TOP ACTIVATIONS
MAX = 0.199

, Anna and Ben . Sleep well . We love you
Sara . Good night . Sleep tight . Don 't let
, my sweet ies . Sleep tight . And don 't
You need to sleep . Sleep is good for you .
" It 's easy . Sleep is when you close your
saw a big ball . Sleep y loved balls . He
One day , Sleep y went for a walk
Good night , Lily . Sleep well ." Lily replied ,
day and all night . Sleep y had a big ,
night , sweet ie . Sleep tight ." He tucked her
you too , kids . Sleep well . Have sweet dreams
Good night , Max . Sleep tight ." Max fell asleep
Good night , doll . Sleep well ." Lily was happy
dog named Sleep y . Sleep y was a very sleepy
was a little dog named Sleep y . Sleep y was
Good night , drum . Sleep well ." The
you need to sleep . Sleep will help you feel better
house and our family . Amen ." Mom smiled
family and our friends . Amen ." Anna said
, I can help . Close your eyes and make a

MIN ACTIVATIONS
MIN = -0.304

Fl oppy saw a mar vell ous view . He also
, laughed and built sand cast les . Soon , they
bucket . She made sand cast les and sand pies .
beach . They made sand cast les and ran through the
while , then built sand cast les with his mom .
't wait to make sand cast les .
play outside and make sand cast les on the beach .
. He would build sand cast les and collect seas hell
She liked to build sand cast les and collect seas hell
the beach and build sand cast les . But one day
the beach and building sand cast les . One day ,
the waves and built sand cast les . M
. They would build sand cast les and swim in the
She saw shells , sand cast les and se ag ull
each other and making sand cast les .
She liked to build sand cast les and collect seas hell
building the most beautiful sand cast les on the beach .
took time to make sand cast les and feel the waves
the beach and build sand cast les .
went back to building sand cast les with his family .

INTERVAL 0.073 - 0.199
CONTAINS 2.443%

� € � � Yes please ! â €
his worries were gone . <|endoftext|> Once upon a time ,
him . She found him lying on the ground , not
cooperate than to compete . <|endoftext|> L ily and Sam were
longer sad or hungry ! <|endoftext|> Tom my enjoyed riding his

INTERVAL -0.052 - 0.073
CONTAINS 91.276%

Bob smiled and said , " We have gained a new
someone more powerful than yourself . <|endoftext|> Once there was a
a letter in the mail . It was from his grandma
it might not be good for him . Max listened to
they hugged him . They drank their hot chocolate and ate

INTERVAL -0.178 - -0.052
CONTAINS 6.265%

. He shouted with g lee , " Look , Molly
alright , Lucky . You don 't need to work .
a drawer and stayed away from it . Days , weeks
was much com f ier than any of her l ilies
couldn 't hear any cars or people talking .

INTERVAL -0.304 - -0.178
CONTAINS 0.015%

sharing is important and qu arre lling is not good .
it - not even the tallest tree .
in the forest . Bub bles told him that he was
't play with your mar bles ." Tim my
. She built a sand castle and decorated it with seas
Token,
Token ID11
Feature activation+3.80e-02

Pos logit contributions
 crib+0.051
Mom+0.049
ara+0.049
 beef+0.040
 End+0.040
Neg logit contributions
vell-0.124
wheel-0.116
inations-0.113
 disl-0.112
od-0.112
Token Anna
Token ID11735
Feature activation+6.94e-02

Pos logit contributions
 crib+0.040
Mom+0.038
ara+0.037
 kitten+0.034
 beef+0.033
Neg logit contributions
vell-0.094
wheel-0.086
inations-0.084
 disl-0.083
od-0.082
Token and
Token ID290
Feature activation+1.64e-02

Pos logit contributions
 crib+0.083
ara+0.078
Mom+0.076
 Sunny+0.068
 mom+0.068
Neg logit contributions
vell-0.167
wheel-0.157
 disl-0.149
inations-0.147
od-0.147
Token Ben
Token ID3932
Feature activation+3.46e-02

Pos logit contributions
 crib+0.027
Mom+0.025
 kitten+0.024
ara+0.024
Me+0.023
Neg logit contributions
vell-0.029
wheel-0.028
asing-0.025
cher-0.025
od-0.025
Token.
Token ID13
Feature activation+2.21e-02

Pos logit contributions
 crib+0.044
ara+0.043
Mom+0.042
 mom+0.038
 Sunny+0.037
Neg logit contributions
vell-0.083
wheel-0.077
 disl-0.074
inations-0.073
od-0.072
Token Sleep
Token ID17376
Feature activation+1.99e-01

Pos logit contributions
 crib+0.032
ara+0.031
Mom+0.031
 mom+0.029
 beef+0.028
Neg logit contributions
vell-0.047
wheel-0.043
 disl-0.043
od-0.040
inations-0.040
Token well
Token ID880
Feature activation+6.73e-02

Pos logit contributions
Mom+0.278
 beef+0.250
 ham+0.248
 crib+0.248
 Sunny+0.243
Neg logit contributions
vell-0.425
inations-0.382
 disl-0.379
wheel-0.377
cast-0.358
Token.
Token ID13
Feature activation+2.23e-02

Pos logit contributions
 crib+0.090
ara+0.088
Mom+0.087
 mom+0.080
 Sunny+0.076
Neg logit contributions
vell-0.157
wheel-0.145
 disl-0.137
inations-0.137
od-0.135
Token We
Token ID775
Feature activation+1.80e-02

Pos logit contributions
 crib+0.030
ara+0.028
Mom+0.028
 mom+0.026
 beef+0.025
Neg logit contributions
vell-0.050
wheel-0.047
 disl-0.046
od-0.044
inations-0.043
Token love
Token ID1842
Feature activation+4.66e-02

Pos logit contributions
 crib+0.024
ara+0.023
Mom+0.023
 mom+0.022
 bunny+0.021
Neg logit contributions
vell-0.043
wheel-0.039
inations-0.037
 disl-0.037
od-0.037
Token you
Token ID345
Feature activation-4.96e-03

Pos logit contributions
ara+0.092
 crib+0.090
um+0.090
Mom+0.089
 vet+0.086
Neg logit contributions
vell-0.059
inations-0.058
 achieve-0.056
od-0.056
 disl-0.055
Token Sara
Token ID24799
Feature activation+2.47e-02

Pos logit contributions
 crib+0.034
Mom+0.032
 End+0.030
ara+0.029
um+0.029
Neg logit contributions
vell-0.081
wheel-0.075
od-0.072
 disl-0.071
inations-0.068
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
 crib+0.033
ara+0.032
Mom+0.031
 mom+0.028
 End+0.028
Neg logit contributions
vell-0.057
wheel-0.053
 disl-0.050
od-0.050
inations-0.050
Token Good
Token ID4599
Feature activation+8.43e-02

Pos logit contributions
 crib+0.018
ara+0.018
Mom+0.018
um+0.017
 chicken+0.017
Neg logit contributions
vell-0.020
wheel-0.019
 disl-0.019
asing-0.017
od-0.017
Token night
Token ID1755
Feature activation+4.71e-02

Pos logit contributions
Mom+0.104
ara+0.094
 vet+0.094
 Sunny+0.092
 crib+0.091
Neg logit contributions
vell-0.179
 disl-0.163
ont-0.162
cast-0.161
wheel-0.160
Token.
Token ID13
Feature activation+1.17e-02

Pos logit contributions
ara+0.049
 crib+0.049
Mom+0.048
 End+0.040
 beef+0.040
Neg logit contributions
vell-0.119
wheel-0.113
inations-0.107
 disl-0.106
od-0.106
Token Sleep
Token ID17376
Feature activation+1.97e-01

Pos logit contributions
 crib+0.017
ara+0.017
Mom+0.016
 beef+0.016
um+0.016
Neg logit contributions
vell-0.023
wheel-0.022
 disl-0.022
asing-0.020
od-0.020
Token tight
Token ID5381
Feature activation+9.94e-02

Pos logit contributions
Mom+0.268
 beef+0.253
 ham+0.249
 vet+0.244
 crib+0.241
Neg logit contributions
vell-0.415
 disl-0.371
wheel-0.368
inations-0.367
cast-0.353
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
 crib+0.119
Mom+0.119
ara+0.119
 mom+0.105
 End+0.102
Neg logit contributions
vell-0.239
wheel-0.225
 disl-0.212
inations-0.208
od-0.207
Token Don
Token ID2094
Feature activation-3.52e-02

Pos logit contributions
 crib+0.016
ara+0.015
Mom+0.015
 mom+0.014
 beef+0.014
Neg logit contributions
vell-0.024
wheel-0.023
 disl-0.022
inations-0.021
od-0.021
Token't
Token ID470
Feature activation-3.26e-02

Pos logit contributions
vell+0.070
wheel+0.068
inations+0.060
od+0.058
 achieve+0.058
Neg logit contributions
 crib-0.058
ara-0.056
Mom-0.054
 ham-0.052
 mom-0.051
Token let
Token ID1309
Feature activation-1.85e-02

Pos logit contributions
vell+0.065
wheel+0.061
 disl+0.058
inations+0.056
od+0.056
Neg logit contributions
 crib-0.052
ara-0.052
Mom-0.050
 beef-0.046
um-0.046
Token,
Token ID11
Feature activation+3.34e-02

Pos logit contributions
 crib+0.042
ara+0.041
Mom+0.040
 mom+0.034
 Sunny+0.033
Neg logit contributions
vell-0.130
wheel-0.122
 disl-0.117
inations-0.117
od-0.116
Token my
Token ID616
Feature activation+1.37e-02

Pos logit contributions
ara+0.037
 crib+0.036
Mom+0.035
 mom+0.034
 Mom+0.031
Neg logit contributions
vell-0.088
wheel-0.082
od-0.078
inations-0.077
 disl-0.077
Token sweet
Token ID6029
Feature activation+5.71e-02

Pos logit contributions
Mom+0.017
 crib+0.017
 Sunny+0.016
ara+0.015
 vet+0.014
Neg logit contributions
vell-0.032
 disl-0.029
wheel-0.029
inations-0.028
od-0.028
Tokenies
Token ID444
Feature activation-9.59e-02

Pos logit contributions
 crib+0.088
Mom+0.085
 Sunny+0.081
ara+0.078
 beef+0.076
Neg logit contributions
vell-0.114
wheel-0.106
 disl-0.103
od-0.101
inations-0.100
Token.
Token ID13
Feature activation+1.60e-02

Pos logit contributions
vell+0.240
wheel+0.221
 disl+0.212
od+0.210
inations+0.208
Neg logit contributions
 crib-0.116
ara-0.112
Mom-0.105
 mom-0.102
 Sunny-0.099
Token Sleep
Token ID17376
Feature activation+1.96e-01

Pos logit contributions
 crib+0.021
ara+0.020
Mom+0.020
 mom+0.018
 Sunny+0.018
Neg logit contributions
vell-0.038
wheel-0.035
 disl-0.033
inations-0.033
od-0.033
Token tight
Token ID5381
Feature activation+9.91e-02

Pos logit contributions
Mom+0.263
 crib+0.240
 ham+0.235
 beef+0.233
ara+0.229
Neg logit contributions
vell-0.432
 disl-0.389
wheel-0.387
inations-0.385
cast-0.367
Token.
Token ID13
Feature activation+1.60e-02

Pos logit contributions
 crib+0.122
ara+0.120
Mom+0.118
 mom+0.107
 Sunny+0.102
Neg logit contributions
vell-0.240
wheel-0.223
 disl-0.212
inations-0.210
od-0.208
Token And
Token ID843
Feature activation-3.57e-02

Pos logit contributions
 crib+0.021
ara+0.020
Mom+0.020
 mom+0.018
 beef+0.017
Neg logit contributions
vell-0.037
wheel-0.034
 disl-0.033
inations-0.032
od-0.032
Token don
Token ID836
Feature activation-4.72e-02

Pos logit contributions
vell+0.077
wheel+0.070
 disl+0.067
inations+0.066
od+0.065
Neg logit contributions
 crib-0.055
ara-0.054
Mom-0.052
 mom-0.049
 Sunny-0.047
Token't
Token ID470
Feature activation-3.15e-02

Pos logit contributions
vell+0.108
wheel+0.099
 disl+0.094
inations+0.093
od+0.092
Neg logit contributions
 crib-0.067
ara-0.065
Mom-0.064
 mom-0.060
 Sunny-0.057
Token You
Token ID921
Feature activation-8.28e-04

Pos logit contributions
vell+0.000
wheel+0.000
 disl+0.000
od+0.000
inations+0.000
Neg logit contributions
 crib-0.000
ara-0.000
Mom-0.000
 mom-0.000
 beef-0.000
Token need
Token ID761
Feature activation+1.77e-02

Pos logit contributions
vell+0.002
 disl+0.002
wheel+0.002
od+0.002
inations+0.002
Neg logit contributions
 crib-0.001
 mom-0.001
 bunny-0.001
Mom-0.001
 Sunny-0.001
Token to
Token ID284
Feature activation+7.47e-03

Pos logit contributions
ara+0.027
 crib+0.024
Mom+0.024
um+0.023
 End+0.023
Neg logit contributions
vell-0.037
wheel-0.035
inations-0.034
 disl-0.033
smart-0.032
Token sleep
Token ID3993
Feature activation+9.17e-02

Pos logit contributions
 crib+0.010
ara+0.010
Mom+0.010
 mom+0.009
 Sunny+0.009
Neg logit contributions
vell-0.017
wheel-0.016
 disl-0.015
inations-0.015
od-0.015
Token.
Token ID13
Feature activation+6.75e-04

Pos logit contributions
 crib+0.113
ara+0.111
Mom+0.107
 mom+0.099
 Sunny+0.095
Neg logit contributions
vell-0.225
wheel-0.208
 disl-0.198
inations-0.197
od-0.195
Token Sleep
Token ID17376
Feature activation+1.96e-01

Pos logit contributions
ara+0.001
 crib+0.001
Mom+0.001
 beef+0.001
um+0.001
Neg logit contributions
vell-0.001
wheel-0.001
 disl-0.001
asing-0.001
inations-0.001
Token is
Token ID318
Feature activation+1.65e-02

Pos logit contributions
Mom+0.259
 crib+0.253
ara+0.248
 beef+0.229
 mom+0.229
Neg logit contributions
vell-0.444
wheel-0.406
 disl-0.394
inations-0.391
od-0.375
Token good
Token ID922
Feature activation-3.74e-02

Pos logit contributions
ara+0.026
 crib+0.024
Mom+0.024
um+0.022
 ham+0.021
Neg logit contributions
vell-0.035
wheel-0.032
inations-0.031
 disl-0.030
cher-0.029
Token for
Token ID329
Feature activation+3.77e-02

Pos logit contributions
vell+0.099
wheel+0.091
 disl+0.087
inations+0.086
od+0.086
Neg logit contributions
 crib-0.042
ara-0.040
Mom-0.038
 mom-0.037
 bunny-0.035
Token you
Token ID345
Feature activation-7.78e-03

Pos logit contributions
ara+0.054
 crib+0.050
Mom+0.049
um+0.046
 ham+0.043
Neg logit contributions
vell-0.080
inations-0.075
wheel-0.073
 disl-0.071
od-0.071
Token.
Token ID13
Feature activation+1.26e-03

Pos logit contributions
vell+0.018
wheel+0.016
inations+0.016
 disl+0.016
od+0.015
Neg logit contributions
ara-0.011
 crib-0.010
Mom-0.010
 mom-0.009
 Sunny-0.009
Token "
Token ID366
Feature activation+3.81e-02

Pos logit contributions
 crib+0.023
ara+0.022
Mom+0.020
 mom+0.017
 beef+0.017
Neg logit contributions
vell-0.060
wheel-0.057
od-0.054
 disl-0.054
inations-0.052
TokenIt
Token ID1026
Feature activation+6.28e-02

Pos logit contributions
ara+0.042
 crib+0.041
Mom+0.040
 mom+0.036
 Sunny+0.035
Neg logit contributions
vell-0.099
wheel-0.092
inations-0.088
 disl-0.088
od-0.086
Token's
Token ID338
Feature activation+5.66e-02

Pos logit contributions
 crib+0.063
ara+0.059
 bunny+0.057
 mom+0.057
 Sunny+0.056
Neg logit contributions
vell-0.168
wheel-0.157
inations-0.150
 disl-0.149
od-0.145
Token easy
Token ID2562
Feature activation-2.90e-02

Pos logit contributions
 crib+0.076
ara+0.076
Mom+0.073
 mom+0.067
 bunny+0.065
Neg logit contributions
vell-0.132
wheel-0.121
 disl-0.115
inations-0.114
od-0.113
Token.
Token ID13
Feature activation+8.47e-05

Pos logit contributions
vell+0.076
wheel+0.070
 disl+0.067
inations+0.066
od+0.066
Neg logit contributions
 crib-0.032
ara-0.030
Mom-0.028
 mom-0.028
 Sunny-0.026
Token Sleep
Token ID17376
Feature activation+1.96e-01

Pos logit contributions
 crib+0.000
ara+0.000
Mom+0.000
 mom+0.000
 beef+0.000
Neg logit contributions
vell-0.000
wheel-0.000
 disl-0.000
od-0.000
inations-0.000
Token is
Token ID318
Feature activation+1.41e-02

Pos logit contributions
Mom+0.253
 crib+0.244
ara+0.242
 mom+0.221
 beef+0.219
Neg logit contributions
vell-0.459
wheel-0.417
 disl-0.409
inations-0.404
od-0.393
Token when
Token ID618
Feature activation+1.53e-02

Pos logit contributions
 crib+0.019
ara+0.019
Mom+0.018
 mom+0.017
 Sunny+0.016
Neg logit contributions
vell-0.033
wheel-0.030
 disl-0.029
inations-0.029
od-0.028
Token you
Token ID345
Feature activation-1.07e-02

Pos logit contributions
ara+0.024
Mom+0.023
 crib+0.023
um+0.021
 End+0.020
Neg logit contributions
vell-0.031
wheel-0.028
inations-0.027
 disl-0.027
od-0.027
Token close
Token ID1969
Feature activation+8.83e-02

Pos logit contributions
vell+0.023
wheel+0.021
 disl+0.021
od+0.020
inations+0.020
Neg logit contributions
 crib-0.016
ara-0.016
Mom-0.015
 mom-0.015
 bunny-0.014
Token your
Token ID534
Feature activation+2.11e-02

Pos logit contributions
 crib+0.105
ara+0.103
Mom+0.099
 mom+0.092
 Sunny+0.088
Neg logit contributions
vell-0.221
wheel-0.205
 disl-0.195
inations-0.194
od-0.192
Token saw
Token ID2497
Feature activation-2.52e-02

Pos logit contributions
vell+0.015
wheel+0.014
inations+0.013
cher+0.013
cast+0.012
Neg logit contributions
 crib-0.012
ara-0.011
Mom-0.011
 beef-0.011
um-0.011
Token a
Token ID257
Feature activation+2.05e-02

Pos logit contributions
vell+0.047
wheel+0.045
 disl+0.042
od+0.040
inations+0.039
Neg logit contributions
ara-0.041
Mom-0.037
um-0.036
 crib-0.035
�-0.034
Token big
Token ID1263
Feature activation-1.05e-02

Pos logit contributions
ara+0.027
um+0.027
Mom+0.026
 End+0.026
 brow+0.025
Neg logit contributions
vell-0.043
wheel-0.039
 achieve-0.036
cher-0.034
inations-0.034
Token ball
Token ID2613
Feature activation-4.56e-03

Pos logit contributions
wheel+0.018
vell+0.018
 achieve+0.016
 disl+0.016
ologist+0.016
Neg logit contributions
Mom-0.016
 End-0.014
ara-0.014
Me-0.014
um-0.014
Token.
Token ID13
Feature activation-3.63e-03

Pos logit contributions
wheel+0.009
vell+0.009
od+0.008
cher+0.008
smart+0.007
Neg logit contributions
ara-0.007
Mom-0.007
 crib-0.007
 mom-0.007
 End-0.006
Token Sleep
Token ID17376
Feature activation+1.95e-01

Pos logit contributions
wheel+0.006
vell+0.005
smart+0.005
 achieve+0.005
cher+0.004
Neg logit contributions
ara-0.007
Mom-0.006
 End-0.006
um-0.006
 end-0.006
Tokeny
Token ID88
Feature activation+4.37e-02

Pos logit contributions
 crib+0.280
Mom+0.275
 beef+0.275
 vet+0.266
 ham+0.262
Neg logit contributions
vell-0.420
cast-0.360
wheel-0.357
 disl-0.355
od-0.350
Token loved
Token ID6151
Feature activation+4.09e-02

Pos logit contributions
 crib+0.066
Mom+0.066
ara+0.064
 beef+0.059
 End+0.058
Neg logit contributions
vell-0.085
wheel-0.084
od-0.077
inations-0.075
cast-0.075
Token balls
Token ID11333
Feature activation-8.51e-02

Pos logit contributions
ara+0.065
Mom+0.063
um+0.060
 crib+0.058
 End+0.055
Neg logit contributions
vell-0.081
wheel-0.078
 disl-0.073
smart-0.072
inations-0.071
Token.
Token ID13
Feature activation-3.05e-03

Pos logit contributions
vell+0.231
 disl+0.213
wheel+0.209
inations+0.205
od+0.202
Neg logit contributions
 crib-0.085
ara-0.074
Mom-0.073
 mom-0.073
 bunny-0.070
Token He
Token ID679
Feature activation-1.97e-03

Pos logit contributions
vell+0.005
wheel+0.004
 achieve+0.004
cast+0.004
smart+0.004
Neg logit contributions
Mom-0.005
ara-0.005
 End-0.005
um-0.005
 mother-0.005
Token
Token ID198
Feature activation-1.65e-02

Pos logit contributions
wheel+0.007
vell+0.007
 achieve+0.007
cast+0.007
inations+0.007
Neg logit contributions
ara-0.008
Mom-0.008
 End-0.007
um-0.007
 lady-0.007
Token
Token ID198
Feature activation-1.66e-02

Pos logit contributions
vell+0.034
wheel+0.033
od+0.033
inations+0.033
 achieve+0.031
Neg logit contributions
 crib-0.022
ara-0.021
 ham-0.020
Mom-0.020
 kitten-0.020
TokenOne
Token ID3198
Feature activation+1.21e-01

Pos logit contributions
 achieve+0.026
vell+0.025
inations+0.024
wheel+0.024
 accomplish+0.022
Neg logit contributions
 eyes-0.028
 mom-0.028
 mother-0.027
 Mom-0.027
 kitten-0.026
Token day
Token ID1110
Feature activation+2.92e-02

Pos logit contributions
 cash+0.174
ara+0.162
 checkout+0.161
Mom+0.155
 brow+0.154
Neg logit contributions
wheel-0.223
vell-0.223
ont-0.215
adows-0.209
inations-0.209
Token,
Token ID11
Feature activation+2.19e-02

Pos logit contributions
Mom+0.047
ara+0.046
 crib+0.046
 vet+0.045
 nurse+0.044
Neg logit contributions
vell-0.044
wheel-0.038
smart-0.037
cher-0.036
od-0.036
Token Sleep
Token ID17376
Feature activation+1.92e-01

Pos logit contributions
ara+0.036
um+0.034
 crib+0.032
 End+0.032
Mom+0.032
Neg logit contributions
vell-0.036
wheel-0.031
cher-0.029
cast-0.029
 achieve-0.029
Tokeny
Token ID88
Feature activation+4.14e-02

Pos logit contributions
 beef+0.280
 cash+0.268
 ham+0.266
 crib+0.266
Mom+0.255
Neg logit contributions
vell-0.386
 disl-0.342
cast-0.337
od-0.331
ont-0.324
Token went
Token ID1816
Feature activation-2.65e-02

Pos logit contributions
 crib+0.063
Mom+0.063
ara+0.058
 beef+0.058
um+0.055
Neg logit contributions
vell-0.078
wheel-0.076
od-0.070
inations-0.070
cast-0.067
Token for
Token ID329
Feature activation+3.48e-02

Pos logit contributions
vell+0.053
wheel+0.051
inations+0.045
cher+0.045
smart+0.045
Neg logit contributions
ara-0.044
Mom-0.042
 End-0.039
 crib-0.039
 mom-0.038
Token a
Token ID257
Feature activation+1.81e-02

Pos logit contributions
ara+0.059
um+0.056
Mom+0.054
 crib+0.048
�+0.047
Neg logit contributions
inations-0.058
vell-0.057
wheel-0.057
 achieve-0.054
 disl-0.053
Token walk
Token ID2513
Feature activation+5.16e-02

Pos logit contributions
ara+0.023
Mom+0.023
um+0.023
 End+0.022
 crib+0.022
Neg logit contributions
vell-0.041
wheel-0.038
inations-0.038
 achieve-0.035
 disl-0.035
TokenGood
Token ID10248
Feature activation-3.29e-03

Pos logit contributions
 crib+0.051
 mom+0.045
 beef+0.043
 eyes+0.043
 Sunny+0.043
Neg logit contributions
wheel-0.069
vell-0.068
 disl-0.061
asing-0.059
inations-0.059
Tokennight
Token ID3847
Feature activation+1.68e-01

Pos logit contributions
vell+0.007
wheel+0.007
ont+0.007
 disl+0.006
od+0.006
Neg logit contributions
Mom-0.004
 Sunny-0.004
 crib-0.004
ara-0.004
 stall-0.003
Token,
Token ID11
Feature activation+1.91e-02

Pos logit contributions
Mom+0.174
ara+0.169
 crib+0.168
 End+0.153
 beef+0.141
Neg logit contributions
vell-0.419
wheel-0.397
 disl-0.372
od-0.371
cher-0.368
Token Lily
Token ID20037
Feature activation-2.02e-02

Pos logit contributions
 crib+0.021
ara+0.020
Mom+0.020
 beef+0.017
 End+0.017
Neg logit contributions
vell-0.049
wheel-0.046
 disl-0.044
inations-0.043
od-0.042
Token.
Token ID13
Feature activation-1.03e-02

Pos logit contributions
vell+0.042
wheel+0.038
 disl+0.036
inations+0.036
od+0.035
Neg logit contributions
 crib-0.032
ara-0.032
Mom-0.031
 mom-0.029
 Sunny-0.028
Token Sleep
Token ID17376
Feature activation+1.92e-01

Pos logit contributions
vell+0.021
wheel+0.020
 disl+0.019
inations+0.018
asing+0.018
Neg logit contributions
 crib-0.015
ara-0.015
 beef-0.014
Mom-0.014
 chicken-0.014
Token well
Token ID880
Feature activation+5.57e-02

Pos logit contributions
Mom+0.262
 ham+0.252
 beef+0.248
 vet+0.236
 crib+0.231
Neg logit contributions
vell-0.402
wheel-0.366
 disl-0.363
inations-0.355
cast-0.343
Token."
Token ID526
Feature activation-2.31e-02

Pos logit contributions
 crib+0.070
ara+0.068
Mom+0.066
 mom+0.062
 Sunny+0.059
Neg logit contributions
vell-0.135
wheel-0.125
 disl-0.119
inations-0.118
od-0.117
Token Lily
Token ID20037
Feature activation-1.93e-02

Pos logit contributions
wheel+0.052
vell+0.051
 disl+0.050
od+0.047
inations+0.047
Neg logit contributions
 crib-0.028
Mom-0.027
ara-0.027
 End-0.025
 beef-0.025
Token replied
Token ID8712
Feature activation+8.58e-02

Pos logit contributions
vell+0.034
wheel+0.033
inations+0.031
od+0.029
ont+0.029
Neg logit contributions
 crib-0.032
 beef-0.030
ara-0.030
Mom-0.030
 kitten-0.029
Token,
Token ID11
Feature activation+2.05e-02

Pos logit contributions
ara+0.144
 vet+0.124
 kitten+0.121
 ham+0.119
Mom+0.119
Neg logit contributions
vell-0.167
wheel-0.158
od-0.145
 achieve-0.140
smart-0.138
Token day
Token ID1110
Feature activation+2.63e-02

Pos logit contributions
vell+0.093
wheel+0.085
inations+0.082
 disl+0.082
cher+0.081
Neg logit contributions
 crib-0.018
ara-0.015
Mom-0.014
 mom-0.012
 Sunny-0.012
Token and
Token ID290
Feature activation-7.18e-03

Pos logit contributions
ara+0.034
Mom+0.033
 crib+0.032
 End+0.029
 mom+0.028
Neg logit contributions
vell-0.062
wheel-0.058
inations-0.056
od-0.055
 disl-0.052
Token all
Token ID477
Feature activation-2.86e-02

Pos logit contributions
vell+0.015
wheel+0.014
 disl+0.014
inations+0.014
 achieve+0.013
Neg logit contributions
ara-0.011
Mom-0.010
 crib-0.010
um-0.010
 kitten-0.009
Token night
Token ID1755
Feature activation+3.86e-02

Pos logit contributions
vell+0.086
wheel+0.079
 disl+0.076
inations+0.076
od+0.075
Neg logit contributions
 crib-0.022
ara-0.020
Mom-0.019
 mom-0.018
 Sunny-0.017
Token.
Token ID13
Feature activation-6.85e-03

Pos logit contributions
ara+0.053
 crib+0.051
Mom+0.051
 mom+0.047
 End+0.045
Neg logit contributions
vell-0.088
wheel-0.082
inations-0.078
od-0.077
 disl-0.077
Token Sleep
Token ID17376
Feature activation+1.90e-01

Pos logit contributions
wheel+0.010
vell+0.010
 achieve+0.010
cast+0.009
inations+0.009
Neg logit contributions
ara-0.011
Mom-0.011
um-0.010
 End-0.010
 kitten-0.010
Tokeny
Token ID88
Feature activation+3.86e-02

Pos logit contributions
 beef+0.258
 crib+0.254
Mom+0.249
 vet+0.247
 ham+0.247
Neg logit contributions
vell-0.401
 disl-0.358
wheel-0.347
cast-0.347
od-0.343
Token had
Token ID550
Feature activation+5.33e-03

Pos logit contributions
Mom+0.051
 crib+0.050
ara+0.050
 beef+0.045
 mom+0.045
Neg logit contributions
vell-0.085
wheel-0.081
inations-0.077
od-0.076
 disl-0.075
Token a
Token ID257
Feature activation+1.47e-02

Pos logit contributions
ara+0.008
Mom+0.007
 crib+0.007
 End+0.007
um+0.006
Neg logit contributions
vell-0.012
wheel-0.011
inations-0.010
od-0.010
 disl-0.010
Token big
Token ID1263
Feature activation-1.48e-02

Pos logit contributions
ara+0.025
um+0.023
 End+0.023
Mom+0.022
 Sunny+0.021
Neg logit contributions
vell-0.025
inations-0.022
 achieve-0.021
wheel-0.021
 disl-0.020
Token,
Token ID11
Feature activation+2.10e-02

Pos logit contributions
inations+0.024
wheel+0.024
 disl+0.024
vell+0.023
ont+0.023
Neg logit contributions
Mom-0.021
ara-0.020
 Ivy-0.018
Please-0.018
 cash-0.018
Token night
Token ID1755
Feature activation+3.70e-02

Pos logit contributions
vell+0.014
wheel+0.014
 disl+0.013
od+0.013
ologist+0.012
Neg logit contributions
 crib-0.007
ara-0.007
Mom-0.007
 Sunny-0.006
 mom-0.006
Token,
Token ID11
Feature activation+2.21e-02

Pos logit contributions
 crib+0.037
ara+0.036
Mom+0.035
 mom+0.030
 Sunny+0.029
Neg logit contributions
vell-0.098
wheel-0.092
inations-0.088
 disl-0.088
od-0.087
Token sweet
Token ID6029
Feature activation+4.52e-02

Pos logit contributions
 crib+0.022
ara+0.021
Mom+0.020
 mom+0.017
 Sunny+0.017
Neg logit contributions
vell-0.059
wheel-0.055
 disl-0.053
inations-0.052
od-0.052
Tokenie
Token ID494
Feature activation-2.08e-02

Pos logit contributions
 crib+0.074
Mom+0.072
ara+0.067
 Sunny+0.066
 End+0.064
Neg logit contributions
vell-0.085
wheel-0.077
 disl-0.076
od-0.075
inations-0.073
Token.
Token ID13
Feature activation+1.26e-03

Pos logit contributions
vell+0.046
wheel+0.042
 disl+0.039
inations+0.039
od+0.039
Neg logit contributions
 crib-0.031
ara-0.030
Mom-0.029
 mom-0.027
 Sunny-0.027
Token Sleep
Token ID17376
Feature activation+1.90e-01

Pos logit contributions
 crib+0.002
ara+0.002
Mom+0.002
 mom+0.001
 beef+0.001
Neg logit contributions
vell-0.003
wheel-0.003
 disl-0.003
inations-0.003
od-0.003
Token tight
Token ID5381
Feature activation+8.82e-02

Pos logit contributions
Mom+0.255
 ham+0.240
ara+0.235
 crib+0.235
 beef+0.234
Neg logit contributions
vell-0.412
wheel-0.366
inations-0.366
 disl-0.362
cast-0.342
Token."
Token ID526
Feature activation-2.39e-02

Pos logit contributions
 crib+0.120
ara+0.119
Mom+0.118
 mom+0.107
 End+0.103
Neg logit contributions
vell-0.200
wheel-0.186
 disl-0.176
inations-0.174
od-0.171
Token He
Token ID679
Feature activation+1.81e-04

Pos logit contributions
vell+0.053
wheel+0.051
 disl+0.051
inations+0.048
od+0.048
Neg logit contributions
 crib-0.028
ara-0.027
Mom-0.027
 End-0.025
 kitten-0.024
Token tucked
Token ID29779
Feature activation+9.04e-02

Pos logit contributions
 crib+0.000
ara+0.000
Mom+0.000
 beef+0.000
 End+0.000
Neg logit contributions
vell-0.000
wheel-0.000
inations-0.000
od-0.000
cher-0.000
Token her
Token ID607
Feature activation+6.49e-03

Pos logit contributions
 crib+0.128
ara+0.124
Mom+0.113
 beef+0.109
 End+0.108
Neg logit contributions
vell-0.187
wheel-0.168
cher-0.163
cast-0.156
smart-0.155
Token you
Token ID345
Feature activation-1.70e-02

Pos logit contributions
 crib+0.056
ara+0.055
Mom+0.052
 End+0.048
um+0.048
Neg logit contributions
vell-0.064
wheel-0.061
 disl-0.060
od-0.058
inations-0.057
Token too
Token ID1165
Feature activation+4.66e-02

Pos logit contributions
vell+0.033
inations+0.031
wheel+0.030
ologist+0.030
asing+0.028
Neg logit contributions
ara-0.027
 crib-0.025
 Goose-0.023
 nurse-0.023
 therapist-0.023
Token,
Token ID11
Feature activation+2.75e-02

Pos logit contributions
ara+0.053
 crib+0.052
Mom+0.050
 bunny+0.044
 nurse+0.044
Neg logit contributions
vell-0.115
wheel-0.105
 disl-0.103
inations-0.103
od-0.102
Token kids
Token ID3988
Feature activation-9.60e-02

Pos logit contributions
 crib+0.029
ara+0.025
Mom+0.024
 beef+0.022
 Sunny+0.021
Neg logit contributions
vell-0.069
wheel-0.065
 disl-0.063
inations-0.062
od-0.062
Token.
Token ID13
Feature activation+1.33e-02

Pos logit contributions
vell+0.215
wheel+0.200
 disl+0.188
inations+0.188
od+0.186
Neg logit contributions
 crib-0.132
ara-0.130
Mom-0.128
 mom-0.116
 End-0.115
Token Sleep
Token ID17376
Feature activation+1.90e-01

Pos logit contributions
 crib+0.021
ara+0.020
Mom+0.019
 mom+0.018
 bunny+0.018
Neg logit contributions
vell-0.027
wheel-0.025
 disl-0.025
asing-0.023
od-0.023
Token well
Token ID880
Feature activation+5.57e-02

Pos logit contributions
Mom+0.258
 beef+0.240
 crib+0.239
 ham+0.233
 hen+0.230
Neg logit contributions
vell-0.397
 disl-0.364
wheel-0.353
inations-0.351
cast-0.339
Token.
Token ID13
Feature activation+1.33e-02

Pos logit contributions
 crib+0.072
ara+0.071
Mom+0.070
 mom+0.064
 Sunny+0.061
Neg logit contributions
vell-0.132
wheel-0.122
 disl-0.116
inations-0.115
od-0.114
Token Have
Token ID8192
Feature activation+4.17e-02

Pos logit contributions
 crib+0.020
ara+0.019
Mom+0.018
 mom+0.018
 beef+0.017
Neg logit contributions
vell-0.027
wheel-0.026
 disl-0.025
od-0.023
inations-0.023
Token sweet
Token ID6029
Feature activation+4.74e-02

Pos logit contributions
 crib+0.074
ara+0.071
Mom+0.067
 nurse+0.064
 kitten+0.064
Neg logit contributions
vell-0.075
wheel-0.072
 disl-0.070
inations-0.069
od-0.064
Token dreams
Token ID10625
Feature activation-2.10e-02

Pos logit contributions
Mom+0.068
 crib+0.067
ara+0.063
 End+0.059
 Sunny+0.058
Neg logit contributions
vell-0.092
 disl-0.090
wheel-0.089
inations-0.089
asing-0.084
TokenGood
Token ID10248
Feature activation-6.81e-03

Pos logit contributions
 crib+0.045
ara+0.041
 mom+0.041
um+0.038
 Mom+0.037
Neg logit contributions
vell-0.066
wheel-0.066
 disl-0.059
inations-0.058
cher-0.058
Tokennight
Token ID3847
Feature activation+1.66e-01

Pos logit contributions
vell+0.016
wheel+0.016
ont+0.015
cast+0.015
 disl+0.015
Neg logit contributions
Mom-0.007
 crib-0.007
ara-0.006
 End-0.006
 Sunny-0.006
Token,
Token ID11
Feature activation+1.68e-02

Pos logit contributions
Mom+0.167
 crib+0.164
ara+0.164
 End+0.143
 beef+0.132
Neg logit contributions
vell-0.425
wheel-0.400
 disl-0.378
od-0.376
inations-0.375
Token Max
Token ID5436
Feature activation+2.06e-02

Pos logit contributions
 crib+0.019
ara+0.019
Mom+0.018
 mom+0.016
 Sunny+0.016
Neg logit contributions
vell-0.043
wheel-0.040
 disl-0.038
inations-0.038
od-0.037
Token.
Token ID13
Feature activation-1.32e-02

Pos logit contributions
 crib+0.034
ara+0.033
Mom+0.033
 mom+0.031
 Sunny+0.029
Neg logit contributions
vell-0.042
wheel-0.038
 disl-0.036
inations-0.035
od-0.035
Token Sleep
Token ID17376
Feature activation+1.89e-01

Pos logit contributions
vell+0.029
wheel+0.028
 disl+0.026
inations+0.025
od+0.025
Neg logit contributions
 crib-0.018
ara-0.017
Mom-0.016
 beef-0.015
 mom-0.015
Token tight
Token ID5381
Feature activation+9.14e-02

Pos logit contributions
Mom+0.261
 ham+0.236
 crib+0.235
 beef+0.234
 vet+0.229
Neg logit contributions
vell-0.412
wheel-0.372
inations-0.363
 disl-0.362
cast-0.355
Token."
Token ID526
Feature activation-2.51e-02

Pos logit contributions
Mom+0.138
ara+0.136
 crib+0.133
 mom+0.122
 End+0.122
Neg logit contributions
vell-0.192
wheel-0.178
 disl-0.168
inations-0.164
od-0.161
Token Max
Token ID5436
Feature activation+2.14e-02

Pos logit contributions
vell+0.059
wheel+0.057
 disl+0.054
inations+0.053
od+0.053
Neg logit contributions
 crib-0.031
ara-0.030
Mom-0.029
 mom-0.026
 End-0.026
Token fell
Token ID3214
Feature activation-3.37e-03

Pos logit contributions
 crib+0.034
Mom+0.032
ara+0.031
 beef+0.030
 kitten+0.030
Neg logit contributions
vell-0.039
wheel-0.038
inations-0.035
od-0.034
cast-0.034
Token asleep
Token ID16039
Feature activation-2.14e-02

Pos logit contributions
vell+0.006
wheel+0.006
cast+0.006
cher+0.005
smart+0.005
Neg logit contributions
ara-0.006
Mom-0.005
 End-0.005
 crib-0.005
 ham-0.005
TokenGood
Token ID10248
Feature activation-5.18e-03

Pos logit contributions
 crib+0.059
 mom+0.051
um+0.050
 eyes+0.050
 beef+0.050
Neg logit contributions
vell-0.080
wheel-0.078
 disl-0.071
cher-0.067
inations-0.066
Token night
Token ID1755
Feature activation+3.71e-02

Pos logit contributions
vell+0.011
wheel+0.011
 disl+0.010
od+0.010
ont+0.010
Neg logit contributions
 crib-0.006
Mom-0.006
 Sunny-0.006
 beef-0.006
ara-0.005
Token,
Token ID11
Feature activation+2.40e-02

Pos logit contributions
 crib+0.038
ara+0.037
Mom+0.037
 End+0.031
 beef+0.031
Neg logit contributions
vell-0.095
wheel-0.090
inations-0.086
od-0.085
 disl-0.084
Token doll
Token ID3654
Feature activation-2.31e-03

Pos logit contributions
Mom+0.029
ara+0.028
 crib+0.028
um+0.026
 brow+0.026
Neg logit contributions
vell-0.054
wheel-0.052
 disl-0.050
inations-0.046
od-0.046
Token.
Token ID13
Feature activation+5.83e-04

Pos logit contributions
vell+0.005
wheel+0.005
 disl+0.004
inations+0.004
od+0.004
Neg logit contributions
 crib-0.003
ara-0.003
Mom-0.003
 mom-0.003
 Sunny-0.003
Token Sleep
Token ID17376
Feature activation+1.89e-01

Pos logit contributions
 crib+0.001
ara+0.001
 beef+0.001
Mom+0.001
 chicken+0.001
Neg logit contributions
vell-0.001
wheel-0.001
 disl-0.001
od-0.001
cher-0.001
Token well
Token ID880
Feature activation+5.28e-02

Pos logit contributions
Mom+0.255
 beef+0.247
 ham+0.238
 crib+0.235
 cash+0.229
Neg logit contributions
vell-0.403
wheel-0.359
 disl-0.353
inations-0.352
cast-0.338
Token."
Token ID526
Feature activation-2.12e-02

Pos logit contributions
 crib+0.076
ara+0.075
Mom+0.074
 mom+0.069
 Sunny+0.066
Neg logit contributions
vell-0.117
wheel-0.108
 disl-0.102
inations-0.101
od-0.100
Token Lily
Token ID20037
Feature activation-1.56e-02

Pos logit contributions
 disl+0.040
wheel+0.039
vell+0.039
od+0.037
inations+0.036
Neg logit contributions
 crib-0.029
 End-0.027
Mom-0.027
 beef-0.027
ara-0.027
Token was
Token ID373
Feature activation+1.31e-02

Pos logit contributions
vell+0.030
wheel+0.029
inations+0.026
 disl+0.026
od+0.026
Neg logit contributions
 crib-0.025
Mom-0.023
ara-0.023
 beef-0.023
 kitten-0.022
Token happy
Token ID3772
Feature activation-3.34e-02

Pos logit contributions
ara+0.020
 crib+0.019
Mom+0.018
 ham+0.017
 beef+0.017
Neg logit contributions
vell-0.028
wheel-0.026
 disl-0.024
inations-0.024
od-0.024
Token dog
Token ID3290
Feature activation+3.46e-02

Pos logit contributions
 End+0.038
Mom+0.036
um+0.034
ara+0.033
 brow+0.033
Neg logit contributions
vell-0.082
wheel-0.072
od-0.070
ologist-0.069
 disl-0.067
Token named
Token ID3706
Feature activation+9.41e-03

Pos logit contributions
ara+0.057
 crib+0.056
Mom+0.054
 End+0.054
um+0.053
Neg logit contributions
vell-0.061
wheel-0.061
od-0.057
smart-0.056
 disl-0.055
Token Sleep
Token ID17376
Feature activation+1.88e-01

Pos logit contributions
 End+0.014
ara+0.013
 crib+0.013
um+0.012
Mom+0.012
Neg logit contributions
vell-0.019
wheel-0.018
 disl-0.017
od-0.016
inations-0.016
Tokeny
Token ID88
Feature activation+3.63e-02

Pos logit contributions
 beef+0.259
 ham+0.245
 crib+0.243
 cash+0.241
Mom+0.238
Neg logit contributions
vell-0.397
 disl-0.342
od-0.333
ont-0.327
wheel-0.323
Token.
Token ID13
Feature activation-8.39e-03

Pos logit contributions
ara+0.065
 crib+0.061
 End+0.061
Mom+0.060
 beef+0.060
Neg logit contributions
vell-0.056
od-0.051
wheel-0.051
 disl-0.045
ophone-0.045
Token Sleep
Token ID17376
Feature activation+1.88e-01

Pos logit contributions
wheel+0.014
vell+0.013
 achieve+0.013
smart+0.013
od+0.012
Neg logit contributions
 End-0.012
um-0.011
ara-0.011
 end-0.010
Mom-0.010
Tokeny
Token ID88
Feature activation+3.68e-02

Pos logit contributions
 beef+0.262
 crib+0.249
 cash+0.247
 vet+0.246
Mom+0.246
Neg logit contributions
vell-0.390
 disl-0.351
cast-0.333
wheel-0.331
ont-0.331
Token was
Token ID373
Feature activation+1.04e-02

Pos logit contributions
 crib+0.054
 beef+0.053
Mom+0.052
ara+0.052
um+0.048
Neg logit contributions
vell-0.069
wheel-0.067
od-0.065
 disl-0.063
inations-0.062
Token a
Token ID257
Feature activation+1.21e-02

Pos logit contributions
ara+0.020
�+0.017
 vet+0.016
 cash+0.016
Mom+0.016
Neg logit contributions
vell-0.017
 supposed-0.017
wheel-0.016
inations-0.015
od-0.015
Token very
Token ID845
Feature activation-1.39e-02

Pos logit contributions
ara+0.018
um+0.018
 End+0.017
 brow+0.017
 eyes+0.016
Neg logit contributions
vell-0.023
wheel-0.020
 disl-0.018
cest-0.018
inations-0.018
Token sleepy
Token ID42023
Feature activation-4.51e-03

Pos logit contributions
vell+0.029
 disl+0.026
inations+0.025
wheel+0.025
cast+0.022
Neg logit contributions
ara-0.021
Mom-0.021
 crib-0.020
 End-0.019
 cash-0.018
Token was
Token ID373
Feature activation+9.13e-03

Pos logit contributions
vell+0.049
od+0.047
wheel+0.047
 disl+0.045
 achieve+0.043
Neg logit contributions
 crib-0.029
Mom-0.027
ara-0.026
 beef-0.026
 ham-0.025
Token a
Token ID257
Feature activation+1.05e-02

Pos logit contributions
ara+0.014
 crib+0.013
 therapist+0.012
Mom+0.012
 nurse+0.012
Neg logit contributions
vell-0.017
wheel-0.016
od-0.016
 supposed-0.015
 disl-0.015
Token little
Token ID1310
Feature activation+3.54e-02

Pos logit contributions
 crib+0.012
ara+0.012
um+0.012
 brow+0.011
Mom+0.011
Neg logit contributions
vell-0.024
wheel-0.021
od-0.021
 disl-0.020
inations-0.020
Token dog
Token ID3290
Feature activation+3.46e-02

Pos logit contributions
 End+0.038
Mom+0.036
um+0.034
ara+0.033
 brow+0.033
Neg logit contributions
vell-0.082
wheel-0.072
od-0.070
ologist-0.069
 disl-0.067
Token named
Token ID3706
Feature activation+9.41e-03

Pos logit contributions
ara+0.057
 crib+0.056
Mom+0.054
 End+0.054
um+0.053
Neg logit contributions
vell-0.061
wheel-0.061
od-0.057
smart-0.056
 disl-0.055
Token Sleep
Token ID17376
Feature activation+1.88e-01

Pos logit contributions
 End+0.014
ara+0.013
 crib+0.013
um+0.012
Mom+0.012
Neg logit contributions
vell-0.019
wheel-0.018
 disl-0.017
od-0.016
inations-0.016
Tokeny
Token ID88
Feature activation+3.63e-02

Pos logit contributions
 beef+0.259
 ham+0.245
 crib+0.243
 cash+0.241
Mom+0.238
Neg logit contributions
vell-0.397
 disl-0.342
od-0.333
ont-0.327
wheel-0.323
Token.
Token ID13
Feature activation-8.39e-03

Pos logit contributions
ara+0.065
 crib+0.061
 End+0.061
Mom+0.060
 beef+0.060
Neg logit contributions
vell-0.056
od-0.051
wheel-0.051
 disl-0.045
ophone-0.045
Token Sleep
Token ID17376
Feature activation+1.88e-01

Pos logit contributions
wheel+0.014
vell+0.013
 achieve+0.013
smart+0.013
od+0.012
Neg logit contributions
 End-0.012
um-0.011
ara-0.011
 end-0.010
Mom-0.010
Tokeny
Token ID88
Feature activation+3.68e-02

Pos logit contributions
 beef+0.262
 crib+0.249
 cash+0.247
 vet+0.246
Mom+0.246
Neg logit contributions
vell-0.390
 disl-0.351
cast-0.333
wheel-0.331
ont-0.331
Token was
Token ID373
Feature activation+1.04e-02

Pos logit contributions
 crib+0.054
 beef+0.053
Mom+0.052
ara+0.052
um+0.048
Neg logit contributions
vell-0.069
wheel-0.067
od-0.065
 disl-0.063
inations-0.062
TokenGood
Token ID10248
Feature activation-9.91e-03

Pos logit contributions
 crib+0.046
ara+0.042
 mom+0.040
Mom+0.038
 Sunny+0.037
Neg logit contributions
vell-0.087
wheel-0.083
 disl-0.078
inations-0.076
od-0.076
Token night
Token ID1755
Feature activation+3.53e-02

Pos logit contributions
vell+0.023
wheel+0.022
 disl+0.021
od+0.020
inations+0.020
Neg logit contributions
 crib-0.013
Mom-0.012
ara-0.012
 Sunny-0.011
 mom-0.011
Token,
Token ID11
Feature activation+1.87e-02

Pos logit contributions
 crib+0.039
ara+0.038
Mom+0.037
 mom+0.034
 Sunny+0.032
Neg logit contributions
vell-0.091
wheel-0.085
 disl-0.081
inations-0.080
od-0.080
Token drum
Token ID13026
Feature activation-1.14e-01

Pos logit contributions
 crib+0.021
ara+0.021
Mom+0.020
 mom+0.019
 bunny+0.018
Neg logit contributions
vell-0.048
wheel-0.045
 disl-0.043
inations-0.043
od-0.042
Token.
Token ID13
Feature activation-2.41e-03

Pos logit contributions
vell+0.256
wheel+0.229
 disl+0.223
inations+0.222
od+0.219
Neg logit contributions
 crib-0.167
ara-0.163
Mom-0.154
 mom-0.153
 bunny-0.148
Token Sleep
Token ID17376
Feature activation+1.88e-01

Pos logit contributions
vell+0.006
wheel+0.006
inations+0.005
 disl+0.005
od+0.005
Neg logit contributions
 crib-0.003
ara-0.003
Mom-0.003
 mom-0.003
 Sunny-0.002
Token well
Token ID880
Feature activation+5.11e-02

Pos logit contributions
Mom+0.245
 crib+0.242
ara+0.234
 beef+0.222
 ham+0.222
Neg logit contributions
vell-0.426
wheel-0.386
inations-0.377
 disl-0.376
od-0.359
Token."
Token ID526
Feature activation-2.25e-02

Pos logit contributions
 crib+0.069
ara+0.067
Mom+0.064
 mom+0.061
 Sunny+0.059
Neg logit contributions
vell-0.120
wheel-0.110
 disl-0.105
od-0.104
inations-0.104
Token
Token ID198
Feature activation-1.11e-02

Pos logit contributions
vell+0.056
wheel+0.053
 disl+0.051
inations+0.050
od+0.050
Neg logit contributions
 crib-0.024
ara-0.024
Mom-0.023
 End-0.020
 mom-0.020
Token
Token ID198
Feature activation-1.06e-02

Pos logit contributions
vell+0.029
wheel+0.027
 disl+0.026
inations+0.026
od+0.026
Neg logit contributions
 crib-0.011
ara-0.011
Mom-0.010
 bunny-0.009
 mom-0.009
TokenThe
Token ID464
Feature activation+1.84e-02

Pos logit contributions
vell+0.024
wheel+0.023
 disl+0.022
inations+0.021
od+0.021
Neg logit contributions
 crib-0.015
ara-0.013
 mom-0.013
Mom-0.012
 bunny-0.012
Token you
Token ID345
Feature activation-2.26e-02

Pos logit contributions
 crib+0.011
ara+0.011
Mom+0.011
 mom+0.010
 bunny+0.010
Neg logit contributions
vell-0.020
wheel-0.018
 disl-0.018
inations-0.017
od-0.017
Token need
Token ID761
Feature activation+3.93e-03

Pos logit contributions
vell+0.051
wheel+0.047
 disl+0.047
od+0.045
cast+0.045
Neg logit contributions
 mom-0.032
Mom-0.030
 crib-0.030
 bunny-0.029
ara-0.029
Token to
Token ID284
Feature activation-5.76e-03

Pos logit contributions
ara+0.006
 crib+0.006
Mom+0.005
 End+0.005
um+0.005
Neg logit contributions
vell-0.008
wheel-0.008
 disl-0.007
inations-0.007
smart-0.007
Token sleep
Token ID3993
Feature activation+7.94e-02

Pos logit contributions
vell+0.012
wheel+0.011
 disl+0.011
inations+0.011
od+0.010
Neg logit contributions
 crib-0.009
ara-0.009
Mom-0.008
 mom-0.008
 Sunny-0.008
Token.
Token ID13
Feature activation-1.35e-02

Pos logit contributions
 crib+0.105
ara+0.104
Mom+0.101
 mom+0.094
 Sunny+0.090
Neg logit contributions
vell-0.187
wheel-0.172
 disl-0.163
inations-0.162
od-0.160
Token Sleep
Token ID17376
Feature activation+1.86e-01

Pos logit contributions
vell+0.027
wheel+0.026
 disl+0.025
asing+0.024
smart+0.023
Neg logit contributions
 crib-0.021
ara-0.020
Mom-0.019
 End-0.018
 blanket-0.018
Token will
Token ID481
Feature activation+2.80e-02

Pos logit contributions
 crib+0.237
Mom+0.237
ara+0.230
 mom+0.212
 beef+0.209
Neg logit contributions
vell-0.435
wheel-0.401
 disl-0.387
inations-0.381
od-0.371
Token help
Token ID1037
Feature activation-1.45e-02

Pos logit contributions
 crib+0.038
ara+0.037
Mom+0.037
 mom+0.035
 Sunny+0.034
Neg logit contributions
vell-0.065
wheel-0.059
 disl-0.057
od-0.056
inations-0.056
Token you
Token ID345
Feature activation-2.18e-02

Pos logit contributions
vell+0.038
wheel+0.036
inations+0.034
 disl+0.034
od+0.034
Neg logit contributions
 crib-0.015
ara-0.014
Mom-0.013
 End-0.012
 mom-0.012
Token feel
Token ID1254
Feature activation-5.23e-02

Pos logit contributions
vell+0.049
wheel+0.045
 disl+0.043
od+0.043
inations+0.042
Neg logit contributions
 crib-0.032
ara-0.030
Mom-0.030
 mom-0.029
 bunny-0.028
Token better
Token ID1365
Feature activation+2.69e-02

Pos logit contributions
vell+0.113
wheel+0.104
 disl+0.099
inations+0.098
od+0.093
Neg logit contributions
ara-0.079
 crib-0.078
Mom-0.075
 mom-0.069
 Sunny-0.067
Token house
Token ID2156
Feature activation-6.83e-03

Pos logit contributions
ara+0.002
Mom+0.002
 crib+0.002
 Sunny+0.002
um+0.002
Neg logit contributions
vell-0.004
 disl-0.003
wheel-0.003
inations-0.003
od-0.003
Token and
Token ID290
Feature activation+1.22e-02

Pos logit contributions
vell+0.017
wheel+0.016
od+0.015
 disl+0.015
inations+0.015
Neg logit contributions
 crib-0.008
ara-0.008
Mom-0.008
 mom-0.007
 Sunny-0.007
Token our
Token ID674
Feature activation+2.71e-03

Pos logit contributions
 crib+0.015
ara+0.015
Mom+0.015
 mom+0.013
 Sunny+0.013
Neg logit contributions
vell-0.029
wheel-0.027
 disl-0.026
inations-0.026
od-0.025
Token family
Token ID1641
Feature activation-1.38e-02

Pos logit contributions
ara+0.003
 crib+0.003
Mom+0.003
 Sunny+0.003
um+0.002
Neg logit contributions
vell-0.007
wheel-0.006
 disl-0.006
inations-0.006
od-0.006
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
vell+0.029
wheel+0.027
 disl+0.025
inations+0.025
od+0.025
Neg logit contributions
 crib-0.022
ara-0.021
Mom-0.021
 mom-0.020
 Sunny-0.019
Token Amen
Token ID34717
Feature activation+1.79e-01

Pos logit contributions
 crib+0.019
ara+0.019
 End+0.016
 blanket+0.016
um+0.016
Neg logit contributions
vell-0.028
 disl-0.027
wheel-0.026
od-0.024
smart-0.024
Token."
Token ID526
Feature activation-9.53e-03

Pos logit contributions
 crib+0.366
ara+0.350
 bunny+0.344
 beef+0.340
 Sunny+0.339
Neg logit contributions
vell-0.263
wheel-0.244
 disl-0.236
inations-0.234
od-0.229
Token
Token ID198
Feature activation+2.10e-03

Pos logit contributions
 disl+0.018
vell+0.018
od+0.018
wheel+0.017
 achieve+0.017
Neg logit contributions
 crib-0.013
 End-0.012
Mom-0.012
ara-0.012
 end-0.012
Token
Token ID198
Feature activation+1.85e-03

Pos logit contributions
 crib+0.003
ara+0.003
 bunny+0.003
 kitten+0.003
 brow+0.003
Neg logit contributions
vell-0.004
 disl-0.004
od-0.004
wheel-0.004
 achieve-0.004
TokenMom
Token ID29252
Feature activation+9.77e-02

Pos logit contributions
 crib+0.003
night+0.003
 eyes+0.003
 brow+0.003
 blanket+0.003
Neg logit contributions
 achieve-0.003
vell-0.003
 disl-0.003
od-0.003
wheel-0.003
Token smiled
Token ID13541
Feature activation+6.03e-02

Pos logit contributions
 crib+0.147
ara+0.130
Mom+0.127
 beef+0.125
 Sunny+0.125
Neg logit contributions
vell-0.211
wheel-0.200
od-0.184
inations-0.182
cher-0.181
Token family
Token ID1641
Feature activation-1.25e-02

Pos logit contributions
Mom+0.005
ara+0.004
um+0.004
 Goose+0.004
 Sunny+0.004
Neg logit contributions
vell-0.009
 disl-0.009
inations-0.008
cast-0.008
ologist-0.008
Token and
Token ID290
Feature activation+1.22e-02

Pos logit contributions
vell+0.026
wheel+0.024
inations+0.022
 disl+0.022
od+0.022
Neg logit contributions
 crib-0.020
ara-0.020
Mom-0.019
 mom-0.018
 Sunny-0.017
Token our
Token ID674
Feature activation+4.92e-03

Pos logit contributions
ara+0.014
 crib+0.013
Mom+0.013
um+0.012
 End+0.012
Neg logit contributions
vell-0.030
wheel-0.028
 disl-0.028
inations-0.027
cher-0.026
Token friends
Token ID2460
Feature activation-7.04e-02

Pos logit contributions
ara+0.007
Mom+0.006
um+0.006
 crib+0.005
 Sunny+0.005
Neg logit contributions
vell-0.011
 disl-0.010
inations-0.010
wheel-0.009
cast-0.009
Token.
Token ID13
Feature activation+1.27e-02

Pos logit contributions
vell+0.135
wheel+0.122
inations+0.114
 disl+0.114
od+0.112
Neg logit contributions
 crib-0.122
ara-0.121
Mom-0.118
 mom-0.110
 Sunny-0.108
Token Amen
Token ID34717
Feature activation+1.77e-01

Pos logit contributions
ara+0.017
 crib+0.016
um+0.015
 End+0.015
 basket+0.014
Neg logit contributions
vell-0.026
 disl-0.025
wheel-0.025
cher-0.023
smart-0.023
Token."
Token ID526
Feature activation-9.47e-03

Pos logit contributions
 crib+0.375
ara+0.364
 beef+0.355
 bunny+0.355
 kitten+0.351
Neg logit contributions
vell-0.242
wheel-0.224
inations-0.214
 disl-0.213
od-0.209
Token
Token ID198
Feature activation+1.62e-03

Pos logit contributions
 disl+0.015
od+0.014
smart+0.014
 achieve+0.014
wheel+0.014
Neg logit contributions
um-0.014
 crib-0.014
ara-0.014
 End-0.014
 kitten-0.014
Token
Token ID198
Feature activation+1.95e-03

Pos logit contributions
 crib+0.002
ara+0.002
 ham+0.002
 kitten+0.002
 bunny+0.002
Neg logit contributions
vell-0.003
 disl-0.003
wheel-0.003
 achieve-0.003
od-0.003
TokenAnna
Token ID31160
Feature activation+8.77e-02

Pos logit contributions
 eyes+0.003
 tum+0.003
 kitten+0.003
um+0.003
 Goose+0.003
Neg logit contributions
 achieve-0.004
vell-0.003
 disl-0.003
smart-0.003
wheel-0.003
Token said
Token ID531
Feature activation+2.11e-02

Pos logit contributions
 crib+0.142
 beef+0.132
Mom+0.129
ara+0.127
 kitten+0.124
Neg logit contributions
vell-0.169
wheel-0.157
od-0.147
 disl-0.144
inations-0.143
Token,
Token ID11
Feature activation+1.45e-02

Pos logit contributions
vell+0.021
wheel+0.019
 disl+0.019
od+0.019
smart+0.018
Neg logit contributions
Mom-0.010
ara-0.010
 crib-0.010
 End-0.009
 nurse-0.008
Token I
Token ID314
Feature activation+1.58e-02

Pos logit contributions
ara+0.018
 crib+0.018
Mom+0.017
 mom+0.016
um+0.015
Neg logit contributions
vell-0.035
wheel-0.032
 disl-0.031
inations-0.030
od-0.030
Token can
Token ID460
Feature activation-4.51e-02

Pos logit contributions
 mom+0.018
ara+0.018
Mom+0.018
 crib+0.017
 bunny+0.017
Neg logit contributions
vell-0.039
wheel-0.036
 disl-0.035
od-0.034
inations-0.034
Token help
Token ID1037
Feature activation-8.33e-03

Pos logit contributions
vell+0.096
wheel+0.088
 disl+0.084
inations+0.083
od+0.082
Neg logit contributions
 crib-0.069
ara-0.068
Mom-0.067
 mom-0.064
 bunny-0.061
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
vell+0.020
wheel+0.018
 disl+0.017
inations+0.017
od+0.017
Neg logit contributions
 crib-0.011
ara-0.011
Mom-0.011
 mom-0.010
 Sunny-0.010
Token Close
Token ID13872
Feature activation+1.77e-01

Pos logit contributions
vell+0.034
wheel+0.032
 disl+0.030
inations+0.029
od+0.029
Neg logit contributions
 crib-0.023
ara-0.023
Mom-0.021
 beef-0.020
 mom-0.020
Token your
Token ID534
Feature activation+1.64e-02

Pos logit contributions
 crib+0.239
ara+0.235
Mom+0.229
 mom+0.211
 Sunny+0.204
Neg logit contributions
vell-0.414
wheel-0.379
 disl-0.364
inations-0.360
od-0.356
Token eyes
Token ID2951
Feature activation+6.78e-02

Pos logit contributions
ara+0.024
Mom+0.021
 crib+0.019
Me+0.019
 Sunny+0.019
Neg logit contributions
vell-0.036
 disl-0.031
 achieve-0.031
inations-0.031
smart-0.031
Token and
Token ID290
Feature activation-1.26e-02

Pos logit contributions
 crib+0.061
ara+0.058
Mom+0.056
 mom+0.052
 Sunny+0.049
Neg logit contributions
vell-0.188
wheel-0.177
 disl-0.175
inations-0.169
od-0.168
Token make
Token ID787
Feature activation-1.61e-02

Pos logit contributions
vell+0.028
wheel+0.025
 disl+0.024
inations+0.024
od+0.023
Neg logit contributions
 crib-0.019
ara-0.018
Mom-0.018
 mom-0.016
 Sunny-0.016
Token a
Token ID257
Feature activation+1.35e-02

Pos logit contributions
vell+0.036
wheel+0.033
 disl+0.032
inations+0.031
od+0.031
Neg logit contributions
 crib-0.023
ara-0.022
Mom-0.022
 mom-0.021
 Sunny-0.021
Token Fl
Token ID1610
Feature activation+6.88e-02

Pos logit contributions
 crib+0.010
ara+0.010
 mom+0.010
Mom+0.010
 Sunny+0.010
Neg logit contributions
vell-0.022
wheel-0.020
 disl-0.020
inations-0.020
asing-0.019
Tokenoppy
Token ID26696
Feature activation-3.33e-02

Pos logit contributions
 crib+0.102
Mom+0.102
 Sunny+0.092
 beef+0.092
 nurse+0.090
Neg logit contributions
vell-0.148
od-0.132
wheel-0.127
asing-0.125
 disl-0.125
Token saw
Token ID2497
Feature activation-4.15e-02

Pos logit contributions
vell+0.084
wheel+0.076
 disl+0.074
inations+0.073
od+0.071
Neg logit contributions
ara-0.040
 crib-0.039
Mom-0.038
 mom-0.036
 bunny-0.034
Token a
Token ID257
Feature activation+7.22e-03

Pos logit contributions
vell+0.110
wheel+0.100
inations+0.098
 disl+0.096
od+0.095
Neg logit contributions
 crib-0.045
ara-0.042
 mom-0.042
Mom-0.041
 bunny-0.038
Token mar
Token ID1667
Feature activation-1.57e-01

Pos logit contributions
ara+0.009
 crib+0.009
Mom+0.009
 Sunny+0.008
um+0.008
Neg logit contributions
vell-0.017
wheel-0.015
inations-0.014
od-0.014
 disl-0.014
Tokenvell
Token ID29333
Feature activation-3.04e-01

Pos logit contributions
 disl+0.255
inations+0.179
wheel+0.176
smart+0.175
 supposed+0.171
Neg logit contributions
ara-0.324
um-0.321
Mom-0.306
 crib-0.303
 bunny-0.300
Tokenous
Token ID516
Feature activation-7.13e-02

Pos logit contributions
 disl+0.523
vell+0.450
inations+0.433
wheel+0.432
 achieve+0.420
Neg logit contributions
 crib-0.570
um-0.554
ara-0.543
 bunny-0.535
Mom-0.529
Token view
Token ID1570
Feature activation-2.81e-02

Pos logit contributions
vell+0.170
wheel+0.155
 disl+0.147
inations+0.147
od+0.144
Neg logit contributions
 crib-0.096
ara-0.092
Mom-0.087
 mom-0.085
 bunny-0.083
Token.
Token ID13
Feature activation-1.61e-02

Pos logit contributions
vell+0.074
 disl+0.068
wheel+0.067
inations+0.066
od+0.064
Neg logit contributions
 crib-0.030
ara-0.029
Mom-0.027
 mom-0.026
 Sunny-0.025
Token He
Token ID679
Feature activation-1.45e-02

Pos logit contributions
vell+0.035
wheel+0.033
 disl+0.031
od+0.031
cher+0.029
Neg logit contributions
 crib-0.022
ara-0.022
Mom-0.022
 End-0.020
 mom-0.020
Token also
Token ID635
Feature activation+3.83e-02

Pos logit contributions
vell+0.033
wheel+0.030
 disl+0.029
inations+0.029
od+0.029
Neg logit contributions
 crib-0.021
ara-0.020
Mom-0.019
 mom-0.018
 Sunny-0.018
Token,
Token ID11
Feature activation+1.29e-02

Pos logit contributions
 crib+0.004
ara+0.004
Mom+0.004
 mom+0.004
 Sunny+0.004
Neg logit contributions
vell-0.010
wheel-0.009
 disl-0.009
inations-0.009
od-0.009
Token laughed
Token ID13818
Feature activation+3.05e-02

Pos logit contributions
 crib+0.020
ara+0.019
Mom+0.019
 mom+0.019
 Sunny+0.018
Neg logit contributions
vell-0.028
wheel-0.025
od-0.024
 disl-0.024
inations-0.024
Token and
Token ID290
Feature activation-1.56e-02

Pos logit contributions
 crib+0.033
ara+0.033
Mom+0.031
 mom+0.028
 End+0.027
Neg logit contributions
vell-0.079
wheel-0.074
 disl-0.070
od-0.069
inations-0.069
Token built
Token ID3170
Feature activation-3.32e-02

Pos logit contributions
vell+0.036
wheel+0.032
inations+0.032
 disl+0.031
od+0.031
Neg logit contributions
 crib-0.021
 mom-0.021
Mom-0.021
ara-0.020
 Sunny-0.020
Token sand
Token ID6450
Feature activation-7.86e-02

Pos logit contributions
vell+0.083
wheel+0.077
 disl+0.074
od+0.072
inations+0.072
Neg logit contributions
ara-0.038
 crib-0.038
Mom-0.037
 mom-0.033
 Sunny-0.032
Tokencast
Token ID2701
Feature activation-2.98e-01

Pos logit contributions
vell+0.127
wheel+0.119
 disl+0.119
inations+0.115
asing+0.108
Neg logit contributions
 crib-0.153
 mom-0.151
ara-0.151
 bunny-0.142
Mom-0.142
Tokenles
Token ID829
Feature activation-7.39e-02

Pos logit contributions
vell+0.681
wheel+0.629
 disl+0.612
inations+0.581
od+0.570
Neg logit contributions
ara-0.439
 crib-0.415
Mom-0.392
 Sunny-0.376
 mom-0.374
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
vell+0.193
wheel+0.177
 disl+0.174
inations+0.171
od+0.165
Neg logit contributions
 crib-0.079
ara-0.075
Mom-0.071
 mom-0.070
 bunny-0.066
Token Soon
Token ID15894
Feature activation-1.30e-02

Pos logit contributions
vell+0.032
wheel+0.030
 disl+0.029
od+0.028
inations+0.028
Neg logit contributions
 crib-0.013
ara-0.013
Mom-0.012
 mom-0.011
 bunny-0.011
Token,
Token ID11
Feature activation+7.36e-03

Pos logit contributions
vell+0.037
wheel+0.034
 disl+0.033
inations+0.032
od+0.032
Neg logit contributions
 crib-0.012
ara-0.012
Mom-0.011
 mom-0.010
 Sunny-0.010
Token they
Token ID484
Feature activation-1.64e-02

Pos logit contributions
 crib+0.008
ara+0.008
Mom+0.007
 mom+0.007
 Sunny+0.007
Neg logit contributions
vell-0.019
wheel-0.018
 disl-0.017
inations-0.017
od-0.017
Token bucket
Token ID19236
Feature activation-5.05e-02

Pos logit contributions
vell+0.052
wheel+0.048
 disl+0.045
inations+0.044
od+0.043
Neg logit contributions
 crib-0.039
ara-0.038
Mom-0.037
 Sunny-0.035
 mom-0.035
Token.
Token ID13
Feature activation-1.94e-02

Pos logit contributions
vell+0.129
wheel+0.119
 disl+0.115
inations+0.114
od+0.112
Neg logit contributions
 crib-0.057
ara-0.055
Mom-0.054
 mom-0.050
 Sunny-0.047
Token She
Token ID1375
Feature activation-2.87e-03

Pos logit contributions
vell+0.052
wheel+0.049
 disl+0.047
od+0.047
inations+0.046
Neg logit contributions
 crib-0.019
ara-0.018
Mom-0.017
 mom-0.015
 bunny-0.015
Token made
Token ID925
Feature activation+2.00e-02

Pos logit contributions
vell+0.007
wheel+0.006
 disl+0.006
inations+0.006
od+0.006
Neg logit contributions
 crib-0.004
ara-0.004
Mom-0.004
 mom-0.003
 bunny-0.003
Token sand
Token ID6450
Feature activation-7.42e-02

Pos logit contributions
 crib+0.018
 mom+0.017
ara+0.016
Mom+0.016
 Mom+0.015
Neg logit contributions
vell-0.056
wheel-0.052
 disl-0.050
inations-0.050
ologist-0.050
Tokencast
Token ID2701
Feature activation-2.95e-01

Pos logit contributions
vell+0.115
wheel+0.111
 disl+0.110
inations+0.104
asing+0.102
Neg logit contributions
 mom-0.153
ara-0.148
Mom-0.145
 crib-0.144
 Mom-0.142
Tokenles
Token ID829
Feature activation-7.35e-02

Pos logit contributions
vell+0.638
wheel+0.583
 disl+0.561
inations+0.544
od+0.534
Neg logit contributions
ara-0.459
 crib-0.448
Mom-0.430
 mom-0.407
 Sunny-0.400
Token and
Token ID290
Feature activation-1.94e-02

Pos logit contributions
vell+0.211
wheel+0.193
 disl+0.193
inations+0.190
ologist+0.183
Neg logit contributions
 crib-0.060
ara-0.055
Mom-0.052
 mom-0.052
 bunny-0.048
Token sand
Token ID6450
Feature activation-7.45e-02

Pos logit contributions
vell+0.046
wheel+0.040
 disl+0.039
inations+0.038
ologist+0.038
Neg logit contributions
 crib-0.026
 mom-0.026
ara-0.026
Mom-0.025
 Mom-0.025
Token pies
Token ID47199
Feature activation-1.13e-01

Pos logit contributions
vell+0.166
wheel+0.158
 disl+0.157
inations+0.156
asing+0.148
Neg logit contributions
 mom-0.102
ara-0.101
 crib-0.098
 Mom-0.092
Mom-0.092
Token.
Token ID13
Feature activation-1.72e-02

Pos logit contributions
vell+0.335
 disl+0.325
inations+0.311
wheel+0.307
asing+0.307
Neg logit contributions
 mom-0.067
 crib-0.066
ara-0.065
Mom-0.060
 blanket-0.060
Token beach
Token ID10481
Feature activation-2.58e-02

Pos logit contributions
vell+0.072
wheel+0.066
 disl+0.061
od+0.061
 achieve+0.060
Neg logit contributions
 crib-0.040
ara-0.040
Mom-0.037
 Sunny-0.035
um-0.034
Token.
Token ID13
Feature activation-1.61e-02

Pos logit contributions
vell+0.075
wheel+0.069
 disl+0.068
inations+0.066
asing+0.065
Neg logit contributions
 crib-0.023
 mom-0.021
ara-0.021
Mom-0.019
 Mom-0.017
Token They
Token ID1119
Feature activation+1.72e-02

Pos logit contributions
vell+0.038
wheel+0.036
 disl+0.034
od+0.034
inations+0.033
Neg logit contributions
ara-0.019
 crib-0.019
Mom-0.019
 End-0.017
 mom-0.016
Token made
Token ID925
Feature activation+1.99e-02

Pos logit contributions
 crib+0.024
ara+0.023
Mom+0.022
 mom+0.021
 Sunny+0.020
Neg logit contributions
vell-0.040
wheel-0.037
inations-0.035
 disl-0.035
od-0.034
Token sand
Token ID6450
Feature activation-7.32e-02

Pos logit contributions
 crib+0.020
ara+0.019
 mom+0.018
Mom+0.018
 Mom+0.016
Neg logit contributions
vell-0.054
wheel-0.050
 disl-0.048
inations-0.047
ologist-0.047
Tokencast
Token ID2701
Feature activation-2.94e-01

Pos logit contributions
wheel+0.104
 disl+0.103
vell+0.099
asing+0.094
cher+0.088
Neg logit contributions
 mom-0.164
 crib-0.153
ara-0.153
Mom-0.151
 blanket-0.150
Tokenles
Token ID829
Feature activation-7.47e-02

Pos logit contributions
vell+0.648
wheel+0.594
 disl+0.578
inations+0.550
od+0.542
Neg logit contributions
ara-0.450
 crib-0.436
Mom-0.418
 mom-0.399
 Sunny-0.393
Token and
Token ID290
Feature activation-1.70e-02

Pos logit contributions
vell+0.226
 disl+0.213
wheel+0.210
inations+0.202
asing+0.197
Neg logit contributions
 crib-0.048
 mom-0.041
 bunny-0.037
ara-0.036
 Sunny-0.035
Token ran
Token ID4966
Feature activation-2.21e-02

Pos logit contributions
vell+0.040
wheel+0.035
 disl+0.035
asing+0.034
inations+0.034
Neg logit contributions
 mom-0.023
 crib-0.023
Mom-0.023
ara-0.022
 Mom-0.022
Token through
Token ID832
Feature activation-2.94e-02

Pos logit contributions
vell+0.057
wheel+0.051
 disl+0.050
asing+0.049
ologist+0.049
Neg logit contributions
 crib-0.027
 mom-0.025
ara-0.024
Mom-0.024
 Mom-0.023
Token the
Token ID262
Feature activation-2.95e-02

Pos logit contributions
vell+0.079
wheel+0.074
 disl+0.070
inations+0.070
od+0.068
Neg logit contributions
 crib-0.030
ara-0.029
Mom-0.028
 mom-0.027
 Sunny-0.025
Token while
Token ID981
Feature activation+1.02e-01

Pos logit contributions
 crib+0.002
ara+0.002
Mom+0.002
 mom+0.001
 Sunny+0.001
Neg logit contributions
vell-0.005
wheel-0.005
inations-0.005
 disl-0.004
od-0.004
Token,
Token ID11
Feature activation+3.94e-03

Pos logit contributions
 crib+0.102
ara+0.100
Mom+0.095
 mom+0.085
 Sunny+0.082
Neg logit contributions
vell-0.273
wheel-0.255
 disl-0.242
inations-0.242
od-0.241
Token then
Token ID788
Feature activation+6.24e-02

Pos logit contributions
 crib+0.005
ara+0.005
 mom+0.005
Mom+0.005
 bunny+0.004
Neg logit contributions
vell-0.010
wheel-0.009
 disl-0.009
inations-0.008
od-0.008
Token built
Token ID3170
Feature activation-3.61e-02

Pos logit contributions
 crib+0.087
ara+0.085
Mom+0.083
 mom+0.078
 Sunny+0.075
Neg logit contributions
vell-0.144
wheel-0.132
 disl-0.126
inations-0.125
od-0.124
Token sand
Token ID6450
Feature activation-7.41e-02

Pos logit contributions
vell+0.081
wheel+0.075
 disl+0.071
inations+0.070
od+0.070
Neg logit contributions
 crib-0.052
ara-0.051
Mom-0.049
 mom-0.046
 Sunny-0.044
Tokencast
Token ID2701
Feature activation-2.94e-01

Pos logit contributions
vell+0.086
 disl+0.083
wheel+0.080
inations+0.078
asing+0.072
Neg logit contributions
ara-0.178
 mom-0.177
 crib-0.177
Mom-0.169
 bunny-0.169
Tokenles
Token ID829
Feature activation-7.45e-02

Pos logit contributions
vell+0.644
wheel+0.591
 disl+0.574
inations+0.551
od+0.543
Neg logit contributions
ara-0.451
 crib-0.440
Mom-0.420
 mom-0.398
 Sunny-0.393
Token with
Token ID351
Feature activation+2.63e-02

Pos logit contributions
vell+0.206
 disl+0.188
wheel+0.188
inations+0.185
od+0.178
Neg logit contributions
 crib-0.069
ara-0.063
Mom-0.059
 mom-0.059
 bunny-0.057
Token his
Token ID465
Feature activation-1.98e-02

Pos logit contributions
 crib+0.033
ara+0.032
Mom+0.032
 mom+0.031
 Sunny+0.028
Neg logit contributions
vell-0.064
wheel-0.059
 disl-0.057
inations-0.056
od-0.055
Token mom
Token ID1995
Feature activation+3.08e-02

Pos logit contributions
vell+0.052
wheel+0.050
 disl+0.046
od+0.046
inations+0.046
Neg logit contributions
 crib-0.021
 mom-0.020
ara-0.020
Mom-0.019
 bunny-0.018
Token.
Token ID13
Feature activation-2.18e-02

Pos logit contributions
 crib+0.032
ara+0.031
Mom+0.031
 mom+0.030
 bunny+0.027
Neg logit contributions
vell-0.082
wheel-0.075
 disl-0.074
inations-0.073
od-0.070
Token't
Token ID470
Feature activation-4.82e-02

Pos logit contributions
vell+0.107
wheel+0.096
 disl+0.093
inations+0.093
od+0.091
Neg logit contributions
 crib-0.061
ara-0.060
Mom-0.059
 mom-0.055
 Sunny-0.053
Token wait
Token ID4043
Feature activation+4.12e-02

Pos logit contributions
vell+0.107
wheel+0.095
 disl+0.093
inations+0.091
od+0.090
Neg logit contributions
Mom-0.070
 crib-0.069
 mom-0.068
ara-0.067
 bunny-0.064
Token to
Token ID284
Feature activation-9.77e-03

Pos logit contributions
 crib+0.035
 mom+0.033
ara+0.032
Mom+0.030
 Mom+0.029
Neg logit contributions
vell-0.119
wheel-0.110
 disl-0.106
cher-0.103
ologist-0.103
Token make
Token ID787
Feature activation-2.64e-02

Pos logit contributions
vell+0.025
wheel+0.022
asing+0.022
cher+0.021
 disl+0.021
Neg logit contributions
 mom-0.012
 crib-0.012
Mom-0.011
 Mom-0.011
 bunny-0.011
Token sand
Token ID6450
Feature activation-7.12e-02

Pos logit contributions
vell+0.077
wheel+0.071
ologist+0.068
inations+0.068
cher+0.068
Neg logit contributions
 mom-0.022
 crib-0.022
ara-0.020
 Mom-0.020
 chicken-0.019
Tokencast
Token ID2701
Feature activation-2.94e-01

Pos logit contributions
 disl+0.084
wheel+0.084
vell+0.083
asing+0.081
inations+0.076
Neg logit contributions
 mom-0.164
 crib-0.156
 bunny-0.154
ara-0.153
 blanket-0.152
Tokenles
Token ID829
Feature activation-7.38e-02

Pos logit contributions
vell+0.654
wheel+0.598
 disl+0.578
inations+0.559
od+0.548
Neg logit contributions
ara-0.442
 crib-0.431
Mom-0.406
 Sunny-0.388
 mom-0.387
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
vell+0.196
wheel+0.178
 disl+0.178
inations+0.175
ologist+0.168
Neg logit contributions
 crib-0.076
ara-0.070
 mom-0.067
Mom-0.066
 bunny-0.065
Token
Token ID220
Feature activation-1.81e-03

Pos logit contributions
vell+0.034
wheel+0.032
 disl+0.031
inations+0.030
od+0.030
Neg logit contributions
 crib-0.011
ara-0.011
Mom-0.010
 mom-0.009
 Sunny-0.009
Token
Token ID198
Feature activation-2.56e-02

Pos logit contributions
vell+0.006
wheel+0.005
 disl+0.005
inations+0.005
ologist+0.005
Neg logit contributions
ara-0.001
Mom-0.001
 crib-0.001
 mom-0.001
 Mom-0.001
Token
Token ID198
Feature activation-2.53e-02

Pos logit contributions
vell+0.074
wheel+0.068
 disl+0.066
inations+0.066
od+0.065
Neg logit contributions
ara-0.021
Mom-0.021
 crib-0.021
 mom-0.018
 Sunny-0.017
Token play
Token ID711
Feature activation+9.55e-03

Pos logit contributions
vell+0.005
wheel+0.005
inations+0.004
asing+0.004
cher+0.004
Neg logit contributions
 crib-0.002
Mom-0.002
 mom-0.002
ara-0.002
 bunny-0.002
Token outside
Token ID2354
Feature activation+2.03e-02

Pos logit contributions
ara+0.013
 crib+0.012
Mom+0.012
 End+0.011
 mom+0.011
Neg logit contributions
vell-0.022
wheel-0.021
od-0.019
 disl-0.019
inations-0.019
Token and
Token ID290
Feature activation-1.40e-02

Pos logit contributions
ara+0.037
 End+0.031
Mom+0.031
 vet+0.031
 ham+0.031
Neg logit contributions
vell-0.035
wheel-0.033
od-0.033
cast-0.030
smart-0.030
Token make
Token ID787
Feature activation-2.23e-02

Pos logit contributions
vell+0.028
wheel+0.026
 disl+0.024
inations+0.024
od+0.024
Neg logit contributions
 crib-0.023
ara-0.023
Mom-0.022
 mom-0.021
 Sunny-0.020
Token sand
Token ID6450
Feature activation-7.20e-02

Pos logit contributions
vell+0.055
wheel+0.050
inations+0.048
 disl+0.047
cher+0.047
Neg logit contributions
 crib-0.029
ara-0.027
Mom-0.026
 mom-0.026
 bunny-0.024
Tokencast
Token ID2701
Feature activation-2.94e-01

Pos logit contributions
vell+0.098
 disl+0.098
wheel+0.096
asing+0.089
inations+0.088
Neg logit contributions
 mom-0.157
 crib-0.154
ara-0.152
Mom-0.151
 blanket-0.146
Tokenles
Token ID829
Feature activation-7.22e-02

Pos logit contributions
vell+0.591
wheel+0.536
 disl+0.502
inations+0.501
od+0.498
Neg logit contributions
 crib-0.492
ara-0.480
Mom-0.474
 mom-0.449
 Sunny-0.432
Token on
Token ID319
Feature activation-3.62e-02

Pos logit contributions
vell+0.178
wheel+0.165
 disl+0.157
inations+0.156
od+0.155
Neg logit contributions
 crib-0.088
ara-0.087
Mom-0.084
 mom-0.078
 Sunny-0.074
Token the
Token ID262
Feature activation-2.38e-02

Pos logit contributions
vell+0.092
wheel+0.086
 disl+0.083
od+0.082
inations+0.081
Neg logit contributions
 crib-0.039
ara-0.039
Mom-0.037
 mom-0.033
 End-0.032
Token beach
Token ID10481
Feature activation-2.55e-02

Pos logit contributions
vell+0.060
wheel+0.056
 disl+0.055
inations+0.055
asing+0.055
Neg logit contributions
 crib-0.028
Mom-0.027
 mom-0.026
ara-0.026
 bunny-0.024
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
vell+0.069
wheel+0.064
inations+0.062
 disl+0.062
cher+0.060
Neg logit contributions
 crib-0.026
ara-0.025
Mom-0.024
 mom-0.024
 Sunny-0.021
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
vell+0.139
wheel+0.128
 disl+0.127
inations+0.124
cher+0.121
Neg logit contributions
 crib-0.041
ara-0.039
Mom-0.039
 mom-0.037
 Mom-0.032
Token He
Token ID679
Feature activation-1.48e-02

Pos logit contributions
vell+0.045
wheel+0.042
 disl+0.040
inations+0.040
od+0.039
Neg logit contributions
 crib-0.019
ara-0.018
Mom-0.018
 mom-0.016
 Sunny-0.015
Token would
Token ID561
Feature activation+2.43e-02

Pos logit contributions
vell+0.036
wheel+0.033
 disl+0.032
inations+0.031
od+0.031
Neg logit contributions
 crib-0.019
ara-0.019
Mom-0.018
 mom-0.017
 Sunny-0.016
Token build
Token ID1382
Feature activation-1.03e-01

Pos logit contributions
 crib+0.036
ara+0.035
Mom+0.034
 mom+0.032
 Sunny+0.031
Neg logit contributions
vell-0.054
wheel-0.049
 disl-0.047
inations-0.046
od-0.046
Token sand
Token ID6450
Feature activation-7.20e-02

Pos logit contributions
vell+0.250
wheel+0.233
 disl+0.226
cher+0.225
inations+0.220
Neg logit contributions
 mom-0.133
 crib-0.131
ara-0.125
Mom-0.124
 Mom-0.123
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
 disl+0.104
vell+0.102
wheel+0.097
inations+0.093
asing+0.089
Neg logit contributions
 mom-0.159
ara-0.156
Mom-0.151
 crib-0.150
 Mom-0.148
Tokenles
Token ID829
Feature activation-7.32e-02

Pos logit contributions
vell+0.645
wheel+0.591
 disl+0.572
inations+0.552
od+0.540
Neg logit contributions
ara-0.450
 crib-0.438
Mom-0.419
 mom-0.397
 Sunny-0.392
Token and
Token ID290
Feature activation-1.52e-02

Pos logit contributions
vell+0.226
 disl+0.215
inations+0.208
wheel+0.206
cher+0.199
Neg logit contributions
 crib-0.042
 mom-0.037
Mom-0.034
ara-0.034
 bunny-0.033
Token collect
Token ID2824
Feature activation-9.64e-02

Pos logit contributions
vell+0.038
wheel+0.031
cher+0.031
asing+0.031
inations+0.031
Neg logit contributions
 mom-0.021
 crib-0.020
 Mom-0.020
 bunny-0.020
 one-0.020
Token seas
Token ID21547
Feature activation-5.64e-02

Pos logit contributions
vell+0.223
wheel+0.223
cher+0.211
 disl+0.210
inations+0.207
Neg logit contributions
ara-0.124
 mom-0.123
 pink-0.119
 ham-0.119
 one-0.117
Tokenhell
Token ID12758
Feature activation-1.41e-01

Pos logit contributions
vell+0.084
wheel+0.076
 disl+0.074
cher+0.070
asing+0.069
Neg logit contributions
ara-0.124
um-0.114
Mom-0.113
 mom-0.112
 crib-0.111
Token She
Token ID1375
Feature activation-6.99e-03

Pos logit contributions
wheel+0.035
 disl+0.033
od+0.032
vell+0.032
ooters+0.030
Neg logit contributions
Mom-0.019
 End-0.019
 crib-0.018
ara-0.018
 beef-0.018
Token liked
Token ID8288
Feature activation+3.40e-02

Pos logit contributions
vell+0.016
wheel+0.015
 disl+0.014
inations+0.014
od+0.014
Neg logit contributions
 crib-0.009
ara-0.009
Mom-0.009
 mom-0.008
 Sunny-0.008
Token to
Token ID284
Feature activation-2.94e-03

Pos logit contributions
 crib+0.030
 mom+0.028
Mom+0.027
ara+0.027
 chicken+0.025
Neg logit contributions
vell-0.099
wheel-0.091
inations-0.087
cher-0.087
 disl-0.086
Token build
Token ID1382
Feature activation-1.05e-01

Pos logit contributions
vell+0.008
asing+0.007
wheel+0.007
cher+0.007
od+0.007
Neg logit contributions
 mom-0.004
 crib-0.003
Mom-0.003
ara-0.003
 Mom-0.003
Token sand
Token ID6450
Feature activation-7.44e-02

Pos logit contributions
vell+0.257
wheel+0.245
cher+0.236
 disl+0.232
asing+0.229
Neg logit contributions
 mom-0.129
 crib-0.129
ara-0.123
 beef-0.119
 me-0.118
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
 disl+0.098
vell+0.097
wheel+0.094
inations+0.089
asing+0.085
Neg logit contributions
 mom-0.169
ara-0.167
 crib-0.162
Mom-0.162
um-0.158
Tokenles
Token ID829
Feature activation-7.30e-02

Pos logit contributions
vell+0.619
wheel+0.565
 disl+0.538
inations+0.528
od+0.518
Neg logit contributions
 crib-0.464
ara-0.464
Mom-0.445
 mom-0.422
 Sunny-0.411
Token and
Token ID290
Feature activation-1.53e-02

Pos logit contributions
vell+0.208
 disl+0.192
wheel+0.191
inations+0.188
cher+0.181
Neg logit contributions
 crib-0.062
ara-0.057
Mom-0.055
 mom-0.052
 bunny-0.049
Token collect
Token ID2824
Feature activation-9.82e-02

Pos logit contributions
vell+0.037
wheel+0.031
cher+0.030
asing+0.030
inations+0.030
Neg logit contributions
 crib-0.021
 mom-0.021
Mom-0.020
 bunny-0.020
ara-0.020
Token seas
Token ID21547
Feature activation-5.82e-02

Pos logit contributions
vell+0.217
wheel+0.214
cher+0.199
 disl+0.199
inations+0.199
Neg logit contributions
ara-0.139
 mom-0.135
 crib-0.135
 ham-0.131
 chicken-0.130
Tokenhell
Token ID12758
Feature activation-1.39e-01

Pos logit contributions
vell+0.086
wheel+0.077
 disl+0.075
cher+0.071
asing+0.070
Neg logit contributions
ara-0.128
Mom-0.119
um-0.119
 mom-0.117
 crib-0.115
Token the
Token ID262
Feature activation-2.39e-02

Pos logit contributions
vell+0.089
wheel+0.083
 disl+0.080
od+0.079
inations+0.078
Neg logit contributions
ara-0.041
 crib-0.041
Mom-0.040
 mom-0.035
 End-0.035
Token beach
Token ID10481
Feature activation-2.32e-02

Pos logit contributions
vell+0.056
wheel+0.052
 disl+0.049
inations+0.049
od+0.048
Neg logit contributions
 crib-0.031
ara-0.031
Mom-0.030
 mom-0.028
 Sunny-0.027
Token and
Token ID290
Feature activation-1.22e-02

Pos logit contributions
vell+0.064
wheel+0.060
 disl+0.058
inations+0.057
od+0.056
Neg logit contributions
 crib-0.022
ara-0.021
Mom-0.020
 mom-0.019
 Sunny-0.017
Token build
Token ID1382
Feature activation-1.05e-01

Pos logit contributions
vell+0.028
wheel+0.025
inations+0.024
 disl+0.024
od+0.024
Neg logit contributions
 crib-0.018
ara-0.017
Mom-0.017
 mom-0.017
 bunny-0.016
Token sand
Token ID6450
Feature activation-7.18e-02

Pos logit contributions
vell+0.229
wheel+0.214
 disl+0.203
cher+0.201
inations+0.200
Neg logit contributions
 crib-0.157
ara-0.156
 mom-0.153
Mom-0.149
 Mom-0.142
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
vell+0.083
 disl+0.082
wheel+0.078
inations+0.072
asing+0.069
Neg logit contributions
ara-0.173
 mom-0.173
 crib-0.171
Mom-0.169
 Mom-0.162
Tokenles
Token ID829
Feature activation-7.12e-02

Pos logit contributions
vell+0.590
wheel+0.535
 disl+0.501
inations+0.500
od+0.497
Neg logit contributions
 crib-0.490
ara-0.478
Mom-0.472
 mom-0.446
 Sunny-0.431
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
vell+0.185
wheel+0.171
 disl+0.167
inations+0.165
od+0.159
Neg logit contributions
 crib-0.078
ara-0.075
Mom-0.073
 mom-0.069
 bunny-0.064
Token But
Token ID887
Feature activation-7.74e-03

Pos logit contributions
wheel+0.027
od+0.026
 disl+0.026
vell+0.025
ooters+0.025
Neg logit contributions
 crib-0.014
 beef-0.014
 End-0.013
 therapist-0.013
 chicken-0.013
Token one
Token ID530
Feature activation+7.98e-02

Pos logit contributions
wheel+0.015
 disl+0.015
vell+0.015
od+0.015
asing+0.014
Neg logit contributions
 crib-0.009
 beef-0.009
ara-0.009
um-0.008
 waitress-0.008
Token day
Token ID1110
Feature activation+2.16e-02

Pos logit contributions
 crib+0.094
ara+0.093
Mom+0.089
 Sunny+0.087
 brow+0.083
Neg logit contributions
vell-0.172
wheel-0.169
od-0.163
ont-0.160
 disl-0.159
Token the
Token ID262
Feature activation-2.11e-02

Pos logit contributions
vell+0.016
wheel+0.014
inations+0.014
cher+0.014
 disl+0.013
Neg logit contributions
 crib-0.005
ara-0.005
Mom-0.005
 mom-0.005
 Mom-0.004
Token beach
Token ID10481
Feature activation-2.47e-02

Pos logit contributions
vell+0.052
wheel+0.049
 disl+0.047
od+0.046
inations+0.045
Neg logit contributions
 crib-0.025
ara-0.024
Mom-0.023
 mom-0.021
 Sunny-0.021
Token and
Token ID290
Feature activation-1.24e-02

Pos logit contributions
vell+0.064
wheel+0.060
od+0.057
 disl+0.057
inations+0.057
Neg logit contributions
 crib-0.026
ara-0.026
Mom-0.025
 mom-0.022
 Sunny-0.022
Token building
Token ID2615
Feature activation-8.06e-02

Pos logit contributions
vell+0.028
wheel+0.026
 disl+0.025
inations+0.025
od+0.024
Neg logit contributions
 crib-0.017
ara-0.017
Mom-0.017
 mom-0.016
 Sunny-0.015
Token sand
Token ID6450
Feature activation-7.14e-02

Pos logit contributions
vell+0.203
wheel+0.188
inations+0.179
 disl+0.179
cher+0.176
Neg logit contributions
 crib-0.097
ara-0.095
Mom-0.093
 mom-0.091
 Mom-0.083
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
vell+0.120
 disl+0.117
wheel+0.114
inations+0.113
asing+0.105
Neg logit contributions
ara-0.137
 mom-0.136
 crib-0.136
Mom-0.132
um-0.127
Tokenles
Token ID829
Feature activation-7.11e-02

Pos logit contributions
vell+0.582
wheel+0.527
inations+0.493
 disl+0.492
od+0.491
Neg logit contributions
 crib-0.496
ara-0.481
Mom-0.478
 mom-0.452
 Sunny-0.437
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
vell+0.178
wheel+0.165
 disl+0.158
inations+0.157
od+0.154
Neg logit contributions
 crib-0.084
ara-0.082
Mom-0.080
 mom-0.074
 Sunny-0.070
Token One
Token ID1881
Feature activation+1.05e-01

Pos logit contributions
wheel+0.029
 disl+0.028
od+0.028
ooters+0.027
vell+0.027
Neg logit contributions
 crib-0.016
 beef-0.015
 therapist-0.015
 End-0.015
Mom-0.014
Token day
Token ID1110
Feature activation+2.19e-02

Pos logit contributions
 crib+0.113
ara+0.106
 Sunny+0.098
Mom+0.098
 kitten+0.090
Neg logit contributions
vell-0.259
wheel-0.250
 disl-0.240
od-0.236
inations-0.235
Token,
Token ID11
Feature activation+1.62e-02

Pos logit contributions
 crib+0.034
 vet+0.032
Mom+0.031
 Amen+0.031
ara+0.030
Neg logit contributions
vell-0.039
wheel-0.039
od-0.038
 disl-0.035
smart-0.035
Token the
Token ID262
Feature activation-2.51e-02

Pos logit contributions
ara+0.025
 crib+0.025
Mom+0.023
 Sunny+0.021
 bunny+0.021
Neg logit contributions
vell-0.048
wheel-0.045
 disl-0.043
inations-0.042
od-0.042
Token waves
Token ID9813
Feature activation-4.81e-02

Pos logit contributions
vell+0.055
wheel+0.050
 disl+0.048
inations+0.047
od+0.046
Neg logit contributions
 crib-0.038
ara-0.037
Mom-0.036
 mom-0.034
 Sunny-0.033
Token and
Token ID290
Feature activation-1.60e-02

Pos logit contributions
vell+0.123
wheel+0.113
 disl+0.110
inations+0.109
od+0.107
Neg logit contributions
 crib-0.054
ara-0.053
Mom-0.051
 mom-0.048
 bunny-0.045
Token built
Token ID3170
Feature activation-3.66e-02

Pos logit contributions
vell+0.039
wheel+0.034
 disl+0.034
inations+0.033
ologist+0.033
Neg logit contributions
 mom-0.020
 crib-0.020
Mom-0.020
ara-0.019
 Mom-0.019
Token sand
Token ID6450
Feature activation-7.26e-02

Pos logit contributions
vell+0.097
wheel+0.090
 disl+0.086
inations+0.085
od+0.084
Neg logit contributions
 crib-0.038
ara-0.037
Mom-0.036
 mom-0.033
 Sunny-0.031
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
vell+0.078
 disl+0.076
wheel+0.074
inations+0.068
asing+0.066
Neg logit contributions
ara-0.178
 crib-0.177
 mom-0.175
Mom-0.168
 blanket-0.167
Tokenles
Token ID829
Feature activation-7.26e-02

Pos logit contributions
vell+0.699
 disl+0.649
wheel+0.647
ologist+0.602
asing+0.597
Neg logit contributions
ara-0.401
 crib-0.368
Mom-0.339
 Sunny-0.335
 bunny-0.332
Token.
Token ID13
Feature activation-1.71e-02

Pos logit contributions
vell+0.193
wheel+0.177
 disl+0.174
inations+0.173
ologist+0.167
Neg logit contributions
 crib-0.073
ara-0.066
 mom-0.064
Mom-0.062
 bunny-0.062
Token
Token ID198
Feature activation-2.60e-02

Pos logit contributions
vell+0.047
wheel+0.044
inations+0.042
 disl+0.042
cher+0.041
Neg logit contributions
 crib-0.016
Mom-0.016
ara-0.016
 mom-0.015
 Mom-0.014
Token
Token ID198
Feature activation-2.58e-02

Pos logit contributions
vell+0.075
wheel+0.070
 disl+0.067
inations+0.066
od+0.065
Neg logit contributions
 crib-0.022
Mom-0.021
ara-0.021
 mom-0.019
 Sunny-0.017
TokenM
Token ID44
Feature activation+4.61e-02

Pos logit contributions
vell+0.057
wheel+0.053
 disl+0.050
inations+0.049
od+0.049
Neg logit contributions
 crib-0.038
ara-0.037
Mom-0.036
 mom-0.034
 Sunny-0.033
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
vell+0.073
wheel+0.068
 disl+0.066
inations+0.065
od+0.064
Neg logit contributions
 crib-0.032
ara-0.031
Mom-0.030
 mom-0.029
 bunny-0.026
Token They
Token ID1119
Feature activation+2.05e-02

Pos logit contributions
vell+0.036
wheel+0.036
 disl+0.035
od+0.033
ount+0.033
Neg logit contributions
 crib-0.017
ara-0.016
 End-0.015
Mom-0.015
 bunny-0.015
Token would
Token ID561
Feature activation+2.42e-02

Pos logit contributions
 crib+0.026
ara+0.025
Mom+0.025
 mom+0.023
 Sunny+0.022
Neg logit contributions
vell-0.051
wheel-0.047
 disl-0.045
inations-0.044
od-0.044
Token build
Token ID1382
Feature activation-1.05e-01

Pos logit contributions
 crib+0.034
ara+0.033
Mom+0.032
 mom+0.030
 Sunny+0.029
Neg logit contributions
vell-0.056
wheel-0.051
 disl-0.049
inations-0.048
od-0.048
Token sand
Token ID6450
Feature activation-7.30e-02

Pos logit contributions
vell+0.260
wheel+0.249
 disl+0.238
cher+0.234
inations+0.228
Neg logit contributions
 crib-0.127
 mom-0.125
ara-0.125
Mom-0.118
 Mom-0.118
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
 disl+0.098
vell+0.094
wheel+0.094
asing+0.082
cher+0.081
Neg logit contributions
 mom-0.169
ara-0.169
Mom-0.161
 crib-0.160
 Mom-0.157
Tokenles
Token ID829
Feature activation-7.15e-02

Pos logit contributions
vell+0.637
wheel+0.585
 disl+0.563
inations+0.544
od+0.535
Neg logit contributions
ara-0.452
 crib-0.443
Mom-0.423
 mom-0.403
 Sunny-0.395
Token and
Token ID290
Feature activation-1.36e-02

Pos logit contributions
vell+0.223
 disl+0.213
wheel+0.208
inations+0.202
cher+0.197
Neg logit contributions
 crib-0.038
 mom-0.034
ara-0.031
Mom-0.030
 chicken-0.029
Token swim
Token ID9422
Feature activation+8.03e-03

Pos logit contributions
vell+0.033
wheel+0.029
asing+0.028
cher+0.028
smart+0.027
Neg logit contributions
 mom-0.018
 crib-0.018
 Mom-0.017
Mom-0.017
 ham-0.017
Token in
Token ID287
Feature activation+1.99e-02

Pos logit contributions
 crib+0.007
 mom+0.007
ara+0.007
Mom+0.007
 Mom+0.006
Neg logit contributions
vell-0.022
wheel-0.022
 disl-0.021
inations-0.020
ologist-0.020
Token the
Token ID262
Feature activation-2.31e-02

Pos logit contributions
 crib+0.021
ara+0.021
Mom+0.020
 mom+0.019
 Sunny+0.017
Neg logit contributions
vell-0.053
wheel-0.049
 disl-0.047
inations-0.046
od-0.046
Token She
Token ID1375
Feature activation-6.22e-03

Pos logit contributions
vell+0.034
wheel+0.033
 disl+0.033
od+0.032
 achieve+0.029
Neg logit contributions
ara-0.019
Mom-0.018
 crib-0.018
 End-0.017
 bunny-0.016
Token saw
Token ID2497
Feature activation-3.77e-02

Pos logit contributions
vell+0.017
wheel+0.015
 disl+0.015
od+0.014
inations+0.014
Neg logit contributions
ara-0.006
 mom-0.006
 crib-0.006
Mom-0.006
 Mom-0.005
Token shells
Token ID19679
Feature activation-1.14e-01

Pos logit contributions
vell+0.100
wheel+0.093
inations+0.089
 disl+0.089
od+0.086
Neg logit contributions
 crib-0.040
ara-0.038
Mom-0.038
 mom-0.036
 bunny-0.033
Token,
Token ID11
Feature activation+1.19e-02

Pos logit contributions
vell+0.338
 disl+0.319
wheel+0.317
inations+0.307
asing+0.297
Neg logit contributions
 crib-0.078
ara-0.075
Mom-0.069
 mom-0.068
 bunny-0.065
Token sand
Token ID6450
Feature activation-7.07e-02

Pos logit contributions
 chicken+0.018
 mom+0.018
 ham+0.017
 bunny+0.017
Mom+0.017
Neg logit contributions
vell-0.026
wheel-0.024
 disl-0.022
cher-0.022
inations-0.021
Tokencast
Token ID2701
Feature activation-2.93e-01

Pos logit contributions
vell+0.214
wheel+0.210
 disl+0.203
inations+0.199
cher+0.193
Neg logit contributions
ara-0.045
 mom-0.042
 crib-0.041
Mom-0.035
 eyes-0.033
Tokenles
Token ID829
Feature activation-7.18e-02

Pos logit contributions
vell+0.646
wheel+0.597
 disl+0.576
inations+0.552
od+0.541
Neg logit contributions
ara-0.446
 crib-0.429
Mom-0.410
 mom-0.390
 Sunny-0.387
Token and
Token ID290
Feature activation-1.37e-02

Pos logit contributions
vell+0.214
wheel+0.199
 disl+0.199
inations+0.192
cher+0.187
Neg logit contributions
 crib-0.048
ara-0.044
 mom-0.041
Mom-0.040
 bunny-0.038
Token se
Token ID384
Feature activation-1.22e-01

Pos logit contributions
vell+0.033
wheel+0.029
 disl+0.028
inations+0.028
cher+0.027
Neg logit contributions
 crib-0.018
 mom-0.018
Mom-0.017
 bunny-0.017
ara-0.017
Tokenag
Token ID363
Feature activation+4.68e-02

Pos logit contributions
vell+0.213
wheel+0.183
 achieve+0.169
 disl+0.165
cher+0.163
Neg logit contributions
ara-0.244
Mom-0.225
 crib-0.224
um-0.222
 beef-0.211
Tokenull
Token ID724
Feature activation-9.00e-02

Pos logit contributions
Mom+0.086
 crib+0.084
ara+0.083
 mom+0.083
 Mom+0.079
Neg logit contributions
vell-0.086
wheel-0.080
 disl-0.072
cher-0.072
inations-0.071
Token each
Token ID1123
Feature activation+2.34e-02

Pos logit contributions
vell+0.118
wheel+0.113
inations+0.105
 disl+0.105
cher+0.103
Neg logit contributions
 crib-0.062
ara-0.061
 mom-0.059
Mom-0.058
 Mom-0.055
Token other
Token ID584
Feature activation-4.13e-02

Pos logit contributions
 crib+0.032
ara+0.032
Mom+0.031
 Sunny+0.028
 mom+0.028
Neg logit contributions
vell-0.053
wheel-0.049
inations-0.046
od-0.046
 disl-0.046
Token and
Token ID290
Feature activation-1.60e-02

Pos logit contributions
vell+0.102
wheel+0.096
 disl+0.092
inations+0.090
cher+0.088
Neg logit contributions
 crib-0.052
ara-0.049
 mom-0.047
Mom-0.047
 bunny-0.045
Token making
Token ID1642
Feature activation-2.80e-02

Pos logit contributions
vell+0.036
wheel+0.033
od+0.031
inations+0.030
cher+0.030
Neg logit contributions
 crib-0.024
 mom-0.023
Mom-0.022
ara-0.022
 Mom-0.021
Token sand
Token ID6450
Feature activation-7.30e-02

Pos logit contributions
vell+0.068
wheel+0.063
cher+0.059
inations+0.059
 disl+0.058
Neg logit contributions
 crib-0.036
ara-0.034
 mom-0.034
Mom-0.033
 Mom-0.032
Tokencast
Token ID2701
Feature activation-2.92e-01

Pos logit contributions
wheel+0.105
 disl+0.102
vell+0.102
asing+0.097
cher+0.094
Neg logit contributions
 mom-0.156
 crib-0.146
 blanket-0.145
ara-0.144
 Mom-0.144
Tokenles
Token ID829
Feature activation-7.10e-02

Pos logit contributions
vell+0.691
wheel+0.639
 disl+0.627
inations+0.589
ologist+0.586
Neg logit contributions
ara-0.410
 crib-0.379
 Sunny-0.351
Mom-0.348
 bunny-0.341
Token.
Token ID13
Feature activation-1.80e-02

Pos logit contributions
vell+0.203
wheel+0.189
 disl+0.186
inations+0.184
ologist+0.178
Neg logit contributions
 crib-0.056
 mom-0.051
 bunny-0.046
 chicken-0.046
 blanket-0.044
Token
Token ID220
Feature activation-2.68e-03

Pos logit contributions
vell+0.049
wheel+0.046
 disl+0.044
inations+0.044
od+0.043
Neg logit contributions
 crib-0.017
ara-0.017
Mom-0.016
 mom-0.014
 Sunny-0.014
Token
Token ID198
Feature activation-2.78e-02

Pos logit contributions
vell+0.009
wheel+0.008
 disl+0.008
inations+0.008
ologist+0.008
Neg logit contributions
Mom-0.001
ara-0.001
 mom-0.001
 crib-0.001
 Mom-0.001
Token
Token ID198
Feature activation-2.76e-02

Pos logit contributions
vell+0.070
wheel+0.066
od+0.064
inations+0.064
 disl+0.063
Neg logit contributions
 crib-0.031
ara-0.028
Mom-0.026
 mom-0.025
 bunny-0.025
Token She
Token ID1375
Feature activation-7.83e-03

Pos logit contributions
wheel+0.035
 disl+0.033
vell+0.033
od+0.032
ooters+0.030
Neg logit contributions
Mom-0.019
 crib-0.019
 End-0.018
 beef-0.018
ara-0.018
Token liked
Token ID8288
Feature activation+3.31e-02

Pos logit contributions
vell+0.019
wheel+0.018
 disl+0.017
inations+0.017
od+0.016
Neg logit contributions
 crib-0.010
ara-0.010
Mom-0.009
 mom-0.009
 Sunny-0.008
Token to
Token ID284
Feature activation-4.67e-03

Pos logit contributions
 crib+0.030
 mom+0.027
ara+0.026
Mom+0.026
 bunny+0.024
Neg logit contributions
vell-0.096
wheel-0.088
inations-0.085
cher-0.084
 disl-0.083
Token build
Token ID1382
Feature activation-1.05e-01

Pos logit contributions
vell+0.012
asing+0.011
od+0.011
cher+0.011
wheel+0.011
Neg logit contributions
 mom-0.005
 crib-0.005
Mom-0.005
 Mom-0.005
ara-0.005
Token sand
Token ID6450
Feature activation-7.24e-02

Pos logit contributions
vell+0.249
wheel+0.236
cher+0.228
 disl+0.224
asing+0.220
Neg logit contributions
 mom-0.135
 crib-0.133
ara-0.131
 me-0.126
 Mom-0.125
Tokencast
Token ID2701
Feature activation-2.92e-01

Pos logit contributions
 disl+0.092
vell+0.090
wheel+0.087
inations+0.082
asing+0.079
Neg logit contributions
 mom-0.168
ara-0.167
 crib-0.161
Mom-0.161
um-0.157
Tokenles
Token ID829
Feature activation-7.22e-02

Pos logit contributions
vell+0.615
wheel+0.562
 disl+0.535
inations+0.525
od+0.516
Neg logit contributions
 crib-0.462
ara-0.462
Mom-0.443
 mom-0.420
 Sunny-0.409
Token and
Token ID290
Feature activation-1.53e-02

Pos logit contributions
vell+0.204
 disl+0.188
wheel+0.188
inations+0.185
cher+0.177
Neg logit contributions
 crib-0.063
ara-0.058
Mom-0.056
 mom-0.053
 bunny-0.050
Token collect
Token ID2824
Feature activation-9.70e-02

Pos logit contributions
vell+0.037
wheel+0.032
cher+0.031
asing+0.030
inations+0.030
Neg logit contributions
 crib-0.021
 mom-0.021
Mom-0.020
 bunny-0.020
 Mom-0.020
Token seas
Token ID21547
Feature activation-5.69e-02

Pos logit contributions
vell+0.210
wheel+0.208
cher+0.194
 disl+0.192
ologist+0.191
Neg logit contributions
ara-0.142
 mom-0.138
 crib-0.135
 ham-0.134
 pink-0.134
Tokenhell
Token ID12758
Feature activation-1.38e-01

Pos logit contributions
vell+0.084
wheel+0.076
 disl+0.073
cher+0.070
asing+0.068
Neg logit contributions
ara-0.126
um-0.115
Mom-0.115
 mom-0.114
 crib-0.113
Token building
Token ID2615
Feature activation-8.20e-02

Pos logit contributions
 crib+0.022
 mom+0.020
ara+0.020
Mom+0.020
 bunny+0.019
Neg logit contributions
vell-0.044
 disl-0.041
wheel-0.041
cher-0.037
inations-0.037
Token the
Token ID262
Feature activation-2.23e-02

Pos logit contributions
vell+0.232
wheel+0.211
 disl+0.211
inations+0.204
asing+0.203
Neg logit contributions
 crib-0.076
 mom-0.068
ara-0.064
Mom-0.061
 Mom-0.057
Token most
Token ID749
Feature activation-8.79e-02

Pos logit contributions
vell+0.050
wheel+0.045
 disl+0.043
inations+0.042
od+0.041
Neg logit contributions
ara-0.031
 crib-0.031
Mom-0.030
 Sunny-0.028
 mom-0.027
Token beautiful
Token ID4950
Feature activation-1.92e-02

Pos logit contributions
vell+0.198
wheel+0.182
 disl+0.173
inations+0.171
od+0.169
Neg logit contributions
 crib-0.127
ara-0.125
Mom-0.122
 mom-0.115
 bunny-0.110
Token sand
Token ID6450
Feature activation-7.19e-02

Pos logit contributions
vell+0.049
wheel+0.046
 disl+0.044
inations+0.044
od+0.043
Neg logit contributions
 crib-0.021
ara-0.021
Mom-0.020
 mom-0.018
 Sunny-0.018
Tokencast
Token ID2701
Feature activation-2.92e-01

Pos logit contributions
vell+0.189
 disl+0.182
wheel+0.181
inations+0.174
asing+0.169
Neg logit contributions
 crib-0.071
 mom-0.066
ara-0.065
Mom-0.060
 bunny-0.060
Tokenles
Token ID829
Feature activation-7.18e-02

Pos logit contributions
vell+0.603
wheel+0.549
 disl+0.519
inations+0.513
od+0.507
Neg logit contributions
 crib-0.473
ara-0.468
Mom-0.454
 mom-0.429
 Sunny-0.417
Token on
Token ID319
Feature activation-3.79e-02

Pos logit contributions
vell+0.187
wheel+0.173
 disl+0.167
inations+0.165
od+0.162
Neg logit contributions
 crib-0.078
ara-0.075
Mom-0.072
 mom-0.067
 Sunny-0.064
Token the
Token ID262
Feature activation-2.32e-02

Pos logit contributions
vell+0.088
wheel+0.081
od+0.078
 disl+0.077
inations+0.075
Neg logit contributions
ara-0.047
 crib-0.046
Mom-0.045
 End-0.041
 ham-0.040
Token beach
Token ID10481
Feature activation-2.40e-02

Pos logit contributions
vell+0.052
wheel+0.048
 disl+0.045
inations+0.045
od+0.045
Neg logit contributions
 crib-0.034
ara-0.033
Mom-0.032
 mom-0.030
 Sunny-0.029
Token.
Token ID13
Feature activation-1.83e-02

Pos logit contributions
vell+0.065
wheel+0.060
 disl+0.058
inations+0.058
asing+0.056
Neg logit contributions
 crib-0.024
ara-0.023
 mom-0.021
Mom-0.021
 bunny-0.019
Token took
Token ID1718
Feature activation-3.27e-02

Pos logit contributions
 crib+0.080
ara+0.079
Mom+0.076
 mom+0.071
 Sunny+0.068
Neg logit contributions
vell-0.147
wheel-0.135
 disl-0.129
inations-0.128
od-0.126
Token time
Token ID640
Feature activation+9.47e-04

Pos logit contributions
vell+0.090
wheel+0.083
 disl+0.082
inations+0.080
ologist+0.079
Neg logit contributions
 mom-0.030
Mom-0.030
 crib-0.030
ara-0.030
 Mom-0.028
Token to
Token ID284
Feature activation-5.57e-03

Pos logit contributions
 crib+0.001
ara+0.001
Mom+0.001
 mom+0.001
 Sunny+0.001
Neg logit contributions
vell-0.002
wheel-0.002
 disl-0.002
inations-0.002
od-0.002
Token make
Token ID787
Feature activation-2.10e-02

Pos logit contributions
vell+0.015
asing+0.013
wheel+0.013
cher+0.013
inations+0.013
Neg logit contributions
 mom-0.007
 crib-0.006
 Mom-0.006
Mom-0.006
 end-0.006
Token sand
Token ID6450
Feature activation-6.99e-02

Pos logit contributions
vell+0.061
wheel+0.055
cher+0.054
ologist+0.054
asing+0.053
Neg logit contributions
 mom-0.020
 Mom-0.017
 one-0.017
 chicken-0.017
 crib-0.016
Tokencast
Token ID2701
Feature activation-2.91e-01

Pos logit contributions
wheel+0.102
vell+0.102
 disl+0.099
asing+0.095
inations+0.091
Neg logit contributions
 mom-0.144
 crib-0.134
 eyes-0.133
 Mom-0.132
 blanket-0.132
Tokenles
Token ID829
Feature activation-7.02e-02

Pos logit contributions
vell+0.689
wheel+0.641
 disl+0.632
inations+0.590
ologist+0.588
Neg logit contributions
ara-0.399
 crib-0.372
 Sunny-0.345
 bunny-0.342
Mom-0.341
Token and
Token ID290
Feature activation-1.63e-02

Pos logit contributions
vell+0.207
 disl+0.190
wheel+0.190
inations+0.186
asing+0.182
Neg logit contributions
 crib-0.048
 mom-0.044
 bunny-0.040
 Sunny-0.036
 blanket-0.036
Token feel
Token ID1254
Feature activation-5.57e-02

Pos logit contributions
vell+0.040
wheel+0.035
 disl+0.034
od+0.034
inations+0.033
Neg logit contributions
 mom-0.020
 crib-0.020
 Mom-0.019
Mom-0.019
 bunny-0.019
Token the
Token ID262
Feature activation-2.20e-02

Pos logit contributions
vell+0.145
wheel+0.133
ologist+0.130
inations+0.128
od+0.128
Neg logit contributions
 crib-0.061
Mom-0.056
 mom-0.056
 Mom-0.053
 bunny-0.053
Token waves
Token ID9813
Feature activation-4.54e-02

Pos logit contributions
vell+0.054
wheel+0.051
 disl+0.048
od+0.048
inations+0.048
Neg logit contributions
 crib-0.027
ara-0.026
Mom-0.026
 mom-0.025
 bunny-0.023
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
 crib+0.019
ara+0.017
Mom+0.017
 mom+0.016
 Sunny+0.016
Neg logit contributions
vell-0.050
wheel-0.046
inations-0.043
 disl-0.043
od-0.043
Token beach
Token ID10481
Feature activation-1.32e-02

Pos logit contributions
vell+0.035
wheel+0.033
 disl+0.030
 achieve+0.030
inations+0.030
Neg logit contributions
ara-0.019
Mom-0.018
 crib-0.017
um-0.016
 End-0.015
Token and
Token ID290
Feature activation-6.40e-03

Pos logit contributions
vell+0.037
wheel+0.034
 disl+0.034
inations+0.033
od+0.033
Neg logit contributions
 crib-0.012
ara-0.011
 mom-0.011
Mom-0.010
 Sunny-0.010
Token build
Token ID1382
Feature activation-9.87e-02

Pos logit contributions
vell+0.016
wheel+0.014
od+0.014
inations+0.013
 disl+0.013
Neg logit contributions
 crib-0.008
ara-0.008
 mom-0.008
Mom-0.008
 Sunny-0.007
Token sand
Token ID6450
Feature activation-7.04e-02

Pos logit contributions
vell+0.237
wheel+0.222
 disl+0.211
asing+0.207
inations+0.205
Neg logit contributions
 crib-0.132
 mom-0.126
ara-0.123
 Mom-0.118
Mom-0.117
Tokencast
Token ID2701
Feature activation-2.91e-01

Pos logit contributions
 disl+0.102
vell+0.102
wheel+0.099
asing+0.092
inations+0.089
Neg logit contributions
 mom-0.148
 crib-0.145
ara-0.144
 blanket-0.141
 basket-0.140
Tokenles
Token ID829
Feature activation-6.88e-02

Pos logit contributions
vell+0.608
wheel+0.555
 disl+0.527
inations+0.517
od+0.511
Neg logit contributions
 crib-0.465
ara-0.462
Mom-0.445
 mom-0.422
 Sunny-0.411
Token.
Token ID13
Feature activation-5.71e-03

Pos logit contributions
vell+0.185
wheel+0.170
 disl+0.168
inations+0.165
ologist+0.158
Neg logit contributions
 crib-0.068
ara-0.063
 mom-0.061
Mom-0.060
 bunny-0.056
Token
Token ID220
Feature activation+4.26e-03

Pos logit contributions
vell+0.015
wheel+0.014
 disl+0.013
inations+0.013
od+0.013
Neg logit contributions
 crib-0.006
ara-0.006
Mom-0.006
 mom-0.005
 Sunny-0.005
Token
Token ID198
Feature activation-1.74e-02

Pos logit contributions
ara+0.003
Mom+0.003
 crib+0.003
 mom+0.002
 Mom+0.002
Neg logit contributions
vell-0.013
wheel-0.012
 disl-0.012
inations-0.012
ologist-0.012
Token
Token ID198
Feature activation-1.68e-02

Pos logit contributions
vell+0.045
wheel+0.043
 disl+0.041
inations+0.041
od+0.041
Neg logit contributions
 crib-0.018
ara-0.017
Mom-0.016
 mom-0.015
 bunny-0.015
Token went
Token ID1816
Feature activation-3.50e-02

Pos logit contributions
vell+0.029
wheel+0.027
inations+0.026
 disl+0.025
od+0.025
Neg logit contributions
 crib-0.016
ara-0.016
Mom-0.015
 mom-0.015
 Sunny-0.014
Token back
Token ID736
Feature activation+1.25e-02

Pos logit contributions
vell+0.087
wheel+0.080
 disl+0.078
od+0.077
inations+0.077
Neg logit contributions
 crib-0.042
ara-0.041
Mom-0.040
 mom-0.038
 Sunny-0.035
Token to
Token ID284
Feature activation-6.62e-03

Pos logit contributions
 crib+0.013
 mom+0.012
ara+0.011
Mom+0.011
 Mom+0.010
Neg logit contributions
vell-0.036
wheel-0.033
inations-0.031
 disl-0.031
od-0.031
Token building
Token ID2615
Feature activation-8.22e-02

Pos logit contributions
vell+0.017
wheel+0.015
inations+0.014
 disl+0.014
od+0.014
Neg logit contributions
 crib-0.009
ara-0.008
 mom-0.008
Mom-0.008
 Mom-0.007
Token sand
Token ID6450
Feature activation-6.95e-02

Pos logit contributions
vell+0.234
wheel+0.214
inations+0.209
 disl+0.208
asing+0.206
Neg logit contributions
 crib-0.075
 mom-0.071
ara-0.066
Mom-0.065
 Mom-0.063
Tokencast
Token ID2701
Feature activation-2.91e-01

Pos logit contributions
vell+0.140
inations+0.136
 disl+0.136
wheel+0.132
asing+0.130
Neg logit contributions
 crib-0.109
 mom-0.108
ara-0.102
 shop-0.097
Mom-0.097
Tokenles
Token ID829
Feature activation-7.27e-02

Pos logit contributions
vell+0.616
wheel+0.563
 disl+0.536
inations+0.525
od+0.518
Neg logit contributions
ara-0.460
 crib-0.459
Mom-0.439
 mom-0.417
 Sunny-0.406
Token with
Token ID351
Feature activation+3.05e-02

Pos logit contributions
vell+0.196
wheel+0.178
 disl+0.178
inations+0.176
od+0.168
Neg logit contributions
 crib-0.073
ara-0.066
 mom-0.064
Mom-0.063
 bunny-0.059
Token his
Token ID465
Feature activation-1.41e-02

Pos logit contributions
 crib+0.041
ara+0.040
Mom+0.039
 mom+0.039
 Mom+0.036
Neg logit contributions
vell-0.072
wheel-0.067
 disl-0.063
inations-0.063
od-0.062
Token family
Token ID1641
Feature activation-2.92e-02

Pos logit contributions
vell+0.040
wheel+0.039
od+0.036
 disl+0.036
inations+0.035
Neg logit contributions
 crib-0.012
 mom-0.012
ara-0.012
Mom-0.011
 Mom-0.010
Token.
Token ID13
Feature activation-8.94e-03

Pos logit contributions
vell+0.073
wheel+0.067
 disl+0.064
inations+0.064
od+0.063
Neg logit contributions
 crib-0.035
ara-0.034
Mom-0.033
 mom-0.031
 Sunny-0.029
Token�
Token ID95
Feature activation+2.23e-02

Pos logit contributions
vell+0.012
wheel+0.011
 disl+0.010
inations+0.010
od+0.010
Neg logit contributions
 crib-0.011
ara-0.010
Mom-0.010
 mom-0.010
 Sunny-0.009
Token€
Token ID26391
Feature activation+4.78e-03

Pos logit contributions
ara+0.039
 crib+0.038
Mom+0.037
 mom+0.034
 Sunny+0.034
Neg logit contributions
vell-0.044
wheel-0.038
inations-0.038
od-0.037
 disl-0.036
Token�
Token ID129
Feature activation+7.46e-03

Pos logit contributions
ara+0.008
 crib+0.008
Mom+0.008
 mom+0.008
 Mom+0.007
Neg logit contributions
vell-0.010
wheel-0.009
inations-0.008
 disl-0.008
od-0.008
Token�
Token ID241
Feature activation+3.40e-02

Pos logit contributions
 crib+0.011
ara+0.011
Mom+0.011
 mom+0.010
 Sunny+0.010
Neg logit contributions
vell-0.016
wheel-0.015
inations-0.014
 disl-0.014
od-0.014
TokenYes
Token ID5297
Feature activation+1.71e-02

Pos logit contributions
 crib+0.036
ara+0.033
Mom+0.031
 mom+0.030
 Sunny+0.029
Neg logit contributions
vell-0.088
wheel-0.084
 disl-0.080
inations-0.079
od-0.078
Token please
Token ID3387
Feature activation+1.02e-01

Pos logit contributions
 crib+0.024
ara+0.023
Mom+0.022
 mom+0.020
 Sunny+0.020
Neg logit contributions
vell-0.039
wheel-0.036
 disl-0.034
inations-0.034
od-0.034
Token!
Token ID0
Feature activation-2.46e-02

Pos logit contributions
ara+0.165
Mom+0.161
 crib+0.160
 mom+0.157
 Mom+0.147
Neg logit contributions
vell-0.211
wheel-0.190
 disl-0.185
inations-0.182
od-0.179
Tokenâ
Token ID22940
Feature activation+1.29e-02

Pos logit contributions
vell+0.057
wheel+0.054
 disl+0.051
od+0.050
inations+0.049
Neg logit contributions
 crib-0.032
ara-0.030
Mom-0.029
 mom-0.027
 End-0.027
Token€
Token ID26391
Feature activation+6.05e-03

Pos logit contributions
ara+0.025
Mom+0.024
 crib+0.024
 End+0.023
um+0.022
Neg logit contributions
vell-0.023
inations-0.019
od-0.019
wheel-0.019
 disl-0.018
Token
Token ID198
Feature activation-1.99e-02

Pos logit contributions
ara+0.010
 crib+0.009
Mom+0.009
 mom+0.009
 Mom+0.008
Neg logit contributions
vell-0.013
wheel-0.012
inations-0.011
od-0.011
 disl-0.011
Token
Token ID198
Feature activation-1.95e-02

Pos logit contributions
vell+0.054
wheel+0.051
 disl+0.049
inations+0.048
od+0.048
Neg logit contributions
 crib-0.019
ara-0.018
Mom-0.017
 mom-0.016
 Sunny-0.015
Token his
Token ID465
Feature activation-7.77e-03

Pos logit contributions
vell+0.026
wheel+0.023
ologist+0.023
inations+0.023
od+0.023
Neg logit contributions
 crib-0.014
 mom-0.014
Mom-0.014
ara-0.014
 Mom-0.013
Token worries
Token ID18572
Feature activation-4.16e-02

Pos logit contributions
vell+0.018
wheel+0.017
 disl+0.016
inations+0.016
od+0.016
Neg logit contributions
 crib-0.010
ara-0.010
Mom-0.010
 mom-0.009
 Sunny-0.009
Token were
Token ID547
Feature activation-2.63e-02

Pos logit contributions
vell+0.100
wheel+0.090
 disl+0.089
inations+0.088
od+0.087
Neg logit contributions
 crib-0.053
ara-0.050
Mom-0.048
 mom-0.048
 bunny-0.046
Token gone
Token ID3750
Feature activation-4.82e-03

Pos logit contributions
vell+0.061
wheel+0.055
 disl+0.053
inations+0.052
od+0.052
Neg logit contributions
 crib-0.037
Mom-0.035
 mom-0.034
ara-0.034
 Sunny-0.032
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
vell+0.013
wheel+0.012
 disl+0.012
inations+0.011
od+0.011
Neg logit contributions
 crib-0.005
ara-0.005
 mom-0.005
Mom-0.005
 bunny-0.004
Token<|endoftext|>
Token ID50256
Feature activation+8.59e-02

Pos logit contributions
vell+0.033
wheel+0.030
inations+0.030
 disl+0.029
ologist+0.029
Neg logit contributions
ara-0.007
Mom-0.007
 crib-0.007
 Mom-0.006
 mom-0.006
TokenOnce
Token ID7454
Feature activation+8.67e-03

Pos logit contributions
 crib+0.097
ara+0.096
Mom+0.092
 mom+0.085
 Sunny+0.081
Neg logit contributions
vell-0.220
wheel-0.203
 disl-0.195
inations-0.194
od-0.191
Token upon
Token ID2402
Feature activation+1.61e-03

Pos logit contributions
ara+0.010
 crib+0.009
 mom+0.009
Mom+0.009
 Mom+0.008
Neg logit contributions
vell-0.023
wheel-0.022
 disl-0.021
inations-0.020
cher-0.020
Token a
Token ID257
Feature activation+1.35e-02

Pos logit contributions
ara+0.002
 crib+0.002
Mom+0.002
 mom+0.001
um+0.001
Neg logit contributions
vell-0.004
wheel-0.004
inations-0.004
 disl-0.004
od-0.004
Token time
Token ID640
Feature activation+8.83e-03

Pos logit contributions
 crib+0.017
 bunny+0.016
 cash+0.016
 ham+0.016
Mom+0.016
Neg logit contributions
vell-0.027
inations-0.027
 disl-0.026
wheel-0.025
od-0.025
Token,
Token ID11
Feature activation+1.67e-02

Pos logit contributions
 crib+0.006
ara+0.006
Mom+0.006
 mom+0.005
 Sunny+0.005
Neg logit contributions
vell-0.026
wheel-0.025
 disl-0.024
inations-0.024
od-0.023
Token him
Token ID683
Feature activation+3.93e-02

Pos logit contributions
vell+0.203
wheel+0.190
 disl+0.181
inations+0.179
od+0.176
Neg logit contributions
ara-0.094
 crib-0.094
Mom-0.089
 mom-0.080
 Sunny-0.078
Token.
Token ID13
Feature activation-6.17e-03

Pos logit contributions
 mom+0.034
 crib+0.033
 bunny+0.027
 Mom+0.027
 end+0.026
Neg logit contributions
vell-0.115
wheel-0.104
 disl-0.103
od-0.103
inations-0.101
Token She
Token ID1375
Feature activation+7.22e-03

Pos logit contributions
vell+0.015
wheel+0.014
 disl+0.014
smart+0.013
od+0.013
Neg logit contributions
ara-0.007
 crib-0.007
Mom-0.006
 End-0.006
 chicken-0.006
Token found
Token ID1043
Feature activation-5.83e-02

Pos logit contributions
 crib+0.013
ara+0.012
Mom+0.012
 Sunny+0.011
 beef+0.011
Neg logit contributions
vell-0.014
wheel-0.013
inations-0.012
 disl-0.012
od-0.012
Token him
Token ID683
Feature activation+4.02e-02

Pos logit contributions
vell+0.144
wheel+0.134
 disl+0.127
inations+0.125
od+0.125
Neg logit contributions
ara-0.071
 crib-0.070
Mom-0.066
 mom-0.060
 End-0.058
Token lying
Token ID9105
Feature activation+1.07e-01

Pos logit contributions
 crib+0.048
ara+0.047
Mom+0.045
 mom+0.043
 Sunny+0.041
Neg logit contributions
vell-0.100
wheel-0.093
 disl-0.089
inations-0.088
od-0.087
Token on
Token ID319
Feature activation-2.70e-02

Pos logit contributions
 crib+0.146
ara+0.144
Mom+0.140
 mom+0.130
 Sunny+0.126
Neg logit contributions
vell-0.249
wheel-0.229
 disl-0.214
inations-0.214
od-0.212
Token the
Token ID262
Feature activation-1.54e-02

Pos logit contributions
vell+0.062
wheel+0.059
 disl+0.056
od+0.055
inations+0.054
Neg logit contributions
ara-0.034
 crib-0.033
Mom-0.032
 End-0.029
 mom-0.029
Token ground
Token ID2323
Feature activation+6.52e-03

Pos logit contributions
vell+0.039
wheel+0.036
 disl+0.034
inations+0.034
od+0.034
Neg logit contributions
 crib-0.019
ara-0.018
Mom-0.018
 mom-0.017
 Sunny-0.016
Token,
Token ID11
Feature activation+2.36e-02

Pos logit contributions
 crib+0.006
ara+0.006
Mom+0.006
 mom+0.005
 Sunny+0.005
Neg logit contributions
vell-0.018
wheel-0.017
 disl-0.016
inations-0.016
od-0.016
Token not
Token ID407
Feature activation-2.66e-02

Pos logit contributions
 crib+0.034
ara+0.033
Mom+0.032
 mom+0.031
 Sunny+0.029
Neg logit contributions
vell-0.054
wheel-0.049
 disl-0.046
inations-0.046
od-0.046
Token cooperate
Token ID21270
Feature activation+1.40e-02

Pos logit contributions
vell+0.004
wheel+0.004
inations+0.003
od+0.003
 disl+0.003
Neg logit contributions
 crib-0.002
ara-0.002
Mom-0.002
 mom-0.002
 bunny-0.002
Token than
Token ID621
Feature activation-7.12e-02

Pos logit contributions
 crib+0.011
ara+0.011
Mom+0.010
 mom+0.010
 end+0.008
Neg logit contributions
vell-0.042
wheel-0.040
 disl-0.037
inations-0.036
cher-0.036
Token to
Token ID284
Feature activation-1.71e-03

Pos logit contributions
vell+0.166
wheel+0.150
 disl+0.141
od+0.140
inations+0.139
Neg logit contributions
 crib-0.096
 mom-0.094
Mom-0.092
ara-0.091
 Sunny-0.087
Token compete
Token ID9320
Feature activation-2.19e-02

Pos logit contributions
vell+0.004
wheel+0.003
inations+0.003
od+0.003
 disl+0.003
Neg logit contributions
ara-0.002
Mom-0.002
 crib-0.002
 mom-0.002
 Mom-0.002
Token.
Token ID13
Feature activation+1.33e-03

Pos logit contributions
vell+0.064
wheel+0.059
 disl+0.059
inations+0.058
ologist+0.055
Neg logit contributions
 mom-0.017
Mom-0.016
 crib-0.016
ara-0.016
 Mom-0.015
Token<|endoftext|>
Token ID50256
Feature activation+8.36e-02

Pos logit contributions
 crib+0.002
ara+0.002
Mom+0.002
 mom+0.002
 bunny+0.001
Neg logit contributions
vell-0.003
wheel-0.003
 disl-0.003
od-0.003
inations-0.003
TokenL
Token ID43
Feature activation-2.86e-02

Pos logit contributions
 crib+0.112
ara+0.107
Mom+0.107
 mom+0.102
 nurse+0.096
Neg logit contributions
vell-0.188
wheel-0.175
od-0.167
 disl-0.163
inations-0.161
Tokenily
Token ID813
Feature activation+2.66e-03

Pos logit contributions
vell+0.057
od+0.052
wheel+0.051
inations+0.051
asing+0.047
Neg logit contributions
 crib-0.045
Mom-0.044
 bunny-0.041
ara-0.040
 Sunny-0.040
Token and
Token ID290
Feature activation-9.57e-03

Pos logit contributions
 crib+0.003
ara+0.003
Mom+0.003
 mom+0.003
 Sunny+0.003
Neg logit contributions
vell-0.007
wheel-0.006
 disl-0.006
inations-0.006
od-0.006
Token Sam
Token ID3409
Feature activation-7.42e-02

Pos logit contributions
vell+0.024
wheel+0.022
 disl+0.022
od+0.021
inations+0.021
Neg logit contributions
 crib-0.011
ara-0.011
Mom-0.010
 End-0.009
 beef-0.009
Token were
Token ID547
Feature activation-2.41e-02

Pos logit contributions
vell+0.162
wheel+0.147
inations+0.140
 disl+0.135
od+0.135
Neg logit contributions
ara-0.116
 crib-0.113
Mom-0.110
 mom-0.105
 Sunny-0.101
Token longer
Token ID2392
Feature activation+4.52e-02

Pos logit contributions
 crib+0.007
Mom+0.006
ara+0.006
 Sunny+0.006
 End+0.005
Neg logit contributions
vell-0.015
wheel-0.014
inations-0.014
asing-0.013
od-0.013
Token sad
Token ID6507
Feature activation-1.44e-02

Pos logit contributions
 crib+0.062
ara+0.057
 mom+0.056
Mom+0.055
 bunny+0.053
Neg logit contributions
vell-0.107
wheel-0.098
inations-0.093
 disl-0.091
cher-0.090
Token or
Token ID393
Feature activation-1.11e-01

Pos logit contributions
vell+0.038
wheel+0.035
inations+0.033
 disl+0.033
od+0.032
Neg logit contributions
 crib-0.016
ara-0.016
Mom-0.015
 mom-0.014
 bunny-0.013
Token hungry
Token ID14720
Feature activation-7.00e-03

Pos logit contributions
vell+0.259
wheel+0.233
inations+0.223
od+0.221
 disl+0.220
Neg logit contributions
 crib-0.152
ara-0.145
Mom-0.143
 mom-0.141
 Sunny-0.134
Token!
Token ID0
Feature activation-2.96e-02

Pos logit contributions
vell+0.018
wheel+0.016
inations+0.016
 disl+0.016
od+0.015
Neg logit contributions
 crib-0.008
ara-0.008
Mom-0.007
 mom-0.007
 Sunny-0.007
Token<|endoftext|>
Token ID50256
Feature activation+7.46e-02

Pos logit contributions
vell+0.079
wheel+0.074
 disl+0.071
od+0.070
inations+0.070
Neg logit contributions
 crib-0.029
ara-0.028
Mom-0.027
 mom-0.024
 Sunny-0.023
TokenTom
Token ID13787
Feature activation-1.11e-03

Pos logit contributions
 crib+0.089
ara+0.085
Mom+0.084
 mom+0.079
 Sunny+0.074
Neg logit contributions
vell-0.183
wheel-0.170
od-0.161
 disl-0.160
inations-0.159
Tokenmy
Token ID1820
Feature activation-5.69e-02

Pos logit contributions
vell+0.002
wheel+0.002
 disl+0.002
inations+0.002
od+0.002
Neg logit contributions
 crib-0.002
ara-0.002
Mom-0.002
 mom-0.002
 Sunny-0.002
Token enjoyed
Token ID8359
Feature activation+1.03e-01

Pos logit contributions
vell+0.138
wheel+0.129
 disl+0.124
inations+0.122
od+0.122
Neg logit contributions
 crib-0.069
ara-0.066
Mom-0.065
 mom-0.060
 Sunny-0.057
Token riding
Token ID10311
Feature activation-1.04e-02

Pos logit contributions
ara+0.155
Mom+0.148
 crib+0.147
 End+0.132
um+0.131
Neg logit contributions
vell-0.217
wheel-0.203
 disl-0.198
inations-0.191
od-0.191
Token his
Token ID465
Feature activation-1.68e-02

Pos logit contributions
vell+0.024
wheel+0.022
 disl+0.021
inations+0.021
od+0.020
Neg logit contributions
 crib-0.015
ara-0.014
Mom-0.014
 mom-0.013
 Sunny-0.013
TokenBob
Token ID18861
Feature activation+8.09e-02

Pos logit contributions
vell+0.048
wheel+0.045
od+0.043
inations+0.043
 disl+0.043
Neg logit contributions
 crib-0.033
ara-0.030
 mom-0.029
 eyes-0.027
 ham-0.027
Token smiled
Token ID13541
Feature activation+5.37e-02

Pos logit contributions
 crib+0.090
ara+0.086
Mom+0.084
 mom+0.076
 Sunny+0.073
Neg logit contributions
vell-0.208
wheel-0.194
 disl-0.185
inations-0.183
od-0.183
Token and
Token ID290
Feature activation-8.52e-03

Pos logit contributions
ara+0.078
 crib+0.077
Mom+0.072
 nurse+0.066
 beef+0.066
Neg logit contributions
vell-0.115
wheel-0.101
od-0.100
cast-0.097
smart-0.094
Token said
Token ID531
Feature activation+1.05e-02

Pos logit contributions
vell+0.020
wheel+0.019
inations+0.018
 disl+0.018
od+0.018
Neg logit contributions
 crib-0.011
ara-0.011
Mom-0.011
 mom-0.010
 Sunny-0.010
Token,
Token ID11
Feature activation+1.55e-02

Pos logit contributions
ara+0.011
 crib+0.010
Mom+0.010
 mom+0.008
 nurse+0.008
Neg logit contributions
vell-0.028
wheel-0.026
od-0.025
 disl-0.025
inations-0.024
Token "
Token ID366
Feature activation+3.32e-02

Pos logit contributions
 crib+0.014
ara+0.014
Mom+0.013
 mom+0.011
 Sunny+0.011
Neg logit contributions
vell-0.042
wheel-0.040
 disl-0.038
od-0.038
inations-0.037
TokenWe
Token ID1135
Feature activation-3.97e-03

Pos logit contributions
 crib+0.038
ara+0.037
Mom+0.036
 mom+0.033
 Sunny+0.032
Neg logit contributions
vell-0.084
wheel-0.078
 disl-0.075
inations-0.074
od-0.073
Token have
Token ID423
Feature activation-9.99e-03

Pos logit contributions
vell+0.009
wheel+0.008
 disl+0.008
inations+0.008
od+0.008
Neg logit contributions
 crib-0.005
Mom-0.005
 mom-0.005
ara-0.005
 end-0.005
Token gained
Token ID8618
Feature activation+2.60e-03

Pos logit contributions
vell+0.026
wheel+0.024
 disl+0.023
inations+0.023
od+0.023
Neg logit contributions
 crib-0.011
ara-0.010
Mom-0.010
 mom-0.009
 Sunny-0.009
Token a
Token ID257
Feature activation+1.43e-02

Pos logit contributions
 crib+0.002
 mom+0.002
 Sunny+0.002
 Mom+0.002
ara+0.002
Neg logit contributions
vell-0.008
wheel-0.007
inations-0.007
od-0.007
ologist-0.007
Token new
Token ID649
Feature activation+1.14e-02

Pos logit contributions
ara+0.017
Mom+0.016
 crib+0.016
 Sunny+0.014
 End+0.014
Neg logit contributions
vell-0.036
wheel-0.033
 disl-0.031
inations-0.031
od-0.030
Token someone
Token ID2130
Feature activation-4.16e-02

Pos logit contributions
vell+0.168
wheel+0.154
 disl+0.148
inations+0.146
od+0.144
Neg logit contributions
 crib-0.057
 mom-0.057
ara-0.056
Mom-0.054
 me-0.053
Token more
Token ID517
Feature activation+4.14e-02

Pos logit contributions
vell+0.112
wheel+0.105
inations+0.098
 disl+0.098
od+0.097
Neg logit contributions
 bunny-0.039
 True-0.039
 crib-0.039
 mom-0.038
 Sunny-0.038
Token powerful
Token ID3665
Feature activation-7.40e-02

Pos logit contributions
 crib+0.050
 mom+0.049
 True+0.046
 End+0.045
 beef+0.045
Neg logit contributions
vell-0.103
wheel-0.097
od-0.089
ount-0.088
cher-0.088
Token than
Token ID621
Feature activation-8.16e-02

Pos logit contributions
vell+0.184
wheel+0.167
inations+0.155
od+0.154
 disl+0.153
Neg logit contributions
 crib-0.093
 bunny-0.086
 mom-0.086
 End-0.084
ara-0.084
Token yourself
Token ID3511
Feature activation-8.16e-02

Pos logit contributions
vell+0.197
wheel+0.181
 disl+0.170
inations+0.169
od+0.168
Neg logit contributions
 crib-0.101
 mom-0.099
 Sunny-0.096
 bunny-0.094
 beef-0.094
Token.
Token ID13
Feature activation-7.51e-03

Pos logit contributions
vell+0.228
wheel+0.213
inations+0.208
 disl+0.206
od+0.198
Neg logit contributions
 crib-0.074
 bunny-0.066
ara-0.065
 Sunny-0.063
 mom-0.062
Token<|endoftext|>
Token ID50256
Feature activation+7.96e-02

Pos logit contributions
vell+0.021
wheel+0.019
inations+0.018
 disl+0.018
od+0.018
Neg logit contributions
 crib-0.007
ara-0.007
Mom-0.007
 mom-0.006
 Sunny-0.006
TokenOnce
Token ID7454
Feature activation-1.14e-04

Pos logit contributions
 crib+0.083
ara+0.081
Mom+0.078
 mom+0.071
 Sunny+0.068
Neg logit contributions
vell-0.210
wheel-0.195
 disl-0.187
inations-0.186
od-0.184
Token there
Token ID612
Feature activation-2.91e-02

Pos logit contributions
vell+0.000
wheel+0.000
 disl+0.000
inations+0.000
od+0.000
Neg logit contributions
 crib-0.000
ara-0.000
Mom-0.000
 mom-0.000
 Sunny-0.000
Token was
Token ID373
Feature activation+3.47e-03

Pos logit contributions
vell+0.077
wheel+0.072
 disl+0.069
od+0.069
inations+0.068
Neg logit contributions
 crib-0.029
ara-0.028
Mom-0.027
 mom-0.023
 beef-0.023
Token a
Token ID257
Feature activation+4.95e-03

Pos logit contributions
ara+0.005
 crib+0.005
Mom+0.004
 nurse+0.004
 cash+0.004
Neg logit contributions
vell-0.007
wheel-0.007
od-0.007
 disl-0.007
inations-0.007
Token a
Token ID257
Feature activation+1.11e-02

Pos logit contributions
vell+0.045
wheel+0.042
 disl+0.040
inations+0.040
od+0.039
Neg logit contributions
 crib-0.023
ara-0.023
Mom-0.021
 mom-0.020
 Sunny-0.019
Token letter
Token ID3850
Feature activation+6.48e-02

Pos logit contributions
Mom+0.016
ara+0.016
 crib+0.015
 Sunny+0.014
 End+0.014
Neg logit contributions
vell-0.025
wheel-0.023
inations-0.021
 disl-0.021
od-0.021
Token in
Token ID287
Feature activation+2.25e-02

Pos logit contributions
 crib+0.086
ara+0.086
Mom+0.081
 mom+0.075
 Sunny+0.074
Neg logit contributions
vell-0.152
wheel-0.142
od-0.131
inations-0.130
 disl-0.130
Token the
Token ID262
Feature activation-2.11e-02

Pos logit contributions
 crib+0.032
ara+0.031
Mom+0.030
 mom+0.028
 Sunny+0.027
Neg logit contributions
vell-0.051
wheel-0.047
 disl-0.045
inations-0.044
od-0.044
Token mail
Token ID6920
Feature activation+5.94e-02

Pos logit contributions
vell+0.050
wheel+0.047
 disl+0.045
ologist+0.043
od+0.043
Neg logit contributions
ara-0.025
 Sunny-0.022
 crib-0.022
Mom-0.021
 Goose-0.021
Token.
Token ID13
Feature activation-8.20e-03

Pos logit contributions
 crib+0.075
ara+0.074
Mom+0.071
 Sunny+0.065
 mom+0.065
Neg logit contributions
vell-0.143
wheel-0.134
od-0.124
 disl-0.123
inations-0.123
Token It
Token ID632
Feature activation+2.88e-02

Pos logit contributions
vell+0.020
wheel+0.019
 disl+0.018
od+0.017
inations+0.017
Neg logit contributions
 crib-0.010
ara-0.010
Mom-0.010
 mom-0.009
 Sunny-0.009
Token was
Token ID373
Feature activation+8.89e-03

Pos logit contributions
 crib+0.031
ara+0.030
Mom+0.028
 mom+0.026
 Sunny+0.025
Neg logit contributions
vell-0.076
wheel-0.071
 disl-0.067
inations-0.067
od-0.066
Token from
Token ID422
Feature activation-5.79e-02

Pos logit contributions
ara+0.012
 crib+0.011
Mom+0.010
 bunny+0.009
 Sunny+0.009
Neg logit contributions
vell-0.021
wheel-0.020
od-0.018
inations-0.018
 disl-0.018
Token his
Token ID465
Feature activation-1.15e-02

Pos logit contributions
vell+0.136
wheel+0.127
 disl+0.120
inations+0.118
od+0.118
Neg logit contributions
ara-0.075
 crib-0.073
Mom-0.071
 bunny-0.063
 mom-0.063
Token grandma
Token ID49890
Feature activation+1.91e-02

Pos logit contributions
vell+0.031
wheel+0.029
 disl+0.028
od+0.028
inations+0.028
Neg logit contributions
ara-0.010
Mom-0.009
 crib-0.008
 Sunny-0.008
 End-0.008
Token it
Token ID340
Feature activation+4.01e-02

Pos logit contributions
vell+0.046
wheel+0.044
 disl+0.041
od+0.040
inations+0.040
Neg logit contributions
ara-0.029
 crib-0.028
Mom-0.027
 End-0.025
um-0.024
Token might
Token ID1244
Feature activation+1.80e-02

Pos logit contributions
 crib+0.030
ara+0.029
Mom+0.028
 mom+0.027
 bunny+0.027
Neg logit contributions
vell-0.117
wheel-0.107
inations-0.106
 disl-0.104
od-0.103
Token not
Token ID407
Feature activation-3.61e-02

Pos logit contributions
 crib+0.025
ara+0.025
Mom+0.024
 mom+0.023
 Sunny+0.023
Neg logit contributions
vell-0.041
wheel-0.037
inations-0.035
od-0.035
 disl-0.035
Token be
Token ID307
Feature activation+1.61e-02

Pos logit contributions
vell+0.081
wheel+0.074
 disl+0.070
inations+0.070
od+0.070
Neg logit contributions
 crib-0.052
ara-0.051
Mom-0.050
 mom-0.048
 Sunny-0.046
Token good
Token ID922
Feature activation-5.31e-02

Pos logit contributions
 crib+0.021
ara+0.020
 mom+0.019
 beef+0.019
 Sunny+0.019
Neg logit contributions
vell-0.039
wheel-0.036
 disl-0.034
inations-0.034
od-0.033
Token for
Token ID329
Feature activation+2.46e-02

Pos logit contributions
vell+0.144
wheel+0.132
inations+0.126
 disl+0.126
od+0.123
Neg logit contributions
 crib-0.054
ara-0.052
 mom-0.050
Mom-0.047
 bunny-0.047
Token him
Token ID683
Feature activation+2.94e-02

Pos logit contributions
ara+0.035
 crib+0.035
Mom+0.034
 mom+0.030
 nurse+0.030
Neg logit contributions
vell-0.055
wheel-0.051
 disl-0.048
inations-0.048
od-0.048
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
 crib+0.029
 mom+0.026
ara+0.026
Mom+0.025
 Sunny+0.025
Neg logit contributions
vell-0.081
wheel-0.074
 disl-0.071
inations-0.071
od-0.070
Token Max
Token ID5436
Feature activation+1.72e-02

Pos logit contributions
vell+0.038
wheel+0.038
 disl+0.036
od+0.034
inations+0.034
Neg logit contributions
 crib-0.019
ara-0.018
Mom-0.018
 beef-0.016
 End-0.016
Token listened
Token ID16399
Feature activation+7.83e-02

Pos logit contributions
 crib+0.032
ara+0.028
Mom+0.028
 beef+0.027
 End+0.026
Neg logit contributions
wheel-0.030
vell-0.029
 disl-0.028
od-0.027
 achieve-0.024
Token to
Token ID284
Feature activation-5.30e-03

Pos logit contributions
 crib+0.103
ara+0.100
Mom+0.095
 End+0.085
 Sunny+0.084
Neg logit contributions
vell-0.184
wheel-0.174
od-0.164
 disl-0.163
inations-0.161
Token they
Token ID484
Feature activation-9.39e-03

Pos logit contributions
vell+0.159
wheel+0.147
 disl+0.146
inations+0.140
od+0.138
Neg logit contributions
 crib-0.104
ara-0.104
Mom-0.099
 End-0.089
 mom-0.088
Token hugged
Token ID41130
Feature activation+2.69e-02

Pos logit contributions
vell+0.023
wheel+0.021
 disl+0.020
od+0.020
inations+0.019
Neg logit contributions
ara-0.011
 crib-0.011
Mom-0.011
 mom-0.011
 bunny-0.011
Token him
Token ID683
Feature activation+2.99e-02

Pos logit contributions
 crib+0.043
ara+0.043
 End+0.041
um+0.039
Mom+0.039
Neg logit contributions
vell-0.046
 disl-0.042
od-0.042
wheel-0.041
smart-0.040
Token.
Token ID13
Feature activation-8.32e-04

Pos logit contributions
ara+0.039
Mom+0.038
 crib+0.038
 End+0.033
um+0.032
Neg logit contributions
vell-0.070
wheel-0.064
od-0.060
inations-0.060
 disl-0.059
Token They
Token ID1119
Feature activation+3.65e-02

Pos logit contributions
 disl+0.002
vell+0.001
cast+0.001
od+0.001
wheel+0.001
Neg logit contributions
 End-0.001
 end-0.001
 crib-0.001
ara-0.001
 bunny-0.001
Token drank
Token ID24070
Feature activation+5.74e-02

Pos logit contributions
 crib+0.052
ara+0.051
Mom+0.050
 mom+0.048
 Sunny+0.045
Neg logit contributions
vell-0.083
wheel-0.076
 disl-0.072
inations-0.071
od-0.071
Token their
Token ID511
Feature activation+9.60e-03

Pos logit contributions
ara+0.082
 crib+0.077
Mom+0.073
 End+0.072
 nurse+0.068
Neg logit contributions
vell-0.118
wheel-0.113
 disl-0.108
cast-0.107
od-0.102
Token hot
Token ID3024
Feature activation+3.89e-02

Pos logit contributions
ara+0.012
 crib+0.012
Mom+0.011
 End+0.010
 nurse+0.010
Neg logit contributions
vell-0.022
inations-0.020
 disl-0.020
wheel-0.020
cast-0.019
Token chocolate
Token ID11311
Feature activation+9.96e-02

Pos logit contributions
 crib+0.046
ara+0.045
Mom+0.045
 vet+0.041
 End+0.041
Neg logit contributions
vell-0.085
 disl-0.082
wheel-0.081
inations-0.079
cast-0.076
Token and
Token ID290
Feature activation-5.48e-03

Pos logit contributions
ara+0.121
 crib+0.116
Mom+0.116
 End+0.110
 nurse+0.100
Neg logit contributions
vell-0.234
wheel-0.223
cast-0.207
od-0.204
 disl-0.202
Token ate
Token ID15063
Feature activation+6.06e-02

Pos logit contributions
vell+0.012
wheel+0.011
 disl+0.011
inations+0.011
od+0.010
Neg logit contributions
ara-0.008
 crib-0.008
Mom-0.007
um-0.007
 End-0.007
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
vell+0.057
wheel+0.055
od+0.049
cher+0.048
ologist+0.047
Neg logit contributions
ara-0.036
 crib-0.036
Mom-0.034
 Sunny-0.032
 mom-0.031
Token He
Token ID679
Feature activation-9.85e-03

Pos logit contributions
vell+0.033
wheel+0.029
inations+0.029
 disl+0.029
od+0.028
Neg logit contributions
ara-0.015
 crib-0.015
Mom-0.015
 mom-0.014
 Mom-0.013
Token shouted
Token ID17293
Feature activation+1.93e-03

Pos logit contributions
vell+0.019
wheel+0.018
od+0.017
 disl+0.017
inations+0.017
Neg logit contributions
 crib-0.017
ara-0.015
 Sunny-0.014
 beef-0.014
Mom-0.014
Token with
Token ID351
Feature activation+3.36e-02

Pos logit contributions
ara+0.002
 crib+0.002
Mom+0.002
 End+0.002
 Sunny+0.002
Neg logit contributions
vell-0.005
wheel-0.005
od-0.004
 disl-0.004
inations-0.004
Token g
Token ID308
Feature activation-2.96e-02

Pos logit contributions
 crib+0.043
ara+0.043
Mom+0.041
 mom+0.038
 Sunny+0.037
Neg logit contributions
vell-0.081
wheel-0.075
 disl-0.071
inations-0.070
od-0.070
Tokenlee
Token ID7197
Feature activation-1.64e-01

Pos logit contributions
vell+0.042
wheel+0.037
cher+0.033
inations+0.032
 disl+0.032
Neg logit contributions
ara-0.067
 crib-0.067
Mom-0.065
 mom-0.064
um-0.063
Token,
Token ID11
Feature activation+1.50e-02

Pos logit contributions
vell+0.427
wheel+0.401
od+0.378
 disl+0.378
inations+0.374
Neg logit contributions
 crib-0.175
ara-0.172
Mom-0.167
 mom-0.147
 Sunny-0.140
Token "
Token ID366
Feature activation+3.09e-02

Pos logit contributions
 crib+0.014
ara+0.013
Mom+0.012
 mom+0.011
 Sunny+0.010
Neg logit contributions
vell-0.041
wheel-0.039
 disl-0.037
od-0.037
inations-0.036
TokenLook
Token ID8567
Feature activation+8.90e-03

Pos logit contributions
ara+0.028
Mom+0.028
 crib+0.027
 mom+0.023
 bunny+0.021
Neg logit contributions
vell-0.087
wheel-0.080
 disl-0.078
inations-0.078
od-0.076
Token,
Token ID11
Feature activation+1.53e-02

Pos logit contributions
 mom+0.009
ara+0.009
 Mom+0.008
Mom+0.008
um+0.008
Neg logit contributions
vell-0.024
wheel-0.023
 disl-0.023
inations-0.022
 achieve-0.021
Token Molly
Token ID30236
Feature activation+2.07e-02

Pos logit contributions
 mom+0.022
 Mom+0.021
ara+0.019
Mom+0.019
 bunny+0.019
Neg logit contributions
vell-0.037
inations-0.034
wheel-0.033
 disl-0.033
asing-0.032
Token alright
Token ID23036
Feature activation-4.25e-03

Pos logit contributions
 crib+0.070
ara+0.069
Mom+0.067
 mom+0.062
 Sunny+0.060
Neg logit contributions
vell-0.123
wheel-0.114
 disl-0.108
inations-0.107
od-0.106
Token,
Token ID11
Feature activation+1.43e-03

Pos logit contributions
vell+0.010
 disl+0.009
wheel+0.009
od+0.009
inations+0.009
Neg logit contributions
 crib-0.005
ara-0.005
Mom-0.005
 End-0.004
 nurse-0.004
Token Lucky
Token ID27963
Feature activation+2.23e-02

Pos logit contributions
 crib+0.002
ara+0.002
Mom+0.002
 mom+0.002
 Sunny+0.001
Neg logit contributions
vell-0.003
wheel-0.003
 disl-0.003
inations-0.003
od-0.003
Token.
Token ID13
Feature activation-2.14e-02

Pos logit contributions
ara+0.026
 crib+0.026
Mom+0.024
 mom+0.023
 Sunny+0.022
Neg logit contributions
vell-0.057
wheel-0.052
inations-0.050
 disl-0.050
od-0.049
Token You
Token ID921
Feature activation-9.76e-03

Pos logit contributions
vell+0.046
wheel+0.043
 disl+0.042
inations+0.040
od+0.040
Neg logit contributions
 crib-0.031
ara-0.030
Mom-0.029
 mom-0.027
 beef-0.026
Token don
Token ID836
Feature activation-6.26e-02

Pos logit contributions
vell+0.020
wheel+0.018
 disl+0.018
cast+0.017
od+0.017
Neg logit contributions
 mom-0.015
 bunny-0.015
 crib-0.015
 Sunny-0.014
Mom-0.014
Token't
Token ID470
Feature activation-4.38e-02

Pos logit contributions
vell+0.159
 disl+0.142
wheel+0.141
inations+0.139
od+0.135
Neg logit contributions
Mom-0.075
 crib-0.073
ara-0.071
 mom-0.066
um-0.063
Token need
Token ID761
Feature activation+6.44e-03

Pos logit contributions
vell+0.099
wheel+0.083
inations+0.081
cher+0.080
od+0.079
Neg logit contributions
 crib-0.067
ara-0.067
Mom-0.067
 mom-0.064
 bunny-0.062
Token to
Token ID284
Feature activation-4.52e-03

Pos logit contributions
 crib+0.008
ara+0.008
Mom+0.008
 mom+0.007
 End+0.007
Neg logit contributions
vell-0.015
wheel-0.014
 disl-0.014
inations-0.014
od-0.013
Token work
Token ID670
Feature activation-6.10e-02

Pos logit contributions
vell+0.011
wheel+0.010
inations+0.009
 disl+0.009
od+0.009
Neg logit contributions
 crib-0.006
ara-0.006
Mom-0.006
 mom-0.006
 Sunny-0.005
Token.
Token ID13
Feature activation-1.92e-02

Pos logit contributions
vell+0.163
wheel+0.147
 disl+0.142
od+0.142
ologist+0.138
Neg logit contributions
 crib-0.065
ara-0.062
Mom-0.061
 mom-0.060
 beef-0.056
Token a
Token ID257
Feature activation+6.60e-03

Pos logit contributions
ara+0.021
 crib+0.020
Mom+0.019
um+0.016
 Sunny+0.016
Neg logit contributions
vell-0.048
wheel-0.046
 disl-0.043
od-0.043
inations-0.043
Token drawer
Token ID33451
Feature activation+1.62e-02

Pos logit contributions
ara+0.009
Mom+0.008
um+0.008
 Sunny+0.008
 crib+0.008
Neg logit contributions
vell-0.015
wheel-0.014
inations-0.013
 disl-0.013
cher-0.013
Token and
Token ID290
Feature activation-1.62e-02

Pos logit contributions
 crib+0.017
ara+0.016
Mom+0.016
 mom+0.015
 bunny+0.014
Neg logit contributions
vell-0.042
wheel-0.039
 disl-0.038
inations-0.037
od-0.037
Token stayed
Token ID9658
Feature activation+4.91e-02

Pos logit contributions
vell+0.038
wheel+0.035
 disl+0.034
inations+0.034
od+0.033
Neg logit contributions
 crib-0.022
ara-0.021
Mom-0.021
 mom-0.020
 Sunny-0.019
Token away
Token ID1497
Feature activation-1.83e-02

Pos logit contributions
 crib+0.065
ara+0.063
Mom+0.062
 mom+0.058
 Sunny+0.055
Neg logit contributions
vell-0.117
wheel-0.108
 disl-0.103
inations-0.102
od-0.101
Token from
Token ID422
Feature activation-6.35e-02

Pos logit contributions
vell+0.045
wheel+0.041
 disl+0.040
inations+0.040
ologist+0.039
Neg logit contributions
 crib-0.023
 mom-0.021
Mom-0.020
ara-0.020
 Sunny-0.020
Token it
Token ID340
Feature activation+4.32e-02

Pos logit contributions
vell+0.162
wheel+0.151
 disl+0.143
inations+0.142
od+0.142
Neg logit contributions
ara-0.071
 crib-0.070
Mom-0.068
 mom-0.060
 Sunny-0.058
Token.
Token ID13
Feature activation-1.66e-02

Pos logit contributions
 crib+0.049
ara+0.045
Mom+0.045
 mom+0.043
 Sunny+0.041
Neg logit contributions
vell-0.111
wheel-0.102
 disl-0.100
inations-0.098
od-0.097
Token Days
Token ID12579
Feature activation-6.26e-02

Pos logit contributions
vell+0.043
wheel+0.041
 disl+0.040
od+0.039
inations+0.038
Neg logit contributions
 crib-0.017
ara-0.016
Mom-0.016
 mom-0.014
 beef-0.013
Token,
Token ID11
Feature activation+9.54e-03

Pos logit contributions
vell+0.140
wheel+0.132
od+0.123
inations+0.120
cher+0.119
Neg logit contributions
 crib-0.089
Mom-0.084
ara-0.083
 mom-0.076
 Sunny-0.075
Token weeks
Token ID2745
Feature activation-2.80e-02

Pos logit contributions
 crib+0.010
ara+0.010
Mom+0.009
 mom+0.009
 bunny+0.008
Neg logit contributions
vell-0.025
wheel-0.024
 disl-0.023
inations-0.023
od-0.022
Token was
Token ID373
Feature activation+6.23e-03

Pos logit contributions
 crib+0.033
ara+0.032
 End+0.029
 beef+0.028
um+0.028
Neg logit contributions
vell-0.044
wheel-0.043
od-0.038
 disl-0.037
cher-0.036
Token much
Token ID881
Feature activation-3.81e-02

Pos logit contributions
ara+0.011
Mom+0.009
 crib+0.009
 End+0.009
�+0.009
Neg logit contributions
vell-0.012
wheel-0.012
 supposed-0.010
od-0.010
 disl-0.009
Token com
Token ID401
Feature activation-6.19e-02

Pos logit contributions
vell+0.076
wheel+0.073
inations+0.065
smart+0.063
 disl+0.061
Neg logit contributions
ara-0.063
Mom-0.056
 crib-0.056
 Sunny-0.053
 End-0.053
Tokenf
Token ID69
Feature activation-3.67e-02

Pos logit contributions
vell+0.127
wheel+0.116
inations+0.108
 disl+0.107
od+0.104
Neg logit contributions
 crib-0.105
ara-0.100
Mom-0.100
 mom-0.096
 Sunny-0.092
Tokenier
Token ID959
Feature activation-1.20e-01

Pos logit contributions
vell+0.065
wheel+0.058
 disl+0.056
inations+0.054
od+0.053
Neg logit contributions
 crib-0.070
ara-0.069
Mom-0.067
 mom-0.064
 Sunny-0.063
Token than
Token ID621
Feature activation-8.16e-02

Pos logit contributions
vell+0.268
wheel+0.249
inations+0.234
 disl+0.234
od+0.226
Neg logit contributions
 crib-0.182
ara-0.175
 mom-0.166
Mom-0.163
 bunny-0.159
Token any
Token ID597
Feature activation-2.83e-02

Pos logit contributions
vell+0.203
wheel+0.188
 disl+0.178
inations+0.178
od+0.177
Neg logit contributions
 crib-0.097
ara-0.096
Mom-0.094
 mom-0.084
 bunny-0.080
Token of
Token ID286
Feature activation+2.52e-02

Pos logit contributions
vell+0.064
wheel+0.060
inations+0.057
cher+0.054
od+0.054
Neg logit contributions
ara-0.038
Mom-0.038
 crib-0.034
um-0.032
 End-0.032
Token her
Token ID607
Feature activation+2.62e-03

Pos logit contributions
Mom+0.034
ara+0.034
um+0.031
 crib+0.031
 End+0.029
Neg logit contributions
vell-0.053
 disl-0.050
wheel-0.050
od-0.048
inations-0.047
Token l
Token ID300
Feature activation+5.70e-02

Pos logit contributions
Mom+0.003
ara+0.003
 crib+0.003
 End+0.003
 beef+0.003
Neg logit contributions
vell-0.006
wheel-0.005
inations-0.005
od-0.005
 disl-0.005
Tokenilies
Token ID3922
Feature activation-1.16e-01

Pos logit contributions
 crib+0.115
ara+0.114
Mom+0.111
 mom+0.106
 Sunny+0.104
Neg logit contributions
vell-0.095
wheel-0.084
 disl-0.081
inations-0.078
od-0.076
Token couldn
Token ID3521
Feature activation-3.94e-02

Pos logit contributions
vell+0.019
wheel+0.018
 disl+0.017
inations+0.017
od+0.016
Neg logit contributions
 crib-0.011
ara-0.011
Mom-0.010
 mom-0.010
 Sunny-0.009
Token't
Token ID470
Feature activation-4.44e-02

Pos logit contributions
vell+0.086
wheel+0.080
 disl+0.075
inations+0.074
od+0.074
Neg logit contributions
 crib-0.058
ara-0.057
Mom-0.055
 mom-0.052
 Sunny-0.050
Token hear
Token ID3285
Feature activation-5.64e-02

Pos logit contributions
vell+0.105
 disl+0.094
wheel+0.091
asing+0.090
inations+0.089
Neg logit contributions
 mom-0.061
Mom-0.060
 end-0.060
 crib-0.057
 bunny-0.057
Token any
Token ID597
Feature activation-2.69e-02

Pos logit contributions
vell+0.150
wheel+0.140
inations+0.133
 disl+0.133
od+0.130
Neg logit contributions
 crib-0.059
ara-0.057
Mom-0.055
 mom-0.052
 Sunny-0.049
Token cars
Token ID5006
Feature activation-9.43e-02

Pos logit contributions
vell+0.064
wheel+0.059
 disl+0.056
inations+0.056
od+0.056
Neg logit contributions
 crib-0.035
ara-0.034
Mom-0.033
 mom-0.031
 Sunny-0.030
Token or
Token ID393
Feature activation-1.06e-01

Pos logit contributions
vell+0.256
 disl+0.232
inations+0.223
ont+0.215
asing+0.213
Neg logit contributions
 end-0.086
 crib-0.084
 mom-0.080
 bunny-0.076
 nurse-0.075
Token people
Token ID661
Feature activation-6.86e-02

Pos logit contributions
vell+0.259
wheel+0.235
inations+0.219
od+0.219
asing+0.215
Neg logit contributions
 crib-0.144
 mom-0.138
 bunny-0.128
 Sunny-0.127
Mom-0.127
Token talking
Token ID3375
Feature activation-1.16e-02

Pos logit contributions
vell+0.178
wheel+0.157
 disl+0.154
inations+0.153
asing+0.148
Neg logit contributions
 crib-0.076
 mom-0.069
 bunny-0.066
 Sunny-0.064
 nurse-0.063
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
vell+0.032
wheel+0.030
inations+0.029
 disl+0.029
cher+0.028
Neg logit contributions
 crib-0.011
 mom-0.010
Mom-0.009
 Mom-0.009
ara-0.009
Token
Token ID220
Feature activation+1.63e-03

Pos logit contributions
vell+0.039
wheel+0.037
 disl+0.036
od+0.035
inations+0.035
Neg logit contributions
 crib-0.016
ara-0.015
Mom-0.015
 mom-0.013
 bunny-0.013
Token
Token ID198
Feature activation-2.48e-02

Pos logit contributions
ara+0.001
 crib+0.001
Mom+0.001
 mom+0.001
 Mom+0.001
Neg logit contributions
vell-0.005
wheel-0.005
inations-0.005
 disl-0.005
ologist-0.005
Token sharing
Token ID7373
Feature activation+3.42e-02

Pos logit contributions
 crib+0.017
ara+0.017
Mom+0.016
 mom+0.016
 Sunny+0.015
Neg logit contributions
vell-0.030
wheel-0.028
inations-0.026
 disl-0.026
od-0.026
Token is
Token ID318
Feature activation+4.55e-03

Pos logit contributions
 crib+0.026
 mom+0.025
Mom+0.024
ara+0.024
 True+0.022
Neg logit contributions
vell-0.102
wheel-0.093
inations-0.091
od-0.089
 disl-0.089
Token important
Token ID1593
Feature activation+9.80e-03

Pos logit contributions
 mom+0.005
Mom+0.005
 crib+0.005
 Mom+0.004
 End+0.004
Neg logit contributions
vell-0.012
wheel-0.011
od-0.011
inations-0.010
ologist-0.010
Token and
Token ID290
Feature activation-1.34e-02

Pos logit contributions
 crib+0.010
ara+0.009
Mom+0.009
 mom+0.009
 beef+0.008
Neg logit contributions
vell-0.027
wheel-0.025
inations-0.024
 disl-0.024
od-0.024
Token qu
Token ID627
Feature activation-3.95e-02

Pos logit contributions
vell+0.034
wheel+0.030
od+0.029
inations+0.029
ologist+0.029
Neg logit contributions
 crib-0.016
 mom-0.016
Mom-0.015
 Mom-0.015
ara-0.014
Tokenarre
Token ID9624
Feature activation-1.90e-01

Pos logit contributions
vell+0.063
wheel+0.055
cher+0.051
 disl+0.051
inations+0.049
Neg logit contributions
ara-0.082
Mom-0.081
 crib-0.081
um-0.078
 End-0.074
Tokenlling
Token ID2680
Feature activation-1.09e-01

Pos logit contributions
vell+0.470
wheel+0.439
 disl+0.426
ooters+0.409
cher+0.402
Neg logit contributions
 crib-0.201
 girl-0.190
 end-0.188
Mom-0.185
 End-0.182
Token is
Token ID318
Feature activation+4.86e-03

Pos logit contributions
vell+0.301
wheel+0.278
inations+0.268
 disl+0.264
od+0.262
Neg logit contributions
 crib-0.105
ara-0.096
 mom-0.094
Mom-0.091
 bunny-0.086
Token not
Token ID407
Feature activation-3.29e-02

Pos logit contributions
 mom+0.005
 crib+0.005
Mom+0.005
ara+0.005
 End+0.005
Neg logit contributions
vell-0.013
wheel-0.011
inations-0.011
od-0.011
 disl-0.011
Token good
Token ID922
Feature activation-4.75e-02

Pos logit contributions
vell+0.085
wheel+0.076
inations+0.073
od+0.072
 disl+0.072
Neg logit contributions
 crib-0.039
 mom-0.037
 beef-0.035
 bunny-0.034
 Sunny-0.034
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
vell+0.134
wheel+0.123
inations+0.119
cher+0.116
 disl+0.116
Neg logit contributions
 crib-0.043
 mom-0.043
ara-0.040
 Mom-0.038
 bunny-0.036
Token it
Token ID340
Feature activation+4.90e-02

Pos logit contributions
vell+0.076
wheel+0.071
 disl+0.070
inations+0.069
ologist+0.068
Neg logit contributions
 crib-0.023
 mom-0.023
Mom-0.021
ara-0.021
 Mom-0.021
Token -
Token ID532
Feature activation+6.91e-03

Pos logit contributions
 crib+0.036
 mom+0.032
 Mom+0.029
Mom+0.029
 one+0.028
Neg logit contributions
vell-0.144
 disl-0.140
inations-0.135
wheel-0.131
ologist-0.131
Token not
Token ID407
Feature activation-3.06e-02

Pos logit contributions
 crib+0.007
ara+0.007
Mom+0.007
 mom+0.006
 Sunny+0.006
Neg logit contributions
vell-0.018
wheel-0.017
 disl-0.016
inations-0.016
od-0.016
Token even
Token ID772
Feature activation-5.17e-02

Pos logit contributions
vell+0.082
wheel+0.074
 disl+0.074
inations+0.073
cher+0.072
Neg logit contributions
 crib-0.032
 mom-0.032
 one-0.029
 Mom-0.028
 bunny-0.027
Token the
Token ID262
Feature activation-1.65e-02

Pos logit contributions
vell+0.146
wheel+0.132
inations+0.127
ologist+0.127
 disl+0.126
Neg logit contributions
 mom-0.052
 crib-0.050
 one-0.049
 bunny-0.048
 Sunny-0.045
Token tallest
Token ID38760
Feature activation-2.05e-01

Pos logit contributions
vell+0.041
wheel+0.038
 disl+0.036
inations+0.036
od+0.035
Neg logit contributions
ara-0.020
 crib-0.019
Mom-0.019
 mom-0.017
 Sunny-0.016
Token tree
Token ID5509
Feature activation+2.64e-02

Pos logit contributions
vell+0.517
wheel+0.480
 disl+0.457
inations+0.454
od+0.451
Neg logit contributions
 crib-0.235
ara-0.233
Mom-0.225
 mom-0.204
 Sunny-0.198
Token.
Token ID13
Feature activation-9.38e-03

Pos logit contributions
 crib+0.028
ara+0.026
 mom+0.026
 bunny+0.025
 Sunny+0.024
Neg logit contributions
vell-0.068
 disl-0.063
inations-0.062
wheel-0.061
ologist-0.060
Token
Token ID220
Feature activation+4.79e-03

Pos logit contributions
vell+0.022
wheel+0.021
 disl+0.020
od+0.020
inations+0.019
Neg logit contributions
ara-0.011
 crib-0.010
Mom-0.010
 chicken-0.009
 End-0.009
Token
Token ID198
Feature activation-1.97e-02

Pos logit contributions
Mom+0.003
ara+0.002
 mom+0.002
 crib+0.002
 Mom+0.002
Neg logit contributions
vell-0.016
wheel-0.015
 disl-0.015
inations-0.014
ologist-0.014
Token
Token ID198
Feature activation-1.95e-02

Pos logit contributions
vell+0.053
wheel+0.050
 disl+0.047
inations+0.047
od+0.047
Neg logit contributions
 crib-0.019
ara-0.019
Mom-0.018
 mom-0.016
 Sunny-0.015
Token in
Token ID287
Feature activation+2.74e-02

Pos logit contributions
vell+0.117
 disl+0.108
wheel+0.108
inations+0.105
ologist+0.101
Neg logit contributions
 crib-0.031
 mom-0.027
ara-0.025
Mom-0.023
 one-0.023
Token the
Token ID262
Feature activation-1.59e-02

Pos logit contributions
 crib+0.030
ara+0.027
Mom+0.027
 mom+0.026
 beef+0.024
Neg logit contributions
vell-0.074
wheel-0.069
inations-0.066
 disl-0.065
od-0.065
Token forest
Token ID8222
Feature activation-1.56e-02

Pos logit contributions
vell+0.039
wheel+0.036
inations+0.034
od+0.034
 disl+0.034
Neg logit contributions
 crib-0.021
Mom-0.020
ara-0.019
 mom-0.019
 beef-0.018
Token.
Token ID13
Feature activation-7.52e-03

Pos logit contributions
vell+0.045
 disl+0.041
wheel+0.041
inations+0.040
asing+0.039
Neg logit contributions
 crib-0.013
 mom-0.011
 shop-0.010
 beef-0.010
 bunny-0.010
Token Bub
Token ID19645
Feature activation-1.04e-01

Pos logit contributions
vell+0.011
wheel+0.010
 disl+0.009
inations+0.009
od+0.009
Neg logit contributions
 crib-0.017
ara-0.016
Mom-0.016
 mom-0.015
 Sunny-0.015
Tokenbles
Token ID7689
Feature activation-2.21e-01

Pos logit contributions
 disl+0.168
wheel+0.165
vell+0.152
inations+0.146
opl+0.140
Neg logit contributions
ara-0.206
Mom-0.186
 friend-0.180
um-0.180
 me-0.179
Token told
Token ID1297
Feature activation-1.80e-02

Pos logit contributions
vell+0.540
wheel+0.496
 disl+0.478
inations+0.473
od+0.459
Neg logit contributions
 crib-0.271
ara-0.269
Mom-0.266
 mom-0.253
 bunny-0.238
Token him
Token ID683
Feature activation+3.87e-02

Pos logit contributions
vell+0.043
wheel+0.040
inations+0.038
 disl+0.038
od+0.037
Neg logit contributions
 crib-0.024
ara-0.023
Mom-0.022
 mom-0.022
 Sunny-0.021
Token that
Token ID326
Feature activation+1.99e-02

Pos logit contributions
 crib+0.049
ara+0.047
 mom+0.046
Mom+0.045
 Sunny+0.043
Neg logit contributions
vell-0.094
wheel-0.086
 disl-0.082
inations-0.081
od-0.079
Token he
Token ID339
Feature activation-9.85e-03

Pos logit contributions
 mom+0.023
 crib+0.023
 bunny+0.022
 beef+0.022
 Sunny+0.022
Neg logit contributions
vell-0.053
wheel-0.047
inations-0.046
asing-0.044
 disl-0.044
Token was
Token ID373
Feature activation+1.47e-02

Pos logit contributions
vell+0.023
wheel+0.021
 disl+0.021
inations+0.020
od+0.020
Neg logit contributions
ara-0.013
 crib-0.013
Mom-0.012
 mom-0.012
 bunny-0.011
Token't
Token ID470
Feature activation-3.62e-02

Pos logit contributions
vell+0.087
wheel+0.080
 disl+0.076
inations+0.075
od+0.075
Neg logit contributions
 crib-0.058
ara-0.057
Mom-0.055
 mom-0.052
 Sunny-0.050
Token play
Token ID711
Feature activation+9.84e-03

Pos logit contributions
vell+0.088
wheel+0.078
 disl+0.076
inations+0.075
od+0.075
Neg logit contributions
 crib-0.048
Mom-0.048
ara-0.046
 mom-0.046
 Mom-0.042
Token with
Token ID351
Feature activation+3.66e-02

Pos logit contributions
 crib+0.010
ara+0.009
Mom+0.009
 mom+0.008
 Sunny+0.008
Neg logit contributions
vell-0.027
wheel-0.025
inations-0.024
 disl-0.024
od-0.024
Token your
Token ID534
Feature activation+9.88e-03

Pos logit contributions
 crib+0.043
ara+0.042
Mom+0.040
 mom+0.037
 Sunny+0.035
Neg logit contributions
vell-0.092
wheel-0.085
 disl-0.081
inations-0.080
od-0.080
Token mar
Token ID1667
Feature activation-1.53e-01

Pos logit contributions
 crib+0.012
ara+0.012
Mom+0.011
 mom+0.010
 Sunny+0.010
Neg logit contributions
vell-0.024
wheel-0.022
 disl-0.022
inations-0.021
od-0.021
Tokenbles
Token ID7689
Feature activation-2.26e-01

Pos logit contributions
 disl+0.244
wheel+0.197
 recognise+0.194
smart+0.192
 achieve+0.189
Neg logit contributions
ara-0.312
um-0.289
Mom-0.282
 crib-0.278
 ham-0.273
Token."
Token ID526
Feature activation-2.28e-02

Pos logit contributions
vell+0.526
 disl+0.507
wheel+0.478
inations+0.474
od+0.463
Neg logit contributions
 crib-0.301
ara-0.287
 mom-0.268
 bunny-0.262
Mom-0.262
Token
Token ID198
Feature activation-1.15e-02

Pos logit contributions
vell+0.058
wheel+0.054
 disl+0.053
od+0.051
inations+0.051
Neg logit contributions
 crib-0.025
ara-0.024
Mom-0.023
 mom-0.021
 End-0.020
Token
Token ID198
Feature activation-1.06e-02

Pos logit contributions
vell+0.030
wheel+0.028
 disl+0.027
inations+0.027
od+0.027
Neg logit contributions
 crib-0.012
ara-0.011
Mom-0.010
 mom-0.010
 bunny-0.009
TokenTim
Token ID14967
Feature activation-1.24e-02

Pos logit contributions
vell+0.025
wheel+0.023
 disl+0.022
inations+0.021
od+0.021
Neg logit contributions
 crib-0.014
ara-0.014
Mom-0.013
 mom-0.013
 Sunny-0.012
Tokenmy
Token ID1820
Feature activation-5.19e-02

Pos logit contributions
vell+0.028
wheel+0.025
 disl+0.024
inations+0.024
od+0.023
Neg logit contributions
ara-0.019
 crib-0.018
Mom-0.018
 mom-0.017
 bunny-0.016
Token.
Token ID13
Feature activation-1.19e-02

Pos logit contributions
vell+0.040
wheel+0.038
od+0.037
inations+0.035
cher+0.034
Neg logit contributions
ara-0.026
 crib-0.026
Mom-0.025
 End-0.023
 kitten-0.022
Token She
Token ID1375
Feature activation-2.23e-03

Pos logit contributions
vell+0.031
wheel+0.029
 disl+0.028
od+0.027
inations+0.027
Neg logit contributions
 crib-0.012
ara-0.012
Mom-0.011
 End-0.010
 bunny-0.010
Token built
Token ID3170
Feature activation-3.34e-02

Pos logit contributions
vell+0.006
wheel+0.005
 disl+0.005
inations+0.005
od+0.005
Neg logit contributions
 crib-0.003
ara-0.003
Mom-0.003
 mom-0.002
 Sunny-0.002
Token a
Token ID257
Feature activation+5.29e-03

Pos logit contributions
vell+0.084
wheel+0.078
 disl+0.074
od+0.074
inations+0.074
Neg logit contributions
 crib-0.039
ara-0.038
Mom-0.037
 mom-0.033
 Sunny-0.032
Token sand
Token ID6450
Feature activation-7.02e-02

Pos logit contributions
ara+0.008
 crib+0.008
Mom+0.007
 Sunny+0.007
 End+0.007
Neg logit contributions
vell-0.012
wheel-0.011
inations-0.010
 disl-0.010
od-0.010
Tokencastle
Token ID18676
Feature activation-1.96e-01

Pos logit contributions
vell+0.102
wheel+0.090
 disl+0.088
inations+0.084
od+0.079
Neg logit contributions
 crib-0.156
ara-0.156
Mom-0.151
 mom-0.149
 bunny-0.143
Token and
Token ID290
Feature activation-1.70e-02

Pos logit contributions
vell+0.591
 disl+0.558
inations+0.537
wheel+0.535
od+0.517
Neg logit contributions
 crib-0.135
ara-0.134
Mom-0.123
 mom-0.121
 Mom-0.104
Token decorated
Token ID24789
Feature activation-1.39e-02

Pos logit contributions
vell+0.040
wheel+0.036
 disl+0.034
inations+0.034
od+0.033
Neg logit contributions
 crib-0.023
ara-0.023
Mom-0.023
 mom-0.022
 bunny-0.020
Token it
Token ID340
Feature activation+4.24e-02

Pos logit contributions
vell+0.036
wheel+0.034
 disl+0.032
od+0.032
inations+0.032
Neg logit contributions
 crib-0.015
ara-0.014
Mom-0.014
 mom-0.012
 Sunny-0.012
Token with
Token ID351
Feature activation+2.92e-02

Pos logit contributions
ara+0.046
 crib+0.045
Mom+0.044
 mom+0.038
 Sunny+0.037
Neg logit contributions
vell-0.111
wheel-0.103
od-0.098
inations-0.097
 disl-0.097
Token seas
Token ID21547
Feature activation-5.40e-02

Pos logit contributions
 crib+0.044
ara+0.043
Mom+0.042
 mom+0.039
 Sunny+0.038
Neg logit contributions
vell-0.064
wheel-0.059
 disl-0.055
inations-0.055
od-0.055