0.210
ocket+0.180
urger+0.170
oll+0.163
anger+0.161
Neg logit contributions
 different-0.131
 fast-0.125
 very-0.122
 slow-0.116
 really-0.114
Token snack
Token ID26906
Feature activation+3.31e+00

Pos logit contributions
lor+0.134
ocket+0.121
urger+0.113
oll+0.110
card+0.107
Neg logit contributions
 different-0.087
 fast-0.082
 very-0.078
 slow-0.076
 really-0.074
Token when
Token ID618
Feature activation+3.35e+00

Pos logit contributions
lor+0.202
ocket+0.189
urger+0.182
card+0.173
oll+0.172
Neg logit contributions
 different-0.041
 fast-0.040
 very-0.035
 slow-0.032
 really-0.031
Token he
Token ID339
Feature activation+1.72e+00

Pos logit contributions
lor+0.175
ocket+0.163
urger+0.155
oll+0.147
card+0.146
Neg logit contributions
 different-0.075
 fast-0.074
 very-0.067
 slow-0.066
 really-0.063
Token suddenly
Token ID6451
Feature activation-1.38e+00

Pos logit contributions
lor+0.098
ocket+0.088
urger+0.087
card+0.085
anger+0.085
Neg logit contributions
 different-0.030
 fast-0.028
 really-0.028
 very-0.028
 slow-0.026
Token came
Token ID1625
Feature activation-2.83e-01

Pos logit contributions
 different+0.030
 fast+0.030
 slow+0.027
 very+0.026
 really+0.025
Neg logit contributions
lor-0.071
ocket-0.066
urger-0.063
oll-0.060
card-0.060
Token across
Token ID1973
Feature activation-4.21e+00

Pos logit contributions
 different+0.005
 fast+0.004
 slow+0.004
 very+0.003
 late+0.003
Neg logit contributions
lor-0.016
ocket-0.015
urger-0.014
card-0.013
ster-0.013
Token a
Token ID257
Feature activation+2.85e-01

Pos logit contributions
 different+0.060
 fast+0.059
 slow+0.051
 very+0.047
 really+0.044
Neg logit contributions
lor-0.243
ocket-0.228
urger-0.218
card-0.206
oll-0.206
Token the
Token ID262
Feature activation+7.39e-01

Pos logit contributions
 fast+0.030
 different+0.029
 slow+0.024
 very+0.022
 late+0.022
Neg logit contributions
lor-0.169
ocket-0.162
urger-0.153
card-0.146
oll-0.145
Token mirror
Token ID10162
Feature activation-5.38e-01

Pos logit contributions
lor+0.033
ocket+0.029
urger+0.029
card+0.026
oll+0.026
Neg logit contributions
 different-0.023
 fast-0.022
 slow-0.021
 very-0.021
 really-0.020
Token.
Token ID13
Feature activation-2.24e-01

Pos logit contributions
 different+0.006
 fast+0.006
 very+0.005
 slow+0.004
 really+0.004
Neg logit contributions
lor-0.034
ocket-0.032
urger-0.031
card-0.029
oll-0.029
Token She
Token ID1375
Feature activation+1.21e+00

Pos logit contributions
 different+0.004
 fast+0.004
 slow+0.003
 very+0.003
 competitive+0.003
Neg logit contributions
lor-0.012
ocket-0.010
anger-0.010
card-0.010
oll-0.010
Token thought
Token ID1807
Feature activation+6.44e+00

Pos logit contributions
lor+0.054
ocket+0.053
urger+0.049
ster+0.047
oll+0.047
Neg logit contributions
 late-0.028
 fast-0.027
 different-0.027
 slow-0.024
 busy-0.023
Token she
Token ID673
Feature activation+2.50e+00

Pos logit contributions
lor+0.366
ocket+0.337
urger+0.327
card+0.309
oll+0.304
Neg logit contributions
 different-0.114
 fast-0.112
 slow-0.098
 very-0.094
 really-0.088
Token looked
Token ID3114
Feature activation+2.81e+00

Pos logit contributions
lor+0.123
ocket+0.113
urger+0.108
oll+0.101
card+0.101
Neg logit contributions
 different-0.060
 fast-0.059
 slow-0.054
 very-0.052
 late-0.050
Token very
Token ID845
Feature activation-1.42e+00

Pos logit contributions
ocket+0.142
lor+0.140
urger+0.135
oll+0.126
card+0.125
Neg logit contributions
 fast-0.034
 late-0.032
 different-0.031
 slow-0.030
B-0.030
Token cool
Token ID3608
Feature activation-6.26e-01

Pos logit contributions
Stop+0.023
 opposite+0.023
Da+0.022
 late+0.022
B+0.022
Neg logit contributions
ocket-0.065
lor-0.063
urger-0.060
oll-0.059
ster-0.057
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
 different+0.009
 fast+0.009
 slow+0.008
 very+0.007
 late+0.007
Neg logit contributions
lor-0.036
ocket-0.033
urger-0.032
oll-0.031
card-0.030
Token
Token ID198
Feature activation-4.10e-01

Pos logit contributions
 different+0.005
 fast+0.005
 slow+0.004
 late+0.004
 competitive+0.004
Neg logit contributions
lor-0.014
ocket-0.012
oll-0.012
anger-0.012
urger-0.011
Token His
Token ID2399
Feature activation+3.20e+00

Pos logit contributions
 different+0.017
 fast+0.017
 slow+0.015
 very+0.015
 really+0.014
Neg logit contributions
lor-0.035
ocket-0.032
urger-0.030
oll-0.029
anger-0.028
Token friends
Token ID2460
Feature activation-5.90e-01

Pos logit contributions
lor+0.156
ocket+0.142
urger+0.133
card+0.125
oll+0.124
Neg logit contributions
 different-0.085
 fast-0.084
 slow-0.078
 very-0.076
 really-0.072
Token laughed
Token ID13818
Feature activation+1.02e+00

Pos logit contributions
 different+0.012
 fast+0.012
 slow+0.011
 very+0.010
 late+0.010
Neg logit contributions
lor-0.030
ocket-0.028
urger-0.027
card-0.025
oll-0.025
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
lor+0.057
ocket+0.053
urger+0.051
oll+0.049
card+0.048
Neg logit contributions
 different-0.016
 fast-0.016
 slow-0.014
 very-0.013
 late-0.012
Token cl
Token ID537
Feature activation-9.51e-01

Pos logit contributions
lor+0.075
ocket+0.069
urger+0.066
card+0.062
oll+0.062
Neg logit contributions
 different-0.044
 fast-0.042
 late-0.039
 slow-0.039
 very-0.037
Tokenapped
Token ID6320
Feature activation-1.57e+00

Pos logit contributions
 different+0.041
 fast+0.041
 slow+0.039
 very+0.038
 really+0.037
Neg logit contributions
lor-0.029
ocket-0.025
urger-0.023
oll-0.021
card-0.020
Token,
Token ID11
Feature activation-8.34e-01

Pos logit contributions
 different+0.025
 fast+0.025
 slow+0.022
 late+0.020
 very+0.020
Neg logit contributions
lor-0.083
ocket-0.078
urger-0.077
card-0.071
oll-0.071
Token they
Token ID484
Feature activation-8.83e-02

Pos logit contributions
 different+0.017
 fast+0.016
 slow+0.015
 very+0.014
 really+0.014
Neg logit contributions
lor-0.041
ocket-0.038
urger-0.037
card-0.035
oll-0.034
Token all
Token ID477
Feature activation-4.47e+00

Pos logit contributions
 different+0.002
 fast+0.002
 slow+0.002
 very+0.002
 really+0.002
Neg logit contributions
lor-0.005
ocket-0.004
urger-0.004
oll-0.004
card-0.004
Token thought
Token ID1807
Feature activation+6.86e+00

Pos logit contributions
 fast+0.115
 late+0.114
 different+0.113
 slow+0.105
Stop+0.102
Neg logit contributions
lor-0.165
ocket-0.157
urger-0.150
card-0.148
oll-0.144
Token it
Token ID340
Feature activation+6.44e-01

Pos logit contributions
lor+0.352
ocket+0.327
urger+0.312
oll+0.295
card+0.292
Neg logit contributions
 different-0.147
 fast-0.145
 slow-0.131
 very-0.126
 really-0.121
Token boy
Token ID2933
Feature activation-2.20e+00

Pos logit contributions
lor+0.026
ocket+0.024
urger+0.023
oll+0.021
card+0.021
Neg logit contributions
 different-0.009
 fast-0.009
 slow-0.008
 very-0.008
 really-0.007
Token was
Token ID373
Feature activation-1.30e-01

Pos logit contributions
 fast+0.048
 different+0.048
 slow+0.043
 late+0.042
 very+0.040
Neg logit contributions
lor-0.107
ocket-0.099
urger-0.097
oll-0.091
ster-0.090
Token so
Token ID523
Feature activation-1.25e+00

Pos logit contributions
B+0.002
Stop+0.002
 different+0.002
Da+0.002
Good+0.002
Neg logit contributions
lor-0.006
ocket-0.006
urger-0.006
oll-0.006
card-0.006
Token happy
Token ID3772
Feature activation-1.49e+00

Pos logit contributions
 opposite+0.021
Da+0.021
B+0.020
Stop+0.020
 different+0.019
Neg logit contributions
oll-0.054
lor-0.053
ocket-0.053
urger-0.051
icking-0.050
Token that
Token ID326
Feature activation+1.86e+00

Pos logit contributions
 different+0.025
 fast+0.024
 slow+0.022
 very+0.019
 really+0.018
Neg logit contributions
lor-0.082
ocket-0.076
urger-0.074
oll-0.070
ster-0.069
Token he
Token ID339
Feature activation+1.33e+00

Pos logit contributions
lor+0.088
ocket+0.081
urger+0.077
oll+0.072
card+0.072
Neg logit contributions
 different-0.048
 fast-0.047
 slow-0.044
 very-0.042
 really-0.041
Token forgot
Token ID16453
Feature activation-9.96e-01

Pos logit contributions
lor+0.062
ocket+0.057
urger+0.055
oll+0.051
ster+0.050
Neg logit contributions
 different-0.033
 fast-0.031
 slow-0.029
 late-0.028
 very-0.027
Token to
Token ID284
Feature activation+9.46e-01

Pos logit contributions
 fast+0.020
 different+0.020
 slow+0.019
 late+0.017
B+0.017
Neg logit contributions
lor-0.049
ocket-0.045
urger-0.044
oll-0.041
card-0.040
Token be
Token ID307
Feature activation-1.20e+00

Pos logit contributions
lor+0.047
ocket+0.044
urger+0.042
oll+0.039
card+0.039
Neg logit contributions
 different-0.022
 fast-0.022
 slow-0.020
 very-0.019
 really-0.019
Token careful
Token ID8161
Feature activation+2.74e-01

Pos logit contributions
 different+0.023
Stop+0.023
 fast+0.022
 opposite+0.021
B+0.021
Neg logit contributions
lor-0.051
ocket-0.049
urger-0.049
card-0.048
oll-0.046
Token.
Token ID13
Feature activation-2.70e-01

Pos logit contributions
lor+0.016
ocket+0.015
urger+0.014
oll+0.014
card+0.014
Neg logit contributions
 different-0.004
 fast-0.004
 slow-0.003
 very-0.003
 really-0.003
TokenTom
Token ID13787
Feature activation-4.76e-01

Pos logit contributions
lor+0.218
ocket+0.196
urger+0.178
oll+0.177
anger+0.174
Neg logit contributions
 different-0.111
 fast-0.108
 slow-0.101
 very-0.095
 really-0.092
Tokenmy
Token ID1820
Feature activation-7.73e-01

Pos logit contributions
 different+0.010
 fast+0.010
 slow+0.008
 very+0.008
 late+0.008
Neg logit contributions
lor-0.024
ocket-0.023
urger-0.022
oll-0.021
ster-0.020
Token was
Token ID373
Feature activation-7.53e-01

Pos logit contributions
 different+0.015
 fast+0.015
 slow+0.013
 very+0.013
 really+0.012
Neg logit contributions
lor-0.042
ocket-0.039
urger-0.037
card-0.035
oll-0.035
Token a
Token ID257
Feature activation-5.04e-01

Pos logit contributions
 different+0.014
 fast+0.014
 very+0.012
 slow+0.012
 really+0.011
Neg logit contributions
lor-0.043
ocket-0.039
urger-0.038
card-0.035
anger-0.035
Token big
Token ID1263
Feature activation-1.76e+00

Pos logit contributions
 different+0.009
 fast+0.009
 late+0.009
Stop+0.009
B+0.008
Neg logit contributions
lor-0.022
ocket-0.022
urger-0.021
ster-0.021
oll-0.020
Token boy
Token ID2933
Feature activation-9.94e-01

Pos logit contributions
 different+0.041
 fast+0.040
 slow+0.036
 late+0.036
B+0.035
Neg logit contributions
lor-0.077
ocket-0.075
urger-0.072
ster-0.068
oll-0.068
Token who
Token ID508
Feature activation+1.70e+00

Pos logit contributions
 different+0.017
 fast+0.016
 slow+0.014
 late+0.013
 very+0.012
Neg logit contributions
lor-0.053
ocket-0.050
urger-0.048
oll-0.046
card-0.046
Token liked
Token ID8288
Feature activation-1.97e-01

Pos logit contributions
lor+0.089
ocket+0.085
urger+0.080
oll+0.079
ster+0.075
Neg logit contributions
 different-0.028
 fast-0.028
 slow-0.024
 late-0.023
 very-0.022
Token to
Token ID284
Feature activation-2.98e-01

Pos logit contributions
 fast+0.002
 different+0.002
 slow+0.002
 late+0.002
 really+0.002
Neg logit contributions
lor-0.011
ocket-0.010
urger-0.010
card-0.009
oll-0.009
Token play
Token ID711
Feature activation-5.25e-04

Pos logit contributions
 different+0.007
 fast+0.007
 slow+0.006
 very+0.006
 really+0.006
Neg logit contributions
lor-0.015
ocket-0.014
urger-0.013
oll-0.012
card-0.012
Token with
Token ID351
Feature activation-5.44e-01

Pos logit contributions
 fast+0.000
 different+0.000
 slow+0.000
 late+0.000
 very+0.000
Neg logit contributions
lor-0.000
ocket-0.000
urger-0.000
oll-0.000
anger-0.000
Token your
Token ID534
Feature activation+1.37e+00

Pos logit contributions
 different+0.006
 fast+0.006
 slow+0.005
 very+0.005
 really+0.005
Neg logit contributions
lor-0.014
ocket-0.013
urger-0.012
oll-0.012
card-0.012
Token daddy
Token ID35822
Feature activation+2.30e-01

Pos logit contributions
lor+0.066
ocket+0.059
urger+0.055
oll+0.053
card+0.053
Neg logit contributions
 different-0.038
 fast-0.038
 slow-0.035
 very-0.034
 really-0.032
Token's
Token ID338
Feature activation+2.09e+00

Pos logit contributions
lor+0.013
ocket+0.012
urger+0.012
oll+0.011
anger+0.011
Neg logit contributions
 different-0.003
 fast-0.003
 slow-0.003
 very-0.003
 really-0.003
Token birthday
Token ID10955
Feature activation+4.85e+00

Pos logit contributions
lor+0.100
ocket+0.088
urger+0.082
oll+0.081
anger+0.079
Neg logit contributions
 different-0.060
 fast-0.059
 very-0.055
 slow-0.055
 really-0.051
Token!"
Token ID2474
Feature activation-3.14e+00

Pos logit contributions
lor+0.276
ocket+0.260
urger+0.247
oll+0.236
card+0.234
Neg logit contributions
 different-0.079
 fast-0.077
 very-0.067
 slow-0.067
 really-0.062
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
 different+0.038
 fast+0.036
 slow+0.030
 very+0.027
 really+0.025
Neg logit contributions
lor-0.192
ocket-0.180
urger-0.173
oll-0.165
card-0.164
Token
Token ID198
Feature activation-1.22e+00

Pos logit contributions
 different+0.016
 fast+0.015
 slow+0.012
 very+0.011
 really+0.010
Neg logit contributions
lor-0.083
ocket-0.077
urger-0.074
oll-0.071
card-0.070
TokenM
Token ID44
Feature activation-3.41e-01

Pos logit contributions
 different+0.022
 fast+0.022
 slow+0.019
 very+0.018
 really+0.017
Neg logit contributions
lor-0.068
ocket-0.062
urger-0.059
oll-0.056
card-0.056
Tokenandy
Token ID10757
Feature activation-9.69e-01

Pos logit contributions
 different+0.013
 fast+0.012
 really+0.012
 very+0.012
 slow+0.012
Neg logit contributions
lor-0.012
ocket-0.011
urger-0.010
card-0.010
 suitcase-0.009
Token felt
Token ID2936
Feature activation-1.85e+00

Pos logit contributions
 different+0.020
 fast+0.020
 slow+0.018
 very+0.017
 really+0.017
Neg logit contributions
lor-0.051
ocket-0.048
urger-0.046
oll-0.043
card-0.043
Token much
Token ID881
Feature activation-5.31e+00

Pos logit contributions
 different+0.030
 fast+0.030
 slow+0.026
Stop+0.024
B+0.024
Neg logit contributions
lor-0.096
ocket-0.092
oll-0.083
urger-0.082
card-0.080
Token Daisy
Token ID40355
Feature activation+4.70e-01

Pos logit contributions
lor+0.213
ocket+0.204
urger+0.188
oll+0.184
card+0.180
Neg logit contributions
 different-0.064
 fast-0.064
 slow-0.057
 very-0.052
 late-0.052
Token.
Token ID13
Feature activation-6.01e-01

Pos logit contributions
lor+0.024
ocket+0.023
urger+0.022
ster+0.021
oll+0.021
Neg logit contributions
 fast-0.008
 different-0.008
 slow-0.007
 late-0.007
Stop-0.007
Token Daisy
Token ID40355
Feature activation-8.16e-01

Pos logit contributions
 different+0.014
 fast+0.014
 slow+0.012
 very+0.012
 late+0.011
Neg logit contributions
lor-0.028
ocket-0.026
oll-0.023
urger-0.023
ster-0.022
Token lived
Token ID5615
Feature activation+1.18e+00

Pos logit contributions
 fast+0.018
 different+0.018
 late+0.017
 slow+0.016
 opposite+0.016
Neg logit contributions
lor-0.037
ocket-0.035
urger-0.032
oll-0.031
ster-0.031
Token in
Token ID287
Feature activation-4.74e+00

Pos logit contributions
lor+0.055
ocket+0.053
ster+0.049
oll+0.048
card+0.047
Neg logit contributions
 different-0.024
 fast-0.021
Stop-0.021
 slow-0.021
 opposite-0.020
Token a
Token ID257
Feature activation-4.00e-01

Pos logit contributions
 different+0.061
 fast+0.060
 slow+0.051
 very+0.047
 really+0.044
Neg logit contributions
lor-0.279
ocket-0.263
urger-0.249
oll-0.239
card-0.238
Token very
Token ID845
Feature activation-3.49e+00

Pos logit contributions
Stop+0.006
 fast+0.006
 wildly+0.006
 late+0.006
 different+0.006
Neg logit contributions
lor-0.019
ocket-0.018
ster-0.018
 suitcase-0.017
urger-0.016
Token colorful
Token ID20239
Feature activation-5.58e-01

Pos logit contributions
 different+0.050
 fast+0.047
Stop+0.047
B+0.044
 each+0.044
Neg logit contributions
ocket-0.175
lor-0.175
urger-0.162
ster-0.159
oll-0.158
Token room
Token ID2119
Feature activation+6.91e-01

Pos logit contributions
 different+0.017
 fast+0.017
 slow+0.016
 very+0.016
 really+0.015
Neg logit contributions
lor-0.023
ocket-0.021
urger-0.020
oll-0.018
card-0.018
Token.
Token ID13
Feature activation-7.82e-01

Pos logit contributions
lor+0.042
ocket+0.040
urger+0.039
oll+0.036
anger+0.036
Neg logit contributions
 different-0.009
 fast-0.009
 very-0.007
 slow-0.007
 really-0.006
Token One
Token ID1881
Feature activation+9.44e-01

Pos logit contributions
 fast+0.016
 different+0.016
 slow+0.014
 very+0.014
 late+0.013
Neg logit contributions
lor-0.038
ocket-0.036
oll-0.032
urger-0.031
anger-0.031
Token into
Token ID656
Feature activation-2.08e+00

Pos logit contributions
 different+0.035
 fast+0.033
 slow+0.030
 very+0.026
 really+0.026
Neg logit contributions
lor-0.102
ocket-0.099
urger-0.096
oll-0.091
card-0.089
Token trouble
Token ID5876
Feature activation-9.68e-01

Pos logit contributions
 fast+0.044
 different+0.043
 slow+0.041
B+0.039
 really+0.038
Neg logit contributions
lor-0.094
ocket-0.090
urger-0.085
oll-0.079
 suitcase-0.078
Token.
Token ID13
Feature activation-2.59e-01

Pos logit contributions
 different+0.014
 fast+0.014
 slow+0.012
 very+0.010
 really+0.010
Neg logit contributions
lor-0.055
ocket-0.052
urger-0.050
oll-0.047
card-0.047
Token He
Token ID679
Feature activation+1.63e+00

Pos logit contributions
 fast+0.006
 different+0.005
 slow+0.005
 very+0.005
 busy+0.004
Neg logit contributions
lor-0.013
ocket-0.011
urger-0.011
oll-0.011
anger-0.010
Token went
Token ID1816
Feature activation+6.60e-01

Pos logit contributions
lor+0.070
ocket+0.067
urger+0.064
oll+0.062
ster+0.058
Neg logit contributions
 fast-0.038
 different-0.038
 late-0.036
 slow-0.033
 busy-0.030
Token outside
Token ID2354
Feature activation-5.08e+00

Pos logit contributions
lor+0.036
ocket+0.034
urger+0.032
card+0.031
anger+0.031
Neg logit contributions
 different-0.009
 fast-0.008
Stop-0.007
 slow-0.007
B-0.007
Token to
Token ID284
Feature activation-6.48e-01

Pos logit contributions
Stop+0.093
B+0.087
 different+0.087
 fast+0.085
Blue+0.080
Neg logit contributions
lor-0.221
ocket-0.209
urger-0.200
ster-0.197
card-0.195
Token play
Token ID711
Feature activation+3.73e-01

Pos logit contributions
 fast+0.016
 different+0.015
 late+0.015
B+0.015
 very+0.014
Neg logit contributions
lor-0.026
ocket-0.025
urger-0.024
card-0.022
 suitcase-0.021
Token and
Token ID290
Feature activation+1.09e+00

Pos logit contributions
lor+0.018
ocket+0.017
urger+0.015
oll+0.015
anger+0.015
Neg logit contributions
 different-0.007
 fast-0.007
 slow-0.006
 late-0.006
 panic-0.006
Token saw
Token ID2497
Feature activation+1.80e+00

Pos logit contributions
lor+0.042
ocket+0.042
urger+0.040
card+0.037
ster+0.036
Neg logit contributions
 different-0.026
 fast-0.026
 late-0.025
B-0.025
 slow-0.023
Token a
Token ID257
Feature activation+8.23e-01

Pos logit contributions
lor+0.089
ocket+0.083
urger+0.080
oll+0.078
ster+0.076
Neg logit contributions
 fast-0.032
 different-0.030
 slow-0.030
 late-0.027
 really-0.026
Token hug
Token ID16225
Feature activation+1.27e+00

Pos logit contributions
 fast+0.020
 different+0.020
 slow+0.019
 very+0.018
 really+0.017
Neg logit contributions
lor-0.042
ocket-0.038
urger-0.036
oll-0.034
card-0.034
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
lor+0.083
ocket+0.079
urger+0.077
oll+0.072
 Majesty+0.071
Neg logit contributions
 fast-0.010
 different-0.009
 very-0.009
 slow-0.006
 really-0.006
Token Then
Token ID3244
Feature activation-1.21e-01

Pos logit contributions
 different+0.003
 fast+0.003
 slow+0.002
 very+0.002
 really+0.002
Neg logit contributions
lor-0.008
ocket-0.008
urger-0.007
oll-0.007
card-0.007
Token she
Token ID673
Feature activation+1.86e-01

Pos logit contributions
 different+0.002
 fast+0.002
 very+0.001
 slow+0.001
 the+0.001
Neg logit contributions
lor-0.007
ocket-0.007
urger-0.007
oll-0.006
card-0.006
Token got
Token ID1392
Feature activation-2.17e+00

Pos logit contributions
lor+0.010
ocket+0.009
urger+0.009
anger+0.009
card+0.008
Neg logit contributions
 fast-0.004
 different-0.004
 really-0.004
 slow-0.004
 very-0.004
Token back
Token ID736
Feature activation-5.40e+00

Pos logit contributions
 different+0.041
 fast+0.041
 very+0.036
 slow+0.036
 really+0.034
Neg logit contributions
lor-0.123
ocket-0.113
urger-0.109
anger-0.102
oll-0.102
Token on
Token ID319
Feature activation-2.95e+00

Pos logit contributions
 different+0.094
 fast+0.091
 slow+0.080
 very+0.076
 really+0.072
Neg logit contributions
lor-0.300
ocket-0.280
urger-0.268
oll-0.255
card-0.254
Token her
Token ID607
Feature activation+9.39e-01

Pos logit contributions
 different+0.030
 fast+0.028
 slow+0.023
 very+0.020
 really+0.019
Neg logit contributions
lor-0.182
ocket-0.172
urger-0.164
card-0.157
oll-0.156
Token seat
Token ID5852
Feature activation+3.09e-01

Pos logit contributions
lor+0.040
ocket+0.036
urger+0.034
oll+0.032
card+0.031
Neg logit contributions
 different-0.030
 fast-0.030
 slow-0.028
 very-0.027
 really-0.026
Token and
Token ID290
Feature activation+1.15e+00

Pos logit contributions
lor+0.019
ocket+0.018
urger+0.018
oll+0.016
ster+0.016
Neg logit contributions
 fast-0.004
 different-0.003
 very-0.003
 slow-0.003
 really-0.003
Token continued
Token ID3767
Feature activation-2.85e+00

Pos logit contributions
lor+0.063
ocket+0.059
urger+0.056
anger+0.053
oll+0.052
Neg logit contributions
 fast-0.025
 different-0.023
 slow-0.022
 the-0.022
 very-0.021
Token?"
Token ID1701
Feature activation-3.41e+00

Pos logit contributions
lor+0.142
ocket+0.130
urger+0.124
oll+0.116
card+0.115
Neg logit contributions
 different-0.081
 fast-0.080
 slow-0.074
 very-0.072
 really-0.069
Token Her
Token ID2332
Feature activation+2.72e+00

Pos logit contributions
 fast+0.097
 different+0.094
 slow+0.088
 very+0.082
 hard+0.080
Neg logit contributions
lor-0.148
ocket-0.134
urger-0.129
card-0.118
ster-0.118
Token dad
Token ID9955
Feature activation-4.81e-01

Pos logit contributions
lor+0.117
ocket+0.102
urger+0.094
card+0.089
anger+0.088
Neg logit contributions
 different-0.093
 fast-0.091
 very-0.087
 slow-0.086
 really-0.083
Token replied
Token ID8712
Feature activation+6.17e+00

Pos logit contributions
 different+0.015
 fast+0.015
 very+0.014
 slow+0.014
 really+0.014
Neg logit contributions
lor-0.021
ocket-0.019
urger-0.018
anger-0.017
oll-0.017
Token,
Token ID11
Feature activation-4.92e-01

Pos logit contributions
lor+0.300
ocket+0.285
urger+0.275
ster+0.261
oll+0.261
Neg logit contributions
 different-0.129
 fast-0.124
 slow-0.114
 late-0.109
Stop-0.102
Token "
Token ID366
Feature activation-3.81e+00

Pos logit contributions
 different+0.011
 fast+0.011
 slow+0.010
 very+0.009
 late+0.009
Neg logit contributions
lor-0.024
ocket-0.022
urger-0.021
card-0.020
ster-0.020
TokenI
Token ID40
Feature activation-2.52e+00

Pos logit contributions
 different+0.067
 fast+0.067
 slow+0.061
 very+0.056
 busy+0.051
Neg logit contributions
lor-0.208
ocket-0.189
urger-0.177
card-0.176
oll-0.173
Token'm
Token ID1101
Feature activation+1.24e-01

Pos logit contributions
 different+0.047
 fast+0.045
 slow+0.040
 very+0.039
 really+0.038
Neg logit contributions
lor-0.140
ocket-0.130
urger-0.125
oll-0.118
card-0.117
Token printing
Token ID13570
Feature activation+2.83e+00

Pos logit contributions
lor+0.006
ocket+0.005
urger+0.005
oll+0.005
card+0.004
Neg logit contributions
 different-0.004
 fast-0.003
 slow-0.003
 very-0.003
 really-0.003
Token a
Token ID257
Feature activation+1.32e+00

Pos logit contributions
lor+0.151
ocket+0.141
urger+0.135
card+0.128
oll+0.127
Neg logit contributions
 fast-0.051
 different-0.051
 slow-0.046
 very-0.043
 late-0.041
Token recipe
Token ID8364
Feature activation+5.28e+00

Pos logit contributions
lor+0.048
ocket+0.044
urger+0.042
card+0.040
ster+0.038
Neg logit contributions
 fast-0.044
 different-0.043
 slow-0.042
 late-0.040
 very-0.039
Token
Token ID198
Feature activation-6.09e-01

Pos logit contributions
 different+0.009
 fast+0.008
 slow+0.007
 very+0.007
 hurt+0.007
Neg logit contributions
lor-0.028
ocket-0.024
anger-0.023
card-0.023
uit-0.022
TokenSuddenly
Token ID38582
Feature activation+3.56e-01

Pos logit contributions
 different+0.014
 fast+0.014
 slow+0.013
 very+0.013
 hard+0.012
Neg logit contributions
lor-0.028
ocket-0.024
card-0.023
bridge-0.022
urger-0.022
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
lor+0.019
ocket+0.018
urger+0.017
card+0.017
oll+0.016
Neg logit contributions
 different-0.006
 fast-0.006
 slow-0.005
 very-0.005
 really-0.005
Token a
Token ID257
Feature activation+8.67e-01

Pos logit contributions
 different+0.022
 fast+0.021
 slow+0.019
 very+0.018
 really+0.017
Neg logit contributions
lor-0.060
ocket-0.056
urger-0.053
card-0.050
oll-0.050
Token strange
Token ID6283
Feature activation-2.82e-01

Pos logit contributions
lor+0.042
ocket+0.040
urger+0.037
ster+0.036
card+0.036
Neg logit contributions
 different-0.018
 fast-0.017
 slow-0.015
 late-0.015
 each-0.014
Token dizz
Token ID29527
Feature activation-3.19e+00

Pos logit contributions
 different+0.008
 fast+0.008
 slow+0.007
 very+0.007
 really+0.007
Neg logit contributions
lor-0.013
ocket-0.012
urger-0.011
card-0.010
oll-0.010
Tokeny
Token ID88
Feature activation-1.82e+00

Pos logit contributions
 different+0.050
 fast+0.048
 slow+0.042
 very+0.040
 really+0.036
Neg logit contributions
lor-0.182
ocket-0.171
urger-0.162
oll-0.157
anger-0.155
Token feeling
Token ID4203
Feature activation-1.73e+00

Pos logit contributions
 different+0.047
 fast+0.047
 slow+0.043
 very+0.042
 really+0.040
Neg logit contributions
lor-0.085
ocket-0.079
urger-0.075
oll-0.070
card-0.069
Token came
Token ID1625
Feature activation-1.31e-01

Pos logit contributions
 different+0.036
 fast+0.035
 slow+0.032
 very+0.030
 late+0.029
Neg logit contributions
lor-0.088
ocket-0.083
urger-0.076
oll-0.075
card-0.074
Token over
Token ID625
Feature activation-6.02e+00

Pos logit contributions
 different+0.003
 fast+0.003
 slow+0.003
 fun+0.003
Stop+0.003
Neg logit contributions
lor-0.005
ocket-0.005
urger-0.005
icking-0.005
card-0.004
Token her
Token ID607
Feature activation+1.72e+00

Pos logit contributions
 different+0.088
 fast+0.087
 slow+0.075
 very+0.070
 really+0.065
Neg logit contributions
lor-0.346
ocket-0.326
urger-0.310
oll-0.295
card-0.295
Token She
Token ID1375
Feature activation+1.52e+00

Pos logit contributions
lor+0.018
ocket+0.017
oll+0.016
urger+0.015
anger+0.015
Neg logit contributions
 different-0.006
 fast-0.005
 slow-0.005
 very-0.005
 really-0.004
Token learned
Token ID4499
Feature activation+2.13e+00

Pos logit contributions
lor+0.079
ocket+0.073
urger+0.070
oll+0.066
card+0.065
Neg logit contributions
 different-0.032
 fast-0.032
 slow-0.028
 very-0.027
 late-0.026
Token how
Token ID703
Feature activation-1.86e+00

Pos logit contributions
lor+0.100
ocket+0.093
oll+0.084
card+0.084
urger+0.083
Neg logit contributions
 fast-0.046
 different-0.045
 slow-0.044
 late-0.040
 panic-0.040
Token to
Token ID284
Feature activation+8.50e-01

Pos logit contributions
 opposite+0.035
 panic+0.034
Uh+0.034
ny+0.033
Stop+0.033
Neg logit contributions
ocket-0.068
lor-0.068
anger-0.063
oll-0.063
ster-0.063
Token be
Token ID307
Feature activation-1.81e+00

Pos logit contributions
lor+0.033
urger+0.029
ocket+0.029
uit+0.027
oll+0.027
Neg logit contributions
 late-0.024
 different-0.023
 fast-0.023
Da-0.022
 very-0.021
Token less
Token ID1342
Feature activation-4.78e+00

Pos logit contributions
 heavily+0.042
Stop+0.041
B+0.040
 wildly+0.039
|+0.038
Neg logit contributions
card-0.063
ocket-0.061
lor-0.060
oll-0.059
urger-0.059
Token shy
Token ID15800
Feature activation-2.00e+00

Pos logit contributions
B+0.101
Amy+0.097
Da+0.096
Lu+0.094
|+0.094
Neg logit contributions
ocket-0.181
oll-0.177
ster-0.172
sters-0.170
lor-0.170
Token.
Token ID13
Feature activation+5.03e-01

Pos logit contributions
 different+0.036
 fast+0.035
 slow+0.031
 late+0.029
 very+0.028
Neg logit contributions
lor-0.101
ocket-0.097
oll-0.090
urger-0.090
ster-0.087
Token She
Token ID1375
Feature activation+1.59e+00

Pos logit contributions
lor+0.028
ocket+0.026
oll+0.024
urger+0.024
card+0.023
Neg logit contributions
 different-0.008
 fast-0.008
 slow-0.007
 very-0.006
 really-0.006
Token had
Token ID550
Feature activation-4.54e-01

Pos logit contributions
lor+0.083
ocket+0.077
urger+0.074
oll+0.070
card+0.069
Neg logit contributions
 different-0.033
 fast-0.032
 slow-0.029
 very-0.028
 really-0.026
Token the
Token ID262
Feature activation+8.12e-01

Pos logit contributions
 fast+0.008
 heavily+0.008
 late+0.007
B+0.007
 wildly+0.007
Neg logit contributions
lor-0.020
ocket-0.019
oll-0.018
urger-0.017
inch-0.017