TOP ACTIVATIONS
MAX = 0.513

And from that day on , Sally and Tom
And from that day on , Laura learned an
something else with paper another day ," Lily said .
!" From that day on , Tiny and Max
and ' no ' all day . But the child was
tick - t ocked all day long . One day ,
." From that day on , Lily always cleaned
and it was a wonderful day . In
ummy lunch . From that day on , Tim my always
. From that day on , Owen was more
. From that day on , Tim my always
. From that day on , they learned that
. From that day on , Amy learned to
opl ane . <|endoftext|> One day , a turkey had an
. Later that day , Lucy knew something was
. Later that day , Tim my and his
. Later that day , when her mom my
answer questions . From that day on , Tim my and
them . One day , they see a big
them . One day , they found something different

MIN ACTIVATIONS
MIN = -0.683

and his dark mustache tw itched with joy .
She st itched and st itched until she had a beautiful
to stitch . She st itched and st itched until she
and thread and carefully st itched it to the fabric .
off some fabric and st itched it around the waist to
needle and thread and st itched up her knee . Lily
, and his nose tw itched . He had never tasted
icked his lips and tw itched his tail . He wanted
them . Then it tw itched its nose and it seemed
hungry . His nose tw itched as he smelled something in
loud , high - p itched noise back .
forest . The bunny tw itched his nose , making tiny
big eyes . It tw itched its nose . Lily smiled
of red cloth and st itched her name on it .
to work and carefully st itched the coat .
was a high - p itched , sque aky noise .
loud , high - p itched noises . They sounded like
She se wed , st itched , and pinned her masterpiece
its mother who had st itched the egg together . <|endoftext|>
sweet , high - p itched voice . � � €

INTERVAL 0.214 - 0.513
CONTAINS 5.807%

. <|endoftext|> Once upon a time , there was a little
said . " You are welcome . We are
and thanked Miss Rose . She felt good and wanted to
Ben learned a lesson that day . They learned that not
<|endoftext|> S ara and Ben like to play in the park

INTERVAL -0.085 - 0.214
CONTAINS 72.241%

go and put something great there to help it ."
. Tim my loved to play games with his friends .
with you ." The little boy smiled and was
they played together every day . <|endoftext|> Once upon a time
The little girl noticed too and said , " Oh no

INTERVAL -0.384 - -0.085
CONTAINS 21.824%

fly away , but he hurt his wing . Ups et
for Spot . She used some paper and cr ay ons
never go near the river again . She was too scared
called his name . " Ben , wait for
" Tom ! Lily ! What are you doing ?" Mom

INTERVAL -0.683 - -0.384
CONTAINS 0.128%

said . P ete nodded . Together , they
special with him - a hook . Sam wanted
into the pond and sw am together . They became best
. Together , they sw am off to the sea .
their dad . They have rods and hooks and worms .
Token
Token ID198
Feature activation-3.85e-02

Pos logit contributions
itched+0.182
 tal+0.172
 fin+0.152
eg+0.152
ades+0.144
Neg logit contributions
 She-0.136
 she-0.135
 day-0.128
 weekend-0.126
 week-0.119
Token
Token ID198
Feature activation-4.11e-02

Pos logit contributions
itched+0.086
 tal+0.082
eg+0.078
izza+0.072
orse+0.071
Neg logit contributions
 She-0.066
 she-0.064
 day-0.064
 always-0.057
 sometimes-0.056
TokenAnd
Token ID1870
Feature activation-4.64e-02

Pos logit contributions
itched+0.098
 tal+0.094
eg+0.089
orse+0.085
izza+0.083
Neg logit contributions
 She-0.062
 day-0.060
 she-0.060
 like-0.053
 always-0.053
Token from
Token ID422
Feature activation+1.03e-01

Pos logit contributions
itched+0.112
 tal+0.108
eg+0.103
orse+0.098
izza+0.096
Neg logit contributions
 She-0.067
 day-0.066
 she-0.065
 like-0.058
 especially-0.057
Token that
Token ID326
Feature activation+4.51e-02

Pos logit contributions
 She+0.173
 she+0.164
 day+0.163
 especially+0.151
my+0.150
Neg logit contributions
itched-0.224
 tal-0.216
eg-0.200
orse-0.193
 fin-0.188
Token day
Token ID1110
Feature activation+4.87e-01

Pos logit contributions
 She+0.022
 she+0.015
 especially+0.010
She+0.009
Hi+0.007
Neg logit contributions
 tal-0.150
itched-0.149
 fin-0.138
orse-0.138
eg-0.137
Token on
Token ID319
Feature activation+3.40e-02

Pos logit contributions
 She+0.813
 day+0.798
 she+0.793
 like+0.716
 especially+0.715
Neg logit contributions
itched-1.080
 tal-1.029
eg-0.970
orse-0.916
izza-0.895
Token,
Token ID11
Feature activation+1.37e-02

Pos logit contributions
 She+0.061
 day+0.060
 she+0.058
 especially+0.056
 like+0.056
Neg logit contributions
itched-0.069
 tal-0.066
eg-0.060
orse-0.056
ves-0.055
Token Sally
Token ID25737
Feature activation+2.01e-01

Pos logit contributions
 She+0.021
 day+0.020
 she+0.019
 weekend+0.019
my+0.019
Neg logit contributions
 tal-0.028
itched-0.028
eg-0.026
orse-0.025
 fin-0.024
Token and
Token ID290
Feature activation+1.29e-01

Pos logit contributions
 She+0.284
 day+0.278
 she+0.277
 like+0.242
 especially+0.241
Neg logit contributions
itched-0.493
 tal-0.474
eg-0.449
orse-0.427
izza-0.418
Token Tom
Token ID4186
Feature activation+4.99e-03

Pos logit contributions
 She+0.216
 day+0.212
 she+0.204
 especially+0.201
 weekend+0.197
Neg logit contributions
 tal-0.262
itched-0.260
eg-0.239
orse-0.227
 fin-0.221
Token
Token ID198
Feature activation-3.85e-02

Pos logit contributions
 She+0.223
 day+0.220
 she+0.216
 like+0.198
 always+0.194
Neg logit contributions
itched-0.472
 tal-0.453
eg-0.432
orse-0.409
izza-0.403
Token
Token ID198
Feature activation-4.11e-02

Pos logit contributions
itched+0.086
 tal+0.082
eg+0.078
izza+0.072
orse+0.071
Neg logit contributions
 She-0.066
 she-0.064
 day-0.064
 always-0.057
 sometimes-0.056
TokenAnd
Token ID1870
Feature activation-4.64e-02

Pos logit contributions
itched+0.098
 tal+0.094
eg+0.089
orse+0.085
izza+0.083
Neg logit contributions
 She-0.062
 day-0.060
 she-0.060
 like-0.053
 always-0.053
Token from
Token ID422
Feature activation+1.03e-01

Pos logit contributions
itched+0.112
 tal+0.108
eg+0.103
orse+0.098
izza+0.096
Neg logit contributions
 She-0.067
 day-0.066
 she-0.065
 like-0.058
 especially-0.057
Token that
Token ID326
Feature activation+4.51e-02

Pos logit contributions
 She+0.173
 she+0.164
 day+0.163
 especially+0.151
my+0.150
Neg logit contributions
itched-0.224
 tal-0.216
eg-0.200
orse-0.193
 fin-0.188
Token day
Token ID1110
Feature activation+4.87e-01

Pos logit contributions
 She+0.022
 she+0.015
 especially+0.010
She+0.009
Hi+0.007
Neg logit contributions
 tal-0.150
itched-0.149
 fin-0.138
orse-0.138
eg-0.137
Token on
Token ID319
Feature activation+3.40e-02

Pos logit contributions
 She+0.813
 day+0.798
 she+0.793
 like+0.716
 especially+0.715
Neg logit contributions
itched-1.080
 tal-1.029
eg-0.970
orse-0.916
izza-0.895
Token,
Token ID11
Feature activation+1.37e-02

Pos logit contributions
 She+0.061
 day+0.060
 she+0.058
 especially+0.056
 like+0.056
Neg logit contributions
itched-0.069
 tal-0.066
eg-0.060
orse-0.056
ves-0.055
Token Laura
Token ID16753
Feature activation-1.39e-02

Pos logit contributions
 She+0.021
 day+0.020
 she+0.019
 weekend+0.019
my+0.019
Neg logit contributions
 tal-0.028
itched-0.028
eg-0.026
orse-0.025
 fin-0.024
Token learned
Token ID4499
Feature activation-2.37e-02

Pos logit contributions
itched+0.034
 tal+0.033
eg+0.031
orse+0.030
izza+0.029
Neg logit contributions
 She-0.020
 day-0.019
 she-0.019
 like-0.017
 sometimes-0.017
Token an
Token ID281
Feature activation-9.75e-02

Pos logit contributions
itched+0.052
 tal+0.050
eg+0.047
orse+0.045
izza+0.044
Neg logit contributions
 She-0.040
 day-0.039
 she-0.039
 like-0.035
 always-0.034
Token something
Token ID1223
Feature activation-6.16e-02

Pos logit contributions
 she+0.555
 She+0.553
 day+0.540
 always+0.503
 sometimes+0.502
Neg logit contributions
 tal-0.982
itched-0.976
eg-0.907
izza-0.864
orse-0.852
Token else
Token ID2073
Feature activation-4.98e-02

Pos logit contributions
itched+0.135
 tal+0.134
orse+0.122
eg+0.121
 fin+0.119
Neg logit contributions
 She-0.096
 she-0.083
 day-0.083
my-0.082
 sometimes-0.078
Token with
Token ID351
Feature activation+3.09e-02

Pos logit contributions
itched+0.114
 tal+0.110
eg+0.102
orse+0.099
 fin+0.096
Neg logit contributions
 She-0.078
 day-0.074
 she-0.073
 always-0.066
 sometimes-0.066
Token paper
Token ID3348
Feature activation-4.89e-02

Pos logit contributions
 She+0.049
 day+0.048
 she+0.048
 always+0.042
 like+0.042
Neg logit contributions
itched-0.070
 tal-0.068
eg-0.064
orse-0.060
izza-0.059
Token another
Token ID1194
Feature activation-1.14e-01

Pos logit contributions
itched+0.111
 tal+0.107
eg+0.101
orse+0.096
izza+0.094
Neg logit contributions
 She-0.079
 she-0.077
 day-0.077
 like-0.069
 sometimes-0.068
Token day
Token ID1110
Feature activation+4.86e-01

Pos logit contributions
itched+0.235
 tal+0.224
eg+0.211
orse+0.197
izza+0.194
Neg logit contributions
 She-0.208
 day-0.207
 she-0.206
 like-0.186
 always-0.185
Token,"
Token ID553
Feature activation-1.46e-01

Pos logit contributions
 She+0.823
 she+0.813
 day+0.809
 like+0.728
 always+0.720
Neg logit contributions
itched-1.066
 tal-1.024
eg-0.970
orse-0.905
izza-0.893
Token Lily
Token ID20037
Feature activation+2.23e-01

Pos logit contributions
itched+0.374
 tal+0.360
eg+0.344
orse+0.323
izza+0.322
Neg logit contributions
 She-0.205
 she-0.203
 day-0.194
 always-0.170
 like-0.169
Token said
Token ID531
Feature activation-8.66e-02

Pos logit contributions
 She+0.445
 day+0.445
 she+0.437
 weekend+0.402
 like+0.401
Neg logit contributions
itched-0.408
 tal-0.388
eg-0.360
orse-0.338
izza-0.330
Token.
Token ID13
Feature activation+6.54e-04

Pos logit contributions
 tal+0.237
eg+0.233
 rods+0.223
itched+0.218
engu+0.215
Neg logit contributions
 she-0.128
 She-0.116
 her-0.105
 day-0.102
 like-0.099
Token
Token ID198
Feature activation-8.36e-02

Pos logit contributions
 She+0.001
 she+0.001
 day+0.001
my+0.001
 like+0.001
Neg logit contributions
 tal-0.002
itched-0.002
eg-0.001
urger-0.001
orse-0.001
Token!"
Token ID2474
Feature activation-9.86e-02

Pos logit contributions
itched+0.145
 tal+0.131
eg+0.129
 rods+0.129
 cannon+0.128
Neg logit contributions
 She-0.122
 she-0.113
 especially-0.104
 like-0.103
heart-0.101
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
itched+0.229
 tal+0.221
eg+0.211
izza+0.194
orse+0.193
Neg logit contributions
 She-0.165
 she-0.162
 day-0.153
 like-0.138
 sometimes-0.137
Token
Token ID198
Feature activation-4.86e-02

Pos logit contributions
itched+0.098
 tal+0.096
eg+0.093
urger+0.091
 cannon+0.086
Neg logit contributions
 She-0.072
 she-0.066
 day-0.063
She-0.059
my-0.057
TokenFrom
Token ID4863
Feature activation+1.30e-02

Pos logit contributions
itched+0.120
 tal+0.117
eg+0.110
izza+0.103
urger+0.102
Neg logit contributions
 She-0.072
 she-0.069
 day-0.067
 always-0.059
 especially-0.059
Token that
Token ID326
Feature activation+4.25e-02

Pos logit contributions
 She+0.021
 day+0.020
 she+0.020
 like+0.018
 always+0.018
Neg logit contributions
itched-0.030
 tal-0.029
eg-0.027
orse-0.026
izza-0.025
Token day
Token ID1110
Feature activation+4.85e-01

Pos logit contributions
 She+0.016
 she+0.011
 especially+0.006
 like+0.005
She+0.004
Neg logit contributions
itched-0.147
 tal-0.146
eg-0.137
orse-0.136
 fin-0.133
Token on
Token ID319
Feature activation+3.32e-02

Pos logit contributions
 She+0.725
 she+0.717
 day+0.717
 always+0.621
 like+0.621
Neg logit contributions
itched-1.166
 tal-1.137
eg-1.076
orse-1.026
izza-1.023
Token,
Token ID11
Feature activation+9.59e-03

Pos logit contributions
 She+0.061
 day+0.059
 she+0.058
 especially+0.056
 like+0.055
Neg logit contributions
itched-0.067
 tal-0.064
eg-0.057
orse-0.054
ves-0.053
Token Tiny
Token ID20443
Feature activation-1.21e-01

Pos logit contributions
 She+0.014
 day+0.013
 she+0.013
 weekend+0.012
 especially+0.012
Neg logit contributions
itched-0.021
 tal-0.021
eg-0.020
orse-0.019
izza-0.018
Token and
Token ID290
Feature activation+1.27e-01

Pos logit contributions
itched+0.294
 tal+0.283
eg+0.266
orse+0.256
 fin+0.247
Neg logit contributions
 She-0.176
 day-0.170
 she-0.170
 like-0.149
 weekend-0.148
Token Max
Token ID5436
Feature activation-9.95e-03

Pos logit contributions
 She+0.229
 day+0.213
 weekend+0.209
 she+0.208
 especially+0.204
Neg logit contributions
 tal-0.251
itched-0.238
eg-0.219
orse-0.215
 fin-0.207
Token and
Token ID290
Feature activation+1.73e-01

Pos logit contributions
itched+0.370
 tal+0.353
eg+0.343
orse+0.324
izza+0.320
Neg logit contributions
 She-0.255
 she-0.244
 day-0.233
 like-0.215
 sometimes-0.213
Token '
Token ID705
Feature activation-2.00e-01

Pos logit contributions
 She+0.280
 day+0.273
 she+0.271
 like+0.243
 always+0.242
Neg logit contributions
itched-0.387
 tal-0.373
eg-0.350
orse-0.333
izza-0.326
Tokenno
Token ID3919
Feature activation+4.83e-02

Pos logit contributions
itched+0.536
 tal+0.518
eg+0.492
orse+0.472
izza+0.466
Neg logit contributions
 She-0.236
 she-0.229
 day-0.228
 like-0.194
 always-0.193
Token'
Token ID6
Feature activation-7.27e-02

Pos logit contributions
 day+0.092
 she+0.089
 She+0.088
 always+0.083
 sometimes+0.082
Neg logit contributions
itched-0.096
eg-0.092
 tal-0.091
 cannon-0.082
 fin-0.081
Token all
Token ID477
Feature activation+1.70e-01

Pos logit contributions
itched+0.162
 tal+0.156
eg+0.148
orse+0.141
 fin+0.136
Neg logit contributions
 She-0.123
 day-0.121
 she-0.121
 always-0.109
 like-0.109
Token day
Token ID1110
Feature activation+4.84e-01

Pos logit contributions
 She+0.292
 she+0.284
 day+0.282
 especially+0.256
 like+0.255
Neg logit contributions
itched-0.363
 tal-0.350
eg-0.322
orse-0.307
izza-0.303
Token.
Token ID13
Feature activation+8.29e-03

Pos logit contributions
 she+0.894
 day+0.885
 She+0.880
 like+0.797
 always+0.795
Neg logit contributions
itched-1.005
 tal-0.957
eg-0.926
orse-0.849
 fin-0.831
Token But
Token ID887
Feature activation+1.60e-01

Pos logit contributions
 She+0.013
 she+0.012
 day+0.012
 sometimes+0.011
 always+0.011
Neg logit contributions
itched-0.020
 tal-0.019
eg-0.018
orse-0.017
 fin-0.017
Token the
Token ID262
Feature activation+1.80e-02

Pos logit contributions
 She+0.237
 day+0.223
 she+0.221
 especially+0.197
 like+0.197
Neg logit contributions
itched-0.376
 tal-0.363
eg-0.339
orse-0.329
izza-0.323
Token child
Token ID1200
Feature activation-1.79e-02

Pos logit contributions
 She+0.028
 she+0.027
 day+0.027
 like+0.024
 sometimes+0.024
Neg logit contributions
itched-0.041
 tal-0.040
eg-0.038
orse-0.036
izza-0.035
Token was
Token ID373
Feature activation+2.06e-02

Pos logit contributions
itched+0.043
 tal+0.041
eg+0.039
orse+0.037
izza+0.036
Neg logit contributions
 She-0.027
 day-0.026
 she-0.026
 like-0.023
 sometimes-0.023
Token tick
Token ID4378
Feature activation+7.01e-02

Pos logit contributions
itched+0.071
 tal+0.065
eg+0.059
 fin+0.059
 cannon+0.057
Neg logit contributions
 She-0.066
 day-0.063
 she-0.063
 weekend-0.059
 week-0.059
Token-
Token ID12
Feature activation-9.25e-02

Pos logit contributions
 She+0.132
 day+0.129
 she+0.129
 like+0.117
 always+0.117
Neg logit contributions
itched-0.142
 tal-0.135
eg-0.126
orse-0.119
izza-0.116
Tokent
Token ID83
Feature activation+1.39e-01

Pos logit contributions
itched+0.179
 tal+0.170
eg+0.158
orse+0.150
ves+0.145
Neg logit contributions
 She-0.179
 day-0.176
 she-0.174
 like-0.160
 especially-0.160
Tokenocked
Token ID3543
Feature activation-8.87e-03

Pos logit contributions
 She+0.177
 day+0.161
 she+0.159
 weekend+0.153
 girl+0.146
Neg logit contributions
itched-0.350
 tal-0.343
orse-0.313
eg-0.307
 fin-0.301
Token all
Token ID477
Feature activation+1.69e-01

Pos logit contributions
itched+0.020
 tal+0.019
eg+0.018
orse+0.017
 fin+0.017
Neg logit contributions
 She-0.014
 day-0.013
 she-0.013
 weekend-0.012
 especially-0.012
Token day
Token ID1110
Feature activation+4.84e-01

Pos logit contributions
 She+0.253
 especially+0.235
 she+0.232
She+0.220
 weekend+0.219
Neg logit contributions
 tal-0.352
itched-0.347
 fin-0.284
 cannon-0.280
eg-0.279
Token long
Token ID890
Feature activation+3.55e-02

Pos logit contributions
 she+0.778
 She+0.758
 day+0.748
 like+0.672
 always+0.662
Neg logit contributions
itched-1.122
 tal-1.094
eg-1.065
izza-0.991
orse-0.971
Token.
Token ID13
Feature activation+5.16e-03

Pos logit contributions
 She+0.059
 day+0.058
 she+0.058
 like+0.052
 always+0.051
Neg logit contributions
itched-0.079
 tal-0.076
eg-0.071
orse-0.067
izza-0.066
Token One
Token ID1881
Feature activation+1.67e-01

Pos logit contributions
 She+0.009
 she+0.008
 day+0.008
 sometimes+0.007
 always+0.007
Neg logit contributions
itched-0.012
 tal-0.011
eg-0.011
orse-0.010
izza-0.010
Token day
Token ID1110
Feature activation+4.69e-01

Pos logit contributions
 She+0.094
She+0.055
 she+0.052
You+0.045
 like+0.042
Neg logit contributions
 tal-0.517
itched-0.515
orse-0.507
 fin-0.488
eg-0.469
Token,
Token ID11
Feature activation+3.86e-03

Pos logit contributions
 she+0.744
 She+0.712
 day+0.682
 like+0.613
 always+0.593
Neg logit contributions
itched-1.144
 tal-1.121
eg-1.063
orse-1.003
izza-1.001
Token."
Token ID526
Feature activation-9.92e-03

Pos logit contributions
itched+0.072
 tal+0.069
eg+0.065
orse+0.061
izza+0.060
Neg logit contributions
 She-0.055
 she-0.054
 day-0.054
 always-0.048
 sometimes-0.048
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.022
 tal+0.021
eg+0.020
orse+0.019
izza+0.019
Neg logit contributions
 She-0.017
 she-0.016
 day-0.016
 like-0.014
 sometimes-0.014
Token
Token ID198
Feature activation-5.22e-02

Pos logit contributions
itched+0.108
 tal+0.104
eg+0.100
urger+0.095
izza+0.092
Neg logit contributions
 She-0.086
 she-0.080
 day-0.079
my-0.071
She-0.070
TokenFrom
Token ID4863
Feature activation+9.81e-03

Pos logit contributions
itched+0.128
 tal+0.124
eg+0.117
orse+0.111
izza+0.110
Neg logit contributions
 She-0.075
 she-0.073
 day-0.073
 like-0.064
 always-0.064
Token that
Token ID326
Feature activation+3.93e-02

Pos logit contributions
 She+0.016
 day+0.016
 she+0.016
 especially+0.014
 always+0.014
Neg logit contributions
itched-0.022
 tal-0.021
eg-0.020
orse-0.019
 fin-0.018
Token day
Token ID1110
Feature activation+4.84e-01

Pos logit contributions
 She+0.019
 she+0.013
 especially+0.009
 like+0.008
She+0.008
Neg logit contributions
 tal-0.131
itched-0.130
eg-0.122
orse-0.122
 fin-0.119
Token on
Token ID319
Feature activation+3.11e-02

Pos logit contributions
 She+0.740
 day+0.729
 she+0.727
 like+0.637
 always+0.636
Neg logit contributions
itched-1.146
 tal-1.111
eg-1.050
orse-1.001
izza-0.990
Token,
Token ID11
Feature activation+7.35e-03

Pos logit contributions
 She+0.059
 day+0.057
 especially+0.056
 she+0.055
 like+0.055
Neg logit contributions
itched-0.059
 tal-0.056
eg-0.050
orse-0.047
ves-0.047
Token Lily
Token ID20037
Feature activation+2.16e-01

Pos logit contributions
 She+0.010
 day+0.010
 she+0.009
 weekend+0.009
my+0.009
Neg logit contributions
itched-0.016
 tal-0.016
eg-0.015
orse-0.015
izza-0.014
Token always
Token ID1464
Feature activation+3.97e-01

Pos logit contributions
 She+0.322
 she+0.306
 day+0.304
 weekend+0.287
 week+0.278
Neg logit contributions
itched-0.502
 tal-0.472
eg-0.445
orse-0.435
 fin-0.415
Token cleaned
Token ID20750
Feature activation-3.00e-02

Pos logit contributions
 She+0.700
 she+0.679
 day+0.676
 like+0.610
 especially+0.608
Neg logit contributions
itched-0.845
 tal-0.812
eg-0.752
orse-0.718
 fin-0.700
Token and
Token ID290
Feature activation+1.73e-01

Pos logit contributions
 She+0.341
 she+0.335
 day+0.334
 like+0.299
 sometimes+0.298
Neg logit contributions
itched-0.445
 tal-0.428
eg-0.403
orse-0.379
izza-0.373
Token it
Token ID340
Feature activation+2.05e-02

Pos logit contributions
 She+0.280
 day+0.273
 she+0.271
 like+0.243
 always+0.242
Neg logit contributions
itched-0.387
 tal-0.373
eg-0.350
orse-0.333
izza-0.326
Token was
Token ID373
Feature activation+5.42e-02

Pos logit contributions
 She+0.031
 she+0.030
 day+0.030
 always+0.027
 like+0.027
Neg logit contributions
itched-0.049
 tal-0.047
eg-0.045
orse-0.042
izza-0.042
Token a
Token ID257
Feature activation-1.13e-02

Pos logit contributions
 day+0.076
 she+0.074
 She+0.073
 always+0.067
 like+0.067
Neg logit contributions
itched-0.137
 tal-0.132
eg-0.129
orse-0.121
izza-0.120
Token wonderful
Token ID7932
Feature activation+9.82e-02

Pos logit contributions
itched+0.027
 tal+0.026
eg+0.024
orse+0.023
izza+0.023
Neg logit contributions
 day-0.017
 She-0.017
 she-0.017
 like-0.015
 always-0.015
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.121
 she+0.117
 day+0.117
 like+0.100
 always+0.100
Neg logit contributions
itched-0.262
 tal-0.253
eg-0.240
orse-0.230
izza-0.226
Token.
Token ID13
Feature activation+4.49e-03

Pos logit contributions
 day+0.751
 she+0.750
 She+0.737
 like+0.667
 always+0.651
Neg logit contributions
itched-1.135
 tal-1.106
eg-1.083
izza-0.988
orse-0.967
Token
Token ID220
Feature activation-1.69e-01

Pos logit contributions
 She+0.008
 day+0.008
 she+0.008
 like+0.007
 always+0.007
Neg logit contributions
itched-0.009
 tal-0.009
eg-0.008
orse-0.008
izza-0.008
Token
Token ID198
Feature activation-7.78e-02

Pos logit contributions
itched+0.405
 tal+0.402
eg+0.378
 fin+0.375
urger+0.368
Neg logit contributions
 She-0.291
 she-0.254
 day-0.238
my-0.224
 always-0.206
Token
Token ID198
Feature activation-7.91e-02

Pos logit contributions
itched+0.169
 tal+0.163
eg+0.155
 fin+0.143
urger+0.142
Neg logit contributions
 She-0.143
 day-0.137
 she-0.137
 especially-0.122
my-0.121
TokenIn
Token ID818
Feature activation+1.06e-01

Pos logit contributions
itched+0.180
 tal+0.172
eg+0.162
orse+0.157
izza+0.152
Neg logit contributions
 She-0.124
 day-0.122
 she-0.122
 like-0.111
 sometimes-0.108
Tokenummy
Token ID13513
Feature activation+1.86e-01

Pos logit contributions
 She+0.022
 she+0.022
 day+0.021
 like+0.019
 always+0.019
Neg logit contributions
itched-0.036
 tal-0.035
eg-0.033
orse-0.031
izza-0.031
Token lunch
Token ID9965
Feature activation-5.96e-02

Pos logit contributions
 She+0.305
 day+0.294
 she+0.293
 especially+0.265
 sometimes+0.264
Neg logit contributions
itched-0.407
 tal-0.396
eg-0.364
orse-0.352
izza-0.346
Token.
Token ID13
Feature activation+2.99e-02

Pos logit contributions
itched+0.128
 tal+0.122
eg+0.114
orse+0.111
izza+0.109
Neg logit contributions
 She-0.098
 day-0.093
 she-0.092
 matter-0.085
 sometimes-0.085
Token From
Token ID3574
Feature activation-1.56e-01

Pos logit contributions
 She+0.045
 day+0.045
 she+0.045
 like+0.040
 always+0.040
Neg logit contributions
itched-0.070
 tal-0.067
eg-0.063
orse-0.060
izza-0.059
Token that
Token ID326
Feature activation+4.14e-02

Pos logit contributions
itched+0.345
 tal+0.334
eg+0.305
orse+0.294
 fin+0.289
Neg logit contributions
 She-0.254
 she-0.240
 day-0.239
 especially-0.218
 like-0.214
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.021
 she+0.014
She+0.010
 like+0.008
 especially+0.008
Neg logit contributions
 tal-0.136
itched-0.135
orse-0.128
eg-0.127
 fin-0.126
Token on
Token ID319
Feature activation+3.78e-02

Pos logit contributions
 She+0.749
 day+0.736
 she+0.735
 like+0.648
 always+0.646
Neg logit contributions
itched-1.137
 tal-1.098
eg-1.038
orse-0.986
izza-0.972
Token,
Token ID11
Feature activation+1.48e-02

Pos logit contributions
 She+0.070
 day+0.068
 she+0.066
 especially+0.065
 like+0.065
Neg logit contributions
itched-0.074
 tal-0.070
eg-0.062
orse-0.059
ves-0.059
Token Tim
Token ID5045
Feature activation+5.31e-02

Pos logit contributions
 She+0.021
 day+0.020
 weekend+0.019
ock+0.019
my+0.019
Neg logit contributions
 tal-0.031
itched-0.030
eg-0.028
orse-0.028
izza-0.027
Tokenmy
Token ID1820
Feature activation+4.10e-01

Pos logit contributions
 She+0.044
 she+0.040
She+0.028
 weekend+0.028
Welcome+0.027
Neg logit contributions
itched-0.153
 tal-0.150
eg-0.143
orse-0.141
urger-0.138
Token always
Token ID1464
Feature activation+3.97e-01

Pos logit contributions
 She+0.587
 she+0.561
 day+0.543
 weekend+0.494
 like+0.488
Neg logit contributions
itched-0.997
 tal-0.952
eg-0.902
orse-0.878
 fin-0.845
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
itched+0.628
 tal+0.592
eg+0.554
orse+0.539
 fin+0.524
Neg logit contributions
 She-0.411
 day-0.395
 she-0.381
 weekend-0.357
 especially-0.351
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenFrom
Token ID4863
Feature activation+6.65e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+4.02e-02

Pos logit contributions
 She+0.011
 day+0.011
 she+0.011
 especially+0.010
my+0.010
Neg logit contributions
itched-0.015
 tal-0.014
eg-0.013
orse-0.012
 fin-0.012
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.020
 she+0.013
She+0.010
 especially+0.010
 like+0.009
Neg logit contributions
 tal-0.132
itched-0.132
eg-0.123
orse-0.123
 fin-0.122
Token on
Token ID319
Feature activation+3.45e-02

Pos logit contributions
 She+0.775
 day+0.757
 she+0.756
 like+0.675
 always+0.672
Neg logit contributions
itched-1.111
 tal-1.065
eg-1.005
orse-0.951
izza-0.933
Token,
Token ID11
Feature activation+9.42e-03

Pos logit contributions
 She+0.065
 day+0.063
 especially+0.062
 she+0.061
 like+0.061
Neg logit contributions
itched-0.066
 tal-0.062
eg-0.055
ves-0.052
orse-0.052
Token Owen
Token ID22605
Feature activation-2.04e-01

Pos logit contributions
 She+0.014
 day+0.013
 she+0.012
 weekend+0.012
my+0.012
Neg logit contributions
itched-0.020
 tal-0.020
eg-0.019
orse-0.018
ves-0.017
Token was
Token ID373
Feature activation+2.52e-02

Pos logit contributions
itched+0.497
 tal+0.473
eg+0.452
orse+0.434
izza+0.417
Neg logit contributions
 She-0.280
 she-0.270
 day-0.267
 weekend-0.236
 week-0.233
Token more
Token ID517
Feature activation+1.01e-01

Pos logit contributions
 She+0.033
 day+0.032
 she+0.032
 like+0.028
 sometimes+0.028
Neg logit contributions
itched-0.065
 tal-0.063
eg-0.060
orse-0.057
izza-0.056
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
itched+0.235
cks+0.219
 tal+0.215
eg+0.212
ves+0.208
Neg logit contributions
 day-0.133
 she-0.129
 She-0.121
 girl-0.114
 like-0.113
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenFrom
Token ID4863
Feature activation+6.65e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+4.02e-02

Pos logit contributions
 She+0.011
 day+0.011
 she+0.011
 especially+0.010
my+0.010
Neg logit contributions
itched-0.015
 tal-0.014
eg-0.013
orse-0.012
 fin-0.012
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.020
 she+0.013
She+0.010
 especially+0.010
 like+0.009
Neg logit contributions
 tal-0.132
itched-0.132
eg-0.123
orse-0.123
 fin-0.122
Token on
Token ID319
Feature activation+3.45e-02

Pos logit contributions
 She+0.775
 day+0.757
 she+0.756
 like+0.675
 always+0.672
Neg logit contributions
itched-1.111
 tal-1.065
eg-1.005
orse-0.951
izza-0.933
Token,
Token ID11
Feature activation+9.42e-03

Pos logit contributions
 She+0.065
 day+0.063
 especially+0.062
 she+0.061
 like+0.061
Neg logit contributions
itched-0.066
 tal-0.062
eg-0.055
ves-0.052
orse-0.052
Token Tim
Token ID5045
Feature activation+5.09e-02

Pos logit contributions
 She+0.014
 day+0.013
 she+0.012
 weekend+0.012
my+0.012
Neg logit contributions
itched-0.020
 tal-0.020
eg-0.019
orse-0.018
ves-0.017
Tokenmy
Token ID1820
Feature activation+4.09e-01

Pos logit contributions
 She+0.041
 she+0.038
 weekend+0.027
 day+0.025
She+0.023
Neg logit contributions
itched-0.150
 tal-0.146
eg-0.140
orse-0.135
 fin-0.132
Token always
Token ID1464
Feature activation+3.98e-01

Pos logit contributions
 She+0.572
 she+0.551
 day+0.548
 weekend+0.481
 like+0.477
Neg logit contributions
itched-1.017
 tal-0.972
eg-0.921
orse-0.886
 fin-0.857
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
itched+0.077
 tal+0.075
eg+0.067
 fin+0.066
orse+0.065
Neg logit contributions
 She-0.079
 she-0.075
 day-0.072
my-0.069
 like-0.068
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenFrom
Token ID4863
Feature activation+6.65e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+4.02e-02

Pos logit contributions
 She+0.011
 day+0.011
 she+0.011
 especially+0.010
my+0.010
Neg logit contributions
itched-0.015
 tal-0.014
eg-0.013
orse-0.012
 fin-0.012
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.020
 she+0.013
She+0.010
 especially+0.010
 like+0.009
Neg logit contributions
 tal-0.132
itched-0.132
eg-0.123
orse-0.123
 fin-0.122
Token on
Token ID319
Feature activation+3.45e-02

Pos logit contributions
 She+0.775
 day+0.757
 she+0.756
 like+0.675
 always+0.672
Neg logit contributions
itched-1.111
 tal-1.065
eg-1.005
orse-0.951
izza-0.933
Token,
Token ID11
Feature activation+9.42e-03

Pos logit contributions
 She+0.065
 day+0.063
 especially+0.062
 she+0.061
 like+0.061
Neg logit contributions
itched-0.066
 tal-0.062
eg-0.055
ves-0.052
orse-0.052
Token they
Token ID484
Feature activation+4.74e-02

Pos logit contributions
 She+0.014
 day+0.013
 she+0.012
 weekend+0.012
my+0.012
Neg logit contributions
itched-0.020
 tal-0.020
eg-0.019
orse-0.018
ves-0.017
Token learned
Token ID4499
Feature activation-2.60e-02

Pos logit contributions
 She+0.059
 day+0.056
 she+0.056
 weekend+0.052
 week+0.050
Neg logit contributions
itched-0.119
 tal-0.114
eg-0.111
orse-0.106
 fin-0.103
Token that
Token ID326
Feature activation+2.78e-02

Pos logit contributions
itched+0.064
 tal+0.062
eg+0.060
orse+0.057
izza+0.055
Neg logit contributions
 she-0.040
 She-0.039
 day-0.039
 sometimes-0.035
 like-0.035
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
itched+0.371
 tal+0.356
eg+0.332
orse+0.321
 fin+0.319
Neg logit contributions
 She-0.261
 she-0.246
 day-0.239
 like-0.224
 especially-0.222
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenFrom
Token ID4863
Feature activation+6.65e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+4.02e-02

Pos logit contributions
 She+0.011
 day+0.011
 she+0.011
 especially+0.010
my+0.010
Neg logit contributions
itched-0.015
 tal-0.014
eg-0.013
orse-0.012
 fin-0.012
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.020
 she+0.013
She+0.010
 especially+0.010
 like+0.009
Neg logit contributions
 tal-0.132
itched-0.132
eg-0.123
orse-0.123
 fin-0.122
Token on
Token ID319
Feature activation+3.45e-02

Pos logit contributions
 She+0.775
 day+0.757
 she+0.756
 like+0.675
 always+0.672
Neg logit contributions
itched-1.111
 tal-1.065
eg-1.005
orse-0.951
izza-0.933
Token,
Token ID11
Feature activation+9.42e-03

Pos logit contributions
 She+0.065
 day+0.063
 especially+0.062
 she+0.061
 like+0.061
Neg logit contributions
itched-0.066
 tal-0.062
eg-0.055
ves-0.052
orse-0.052
Token Amy
Token ID14235
Feature activation+6.40e-02

Pos logit contributions
 She+0.014
 day+0.013
 she+0.012
 weekend+0.012
my+0.012
Neg logit contributions
itched-0.020
 tal-0.020
eg-0.019
orse-0.018
ves-0.017
Token learned
Token ID4499
Feature activation-2.78e-02

Pos logit contributions
 She+0.085
 day+0.082
 she+0.081
 weekend+0.075
 week+0.073
Neg logit contributions
itched-0.159
 tal-0.151
eg-0.142
orse-0.137
 fin-0.133
Token to
Token ID284
Feature activation-1.40e-02

Pos logit contributions
itched+0.060
 tal+0.058
eg+0.054
orse+0.050
izza+0.050
Neg logit contributions
 She-0.047
 day-0.047
 she-0.046
 especially-0.042
 like-0.041
Tokenopl
Token ID20106
Feature activation+5.66e-02

Pos logit contributions
 She+0.133
 she+0.118
my+0.118
 especially+0.114
 day+0.111
Neg logit contributions
 tal-0.170
itched-0.168
 fin-0.152
eg-0.150
orse-0.149
Tokenane
Token ID1531
Feature activation+8.48e-03

Pos logit contributions
 She+0.105
 day+0.104
 she+0.103
 like+0.094
 always+0.093
Neg logit contributions
itched-0.114
 tal-0.110
eg-0.102
orse-0.095
izza-0.095
Token.
Token ID13
Feature activation+4.11e-02

Pos logit contributions
 day+0.013
 she+0.013
 She+0.013
 always+0.012
 like+0.012
Neg logit contributions
itched-0.020
 tal-0.019
eg-0.018
izza-0.017
orse-0.017
Token<|endoftext|>
Token ID50256
Feature activation-1.96e-01

Pos logit contributions
 She+0.057
 day+0.056
 she+0.056
 like+0.049
 always+0.049
Neg logit contributions
itched-0.102
 tal-0.098
eg-0.093
orse-0.089
izza-0.087
TokenOne
Token ID3198
Feature activation+2.33e-01

Pos logit contributions
itched+0.444
 tal+0.429
eg+0.407
urger+0.391
izza+0.387
Neg logit contributions
 She-0.343
 day-0.334
 she-0.318
my-0.290
 like-0.284
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.132
 she+0.090
Why+0.071
You+0.068
 especially+0.068
Neg logit contributions
itched-0.743
 tal-0.737
orse-0.714
 fin-0.674
eg-0.672
Token,
Token ID11
Feature activation+1.60e-02

Pos logit contributions
 she+0.729
 day+0.719
 She+0.701
 week+0.601
 like+0.599
Neg logit contributions
 tal-1.185
itched-1.160
eg-1.096
 wounds-1.062
izza-1.040
Token a
Token ID257
Feature activation-2.23e-02

Pos logit contributions
 She+0.028
 she+0.027
 day+0.027
 like+0.024
 always+0.024
Neg logit contributions
itched-0.035
 tal-0.034
eg-0.032
orse-0.030
izza-0.029
Token turkey
Token ID26876
Feature activation-3.59e-02

Pos logit contributions
itched+0.050
 tal+0.047
eg+0.046
orse+0.043
 fin+0.042
Neg logit contributions
 She-0.037
 she-0.035
 day-0.035
 sometimes-0.032
 like-0.032
Token had
Token ID550
Feature activation+1.54e-01

Pos logit contributions
itched+0.078
 tal+0.074
eg+0.069
orse+0.067
 fin+0.064
Neg logit contributions
 She-0.061
 she-0.059
 day-0.059
 weekend-0.053
 especially-0.053
Token an
Token ID281
Feature activation-9.60e-02

Pos logit contributions
 She+0.256
 she+0.250
 day+0.248
 always+0.224
 like+0.219
Neg logit contributions
itched-0.350
 tal-0.335
eg-0.323
orse-0.302
izza-0.302
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
 She+0.154
 she+0.151
 day+0.149
 weekend+0.137
 always+0.137
Neg logit contributions
itched-0.170
 tal-0.162
eg-0.149
 fin-0.139
orse-0.139
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenLater
Token ID18602
Feature activation+1.75e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+3.84e-02

Pos logit contributions
 She+0.003
 day+0.003
 she+0.003
 especially+0.003
 like+0.003
Neg logit contributions
itched-0.004
 tal-0.004
eg-0.003
orse-0.003
izza-0.003
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.012
 she+0.008
 especially+0.006
 like+0.005
 sometimes+0.003
Neg logit contributions
itched-0.134
 tal-0.130
eg-0.125
orse-0.124
 fin-0.121
Token,
Token ID11
Feature activation+6.32e-03

Pos logit contributions
 she+0.773
 She+0.760
 day+0.749
 always+0.639
 week+0.638
Neg logit contributions
itched-1.134
 tal-1.117
eg-1.047
orse-0.997
izza-0.987
Token Lucy
Token ID22162
Feature activation+1.28e-01

Pos logit contributions
 She+0.008
 day+0.008
 she+0.008
 especially+0.007
 sometimes+0.007
Neg logit contributions
itched-0.016
 tal-0.015
eg-0.014
orse-0.014
izza-0.014
Token knew
Token ID2993
Feature activation+5.06e-02

Pos logit contributions
 She+0.199
 day+0.196
 she+0.195
 like+0.173
 weekend+0.172
Neg logit contributions
itched-0.295
 tal-0.282
eg-0.265
orse-0.253
izza-0.245
Token something
Token ID1223
Feature activation-1.12e-01

Pos logit contributions
 day+0.043
 She+0.043
my+0.036
 weekend+0.035
 especially+0.035
Neg logit contributions
itched-0.146
 tal-0.142
eg-0.130
orse-0.130
ves-0.129
Token was
Token ID373
Feature activation+2.15e-02

Pos logit contributions
 tal+0.218
itched+0.215
ves+0.197
eg+0.187
ggy+0.186
Neg logit contributions
 She-0.186
my-0.169
 day-0.169
 weekend-0.162
 she-0.161
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
itched+0.319
 tal+0.311
eg+0.294
 fin+0.278
urger+0.278
Neg logit contributions
 She-0.251
 she-0.241
 day-0.235
my-0.209
 week-0.206
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenLater
Token ID18602
Feature activation+1.75e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+3.84e-02

Pos logit contributions
 She+0.003
 day+0.003
 she+0.003
 especially+0.003
 like+0.003
Neg logit contributions
itched-0.004
 tal-0.004
eg-0.003
orse-0.003
izza-0.003
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.012
 she+0.008
 especially+0.006
 like+0.005
 sometimes+0.003
Neg logit contributions
itched-0.134
 tal-0.130
eg-0.125
orse-0.124
 fin-0.121
Token,
Token ID11
Feature activation+6.32e-03

Pos logit contributions
 she+0.773
 She+0.760
 day+0.749
 always+0.639
 week+0.638
Neg logit contributions
itched-1.134
 tal-1.117
eg-1.047
orse-0.997
izza-0.987
Token Tim
Token ID5045
Feature activation+5.22e-02

Pos logit contributions
 She+0.008
 day+0.008
 she+0.008
 especially+0.007
 sometimes+0.007
Neg logit contributions
itched-0.016
 tal-0.015
eg-0.014
orse-0.014
izza-0.014
Tokenmy
Token ID1820
Feature activation+4.09e-01

Pos logit contributions
 She+0.030
 she+0.029
 day+0.024
 weekend+0.018
 especially+0.018
Neg logit contributions
itched-0.167
 tal-0.163
eg-0.157
orse-0.152
 fin-0.149
Token and
Token ID290
Feature activation+1.24e-01

Pos logit contributions
 She+0.597
 she+0.591
 day+0.581
 always+0.534
my+0.525
Neg logit contributions
itched-1.014
 tal-0.979
eg-0.928
izza-0.886
ades-0.875
Token his
Token ID465
Feature activation-7.34e-02

Pos logit contributions
 She+0.233
 day+0.228
 she+0.228
 like+0.207
 always+0.206
Neg logit contributions
itched-0.253
 tal-0.242
eg-0.226
orse-0.213
izza-0.208
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
itched+0.113
 tal+0.108
eg+0.103
izza+0.095
orse+0.094
Neg logit contributions
 day-0.105
 She-0.103
 she-0.101
 weekend-0.096
 week-0.095
Token
Token ID198
Feature activation-4.23e-02

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
Token
Token ID198
Feature activation-4.82e-02

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.081
urger+0.075
 fin+0.074
Neg logit contributions
 She-0.081
 day-0.077
 she-0.076
my-0.069
 week-0.068
TokenLater
Token ID18602
Feature activation+1.75e-03

Pos logit contributions
itched+0.114
 tal+0.109
eg+0.103
orse+0.099
izza+0.096
Neg logit contributions
 She-0.073
 day-0.072
 she-0.072
 like-0.064
 always-0.063
Token that
Token ID326
Feature activation+3.84e-02

Pos logit contributions
 She+0.003
 day+0.003
 she+0.003
 especially+0.003
 like+0.003
Neg logit contributions
itched-0.004
 tal-0.004
eg-0.003
orse-0.003
izza-0.003
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.012
 she+0.008
 especially+0.006
 like+0.005
 sometimes+0.003
Neg logit contributions
itched-0.134
 tal-0.130
eg-0.125
orse-0.124
 fin-0.121
Token,
Token ID11
Feature activation+6.32e-03

Pos logit contributions
 she+0.773
 She+0.760
 day+0.749
 always+0.639
 week+0.638
Neg logit contributions
itched-1.134
 tal-1.117
eg-1.047
orse-0.997
izza-0.987
Token when
Token ID618
Feature activation+2.62e-01

Pos logit contributions
 She+0.008
 day+0.008
 she+0.008
 especially+0.007
 sometimes+0.007
Neg logit contributions
itched-0.016
 tal-0.015
eg-0.014
orse-0.014
izza-0.014
Token her
Token ID607
Feature activation+3.66e-01

Pos logit contributions
 She+0.383
 day+0.361
 she+0.346
 especially+0.336
my+0.334
Neg logit contributions
itched-0.608
 tal-0.586
eg-0.547
orse-0.533
 fin-0.515
Token mom
Token ID1995
Feature activation-1.65e-01

Pos logit contributions
 day+0.709
 she+0.675
 She+0.642
 always+0.610
 girl+0.608
Neg logit contributions
itched-0.757
 tal-0.737
eg-0.665
cks-0.651
orse-0.642
Tokenmy
Token ID1820
Feature activation+4.05e-01

Pos logit contributions
itched+0.470
 tal+0.441
eg+0.430
izza+0.408
orse+0.407
Neg logit contributions
 day-0.157
 She-0.150
 she-0.146
 like-0.123
 weekend-0.123
Token answer
Token ID3280
Feature activation+1.53e-01

Pos logit contributions
 tal+0.071
eg+0.065
itched+0.063
 fin+0.063
 rods+0.061
Neg logit contributions
 she-0.066
 especially-0.064
 She-0.064
 weekend-0.062
 sometimes-0.062
Token questions
Token ID2683
Feature activation+3.23e-02

Pos logit contributions
 She+0.245
 day+0.239
 she+0.237
 always+0.212
 especially+0.211
Neg logit contributions
itched-0.347
 tal-0.334
eg-0.311
orse-0.297
izza-0.291
Token.
Token ID13
Feature activation+3.25e-02

Pos logit contributions
 She+0.053
 day+0.052
 she+0.051
 especially+0.046
 weekend+0.046
Neg logit contributions
itched-0.070
 tal-0.066
eg-0.062
orse-0.059
izza-0.059
Token From
Token ID3574
Feature activation-1.57e-01

Pos logit contributions
 She+0.046
 she+0.044
 day+0.044
 like+0.038
 sometimes+0.038
Neg logit contributions
itched-0.081
 tal-0.078
eg-0.074
orse-0.070
izza-0.069
Token that
Token ID326
Feature activation+4.53e-02

Pos logit contributions
itched+0.357
 tal+0.345
eg+0.318
orse+0.306
 fin+0.299
Neg logit contributions
 She-0.245
 day-0.235
 she-0.233
 especially-0.212
 always-0.208
Token day
Token ID1110
Feature activation+4.83e-01

Pos logit contributions
 She+0.017
 she+0.011
 especially+0.008
 like+0.006
She+0.006
Neg logit contributions
itched-0.153
 tal-0.151
eg-0.143
orse-0.141
izza-0.140
Token on
Token ID319
Feature activation+3.75e-02

Pos logit contributions
 She+0.756
 she+0.741
 day+0.741
 like+0.655
 always+0.653
Neg logit contributions
itched-1.128
 tal-1.088
eg-1.028
orse-0.976
izza-0.959
Token,
Token ID11
Feature activation+1.48e-02

Pos logit contributions
 She+0.068
 day+0.066
 she+0.064
 especially+0.062
 like+0.062
Neg logit contributions
itched-0.075
 tal-0.071
eg-0.064
orse-0.061
ves-0.061
Token Tim
Token ID5045
Feature activation+5.09e-02

Pos logit contributions
 She+0.021
 day+0.020
 weekend+0.019
my+0.018
ock+0.018
Neg logit contributions
itched-0.032
 tal-0.032
eg-0.029
orse-0.029
ves-0.028
Tokenmy
Token ID1820
Feature activation+4.09e-01

Pos logit contributions
 She+0.048
 she+0.045
 weekend+0.035
She+0.033
 day+0.033
Neg logit contributions
itched-0.140
 tal-0.137
eg-0.130
orse-0.126
urger-0.121
Token and
Token ID290
Feature activation+1.30e-01

Pos logit contributions
 She+0.627
 she+0.604
 day+0.598
 weekend+0.553
 week+0.540
Neg logit contributions
itched-0.941
 tal-0.897
eg-0.840
orse-0.812
 fin-0.778
Token them
Token ID606
Feature activation+5.37e-02

Pos logit contributions
 day+0.093
 She+0.093
 she+0.089
 weekend+0.085
 week+0.083
Neg logit contributions
itched-0.130
 tal-0.123
eg-0.120
orse-0.112
izza-0.112
Token.
Token ID13
Feature activation+3.92e-02

Pos logit contributions
 day+0.079
 she+0.078
 She+0.076
 like+0.073
 sometimes+0.069
Neg logit contributions
itched-0.133
 tal-0.128
eg-0.123
orse-0.114
izza-0.113
Token
Token ID198
Feature activation-4.71e-02

Pos logit contributions
 She+0.058
 she+0.055
 day+0.054
 sometimes+0.048
 like+0.048
Neg logit contributions
itched-0.097
 tal-0.094
eg-0.089
orse-0.083
izza-0.082
Token
Token ID198
Feature activation-5.64e-02

Pos logit contributions
itched+0.106
 tal+0.102
eg+0.097
urger+0.092
 fin+0.090
Neg logit contributions
 She-0.084
 day-0.078
 she-0.078
my-0.070
 week-0.069
TokenOne
Token ID3198
Feature activation+2.30e-01

Pos logit contributions
itched+0.135
 tal+0.130
eg+0.123
orse+0.117
izza+0.115
Neg logit contributions
 She-0.084
 day-0.083
 she-0.082
 like-0.073
 always-0.073
Token day
Token ID1110
Feature activation+4.82e-01

Pos logit contributions
 She+0.104
 she+0.068
my+0.040
She+0.040
 especially+0.039
Neg logit contributions
itched-0.759
 tal-0.746
orse-0.724
 fin-0.714
eg-0.708
Token,
Token ID11
Feature activation+9.63e-03

Pos logit contributions
 she+0.748
 She+0.703
 day+0.679
 like+0.611
 her+0.577
Neg logit contributions
itched-1.219
 tal-1.194
eg-1.122
orse-1.058
 wounds-1.055
Token they
Token ID484
Feature activation+5.18e-02

Pos logit contributions
 She+0.015
 day+0.015
 she+0.014
 like+0.013
 always+0.013
Neg logit contributions
itched-0.022
 tal-0.021
eg-0.020
orse-0.019
izza-0.019
Token see
Token ID766
Feature activation+2.05e-02

Pos logit contributions
 She+0.075
 day+0.074
 she+0.073
 weekend+0.064
 week+0.064
Neg logit contributions
itched-0.122
 tal-0.118
eg-0.113
orse-0.107
 fin-0.106
Token a
Token ID257
Feature activation-2.82e-02

Pos logit contributions
 she+0.029
 day+0.027
 She+0.027
 like+0.027
 sometimes+0.025
Neg logit contributions
itched-0.055
eg-0.053
 tal-0.052
urger-0.048
orse-0.048
Token big
Token ID1263
Feature activation+1.41e-02

Pos logit contributions
itched+0.071
 tal+0.068
eg+0.062
orse+0.060
cks+0.060
Neg logit contributions
 day-0.043
 she-0.041
 She-0.039
 girl-0.037
 week-0.036
Token them
Token ID606
Feature activation+5.37e-02

Pos logit contributions
 She+0.198
 day+0.190
 she+0.186
 weekend+0.175
 especially+0.172
Neg logit contributions
itched-0.235
 tal-0.220
 fin-0.196
eg-0.196
 cannon-0.191
Token.
Token ID13
Feature activation+3.92e-02

Pos logit contributions
 day+0.079
 she+0.078
 She+0.076
 like+0.073
 sometimes+0.069
Neg logit contributions
itched-0.133
 tal-0.128
eg-0.123
orse-0.114
izza-0.113
Token
Token ID198
Feature activation-4.71e-02

Pos logit contributions
 She+0.058
 she+0.055
 day+0.054
 sometimes+0.048
 like+0.048
Neg logit contributions
itched-0.097
 tal-0.094
eg-0.089
orse-0.083
izza-0.082
Token
Token ID198
Feature activation-5.64e-02

Pos logit contributions
itched+0.106
 tal+0.102
eg+0.097
urger+0.092
 fin+0.090
Neg logit contributions
 She-0.084
 day-0.078
 she-0.078
my-0.070
 week-0.069
TokenOne
Token ID3198
Feature activation+2.30e-01

Pos logit contributions
itched+0.135
 tal+0.130
eg+0.123
orse+0.117
izza+0.115
Neg logit contributions
 She-0.084
 day-0.083
 she-0.082
 like-0.073
 always-0.073
Token day
Token ID1110
Feature activation+4.82e-01

Pos logit contributions
 She+0.104
 she+0.068
my+0.040
She+0.040
 especially+0.039
Neg logit contributions
itched-0.759
 tal-0.746
orse-0.724
 fin-0.714
eg-0.708
Token,
Token ID11
Feature activation+9.63e-03

Pos logit contributions
 she+0.748
 She+0.703
 day+0.679
 like+0.611
 her+0.577
Neg logit contributions
itched-1.219
 tal-1.194
eg-1.122
orse-1.058
 wounds-1.055
Token they
Token ID484
Feature activation+5.18e-02

Pos logit contributions
 She+0.015
 day+0.015
 she+0.014
 like+0.013
 always+0.013
Neg logit contributions
itched-0.022
 tal-0.021
eg-0.020
orse-0.019
izza-0.019
Token found
Token ID1043
Feature activation+2.63e-02

Pos logit contributions
 She+0.075
 day+0.074
 she+0.073
 weekend+0.064
 week+0.064
Neg logit contributions
itched-0.122
 tal-0.118
eg-0.113
orse-0.107
 fin-0.106
Token something
Token ID1223
Feature activation-1.08e-01

Pos logit contributions
 she+0.035
 day+0.034
 She+0.034
 like+0.032
 her+0.031
Neg logit contributions
itched-0.072
eg-0.067
 tal-0.065
orse-0.065
anas-0.063
Token different
Token ID1180
Feature activation+1.33e-01

Pos logit contributions
itched+0.262
 tal+0.252
eg+0.240
orse+0.227
izza+0.224
Neg logit contributions
 she-0.159
 She-0.159
 day-0.158
 like-0.141
 always-0.138
Token and
Token ID290
Feature activation+7.15e-02

Pos logit contributions
itched+0.734
 tal+0.702
eg+0.661
orse+0.627
izza+0.614
Neg logit contributions
 She-0.523
 day-0.511
 she-0.509
 always-0.453
 like-0.452
Token his
Token ID465
Feature activation-1.28e-01

Pos logit contributions
 She+0.117
 day+0.114
 she+0.113
 like+0.102
 always+0.101
Neg logit contributions
itched-0.161
 tal-0.155
eg-0.145
orse-0.138
izza-0.135
Token dark
Token ID3223
Feature activation+1.80e-01

Pos logit contributions
itched+0.228
 tal+0.218
orse+0.216
engu+0.215
cks+0.212
Neg logit contributions
 day-0.276
 she-0.241
 She-0.236
 gloomy-0.234
 wind-0.232
Token mustache
Token ID49303
Feature activation-2.05e-01

Pos logit contributions
 day+0.392
 She+0.390
 she+0.385
my+0.363
 always+0.358
Neg logit contributions
itched-0.287
 tal-0.274
eg-0.272
izza-0.267
engu-0.250
Token tw
Token ID665
Feature activation+6.80e-03

Pos logit contributions
 tal+0.497
itched+0.485
eg+0.470
izza+0.454
orse+0.445
Neg logit contributions
 she-0.309
 She-0.297
 day-0.295
 always-0.279
 like-0.264
Tokenitched
Token ID10981
Feature activation-6.79e-01

Pos logit contributions
 She+0.016
 always+0.015
 she+0.015
 especially+0.015
 day+0.015
Neg logit contributions
 tal-0.008
izza-0.008
 cannon-0.008
 rods-0.007
eg-0.007
Token with
Token ID351
Feature activation-6.33e-02

Pos logit contributions
itched+1.523
 tal+1.475
eg+1.401
orse+1.338
izza+1.307
Neg logit contributions
 She-1.119
 she-1.094
 day-1.093
 like-0.996
 always-0.978
Token joy
Token ID8716
Feature activation-8.82e-02

Pos logit contributions
itched+0.134
 tal+0.127
eg+0.123
orse+0.116
izza+0.115
Neg logit contributions
 She-0.113
 she-0.112
 day-0.111
 like-0.102
 always-0.100
Token.
Token ID13
Feature activation-5.59e-02

Pos logit contributions
itched+0.198
 tal+0.195
eg+0.184
orse+0.174
izza+0.172
Neg logit contributions
 she-0.145
 She-0.145
 day-0.141
 like-0.130
 always-0.127
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
itched+0.119
 tal+0.114
eg+0.107
orse+0.101
izza+0.099
Neg logit contributions
 She-0.100
 she-0.098
 day-0.098
 always-0.088
 like-0.087
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
 tal+0.278
itched+0.274
 jaws+0.262
urger+0.257
 fins+0.257
Neg logit contributions
 day-0.267
 She-0.266
 she-0.253
She-0.227
 always-0.225
Token She
Token ID1375
Feature activation+4.05e-01

Pos logit contributions
itched+0.167
 tal+0.158
eg+0.150
izza+0.148
rolled+0.145
Neg logit contributions
 day-0.057
 she-0.049
 especially-0.049
 weekend-0.047
 matter-0.047
Token st
Token ID336
Feature activation-1.21e-01

Pos logit contributions
 she+0.622
 day+0.603
 She+0.592
 always+0.579
 sometimes+0.565
Neg logit contributions
itched-0.959
 tal-0.943
eg-0.917
izza-0.866
urger-0.831
Tokenitched
Token ID10981
Feature activation-6.76e-01

Pos logit contributions
 tal+0.135
orse+0.129
 fin+0.118
urger+0.118
 cannon+0.116
Neg logit contributions
 She-0.325
 she-0.281
my-0.275
She-0.272
 her-0.261
Token and
Token ID290
Feature activation+7.11e-02

Pos logit contributions
itched+1.681
 tal+1.657
eg+1.616
orse+1.543
izza+1.511
Neg logit contributions
 She-0.968
 she-0.958
 day-0.931
 like-0.847
 sometimes-0.834
Token st
Token ID336
Feature activation-1.21e-01

Pos logit contributions
 she+0.123
 day+0.120
 She+0.117
 sometimes+0.110
 always+0.109
Neg logit contributions
itched-0.157
eg-0.152
 tal-0.152
izza-0.140
ades-0.137
Tokenitched
Token ID10981
Feature activation-6.77e-01

Pos logit contributions
orse+0.124
 tal+0.123
 fin+0.115
 gru+0.111
urger+0.110
Neg logit contributions
 She-0.333
 she-0.292
 like-0.284
She-0.280
 her-0.276
Token until
Token ID1566
Feature activation+3.78e-03

Pos logit contributions
itched+1.684
 tal+1.656
eg+1.607
orse+1.535
izza+1.502
Neg logit contributions
 She-0.969
 she-0.955
 day-0.927
 like-0.850
 sometimes-0.825
Token she
Token ID673
Feature activation+3.98e-01

Pos logit contributions
 She+0.005
 day+0.004
my+0.004
 especially+0.004
 like+0.004
Neg logit contributions
itched-0.010
 tal-0.009
eg-0.009
orse-0.009
ves-0.008
Token had
Token ID550
Feature activation+9.13e-02

Pos logit contributions
 she+0.573
 day+0.561
 She+0.551
 always+0.524
 like+0.510
Neg logit contributions
itched-0.985
 tal-0.970
eg-0.919
izza-0.873
ades-0.845
Token a
Token ID257
Feature activation-8.95e-02

Pos logit contributions
 She+0.148
 she+0.148
 day+0.143
 always+0.135
 like+0.133
Neg logit contributions
itched-0.212
 tal-0.200
eg-0.196
orse-0.185
izza-0.179
Token beautiful
Token ID4950
Feature activation+1.47e-02

Pos logit contributions
itched+0.221
 tal+0.212
eg+0.204
orse+0.195
izza+0.192
Neg logit contributions
 day-0.132
 she-0.130
 She-0.128
 always-0.116
 like-0.115
Token to
Token ID284
Feature activation-6.90e-02

Pos logit contributions
 tal+0.265
eg+0.258
itched+0.252
izza+0.242
orse+0.238
Neg logit contributions
 she-0.151
 She-0.144
 day-0.137
 her-0.128
 always-0.122
Token stitch
Token ID24695
Feature activation-1.50e-01

Pos logit contributions
itched+0.155
 tal+0.149
eg+0.141
orse+0.133
izza+0.131
Neg logit contributions
 She-0.115
 she-0.112
 day-0.112
 like-0.101
 always-0.100
Token.
Token ID13
Feature activation-5.92e-02

Pos logit contributions
 tal+0.377
itched+0.373
eg+0.372
orse+0.354
izza+0.352
Neg logit contributions
 she-0.217
 She-0.201
 day-0.192
 her-0.187
 sometimes-0.183
Token She
Token ID1375
Feature activation+4.05e-01

Pos logit contributions
itched+0.167
 tal+0.158
eg+0.150
izza+0.148
rolled+0.145
Neg logit contributions
 day-0.057
 she-0.049
 especially-0.049
 weekend-0.047
 matter-0.047
Token st
Token ID336
Feature activation-1.21e-01

Pos logit contributions
 she+0.622
 day+0.603
 She+0.592
 always+0.579
 sometimes+0.565
Neg logit contributions
itched-0.959
 tal-0.943
eg-0.917
izza-0.866
urger-0.831
Tokenitched
Token ID10981
Feature activation-6.76e-01

Pos logit contributions
 tal+0.135
orse+0.129
 fin+0.118
urger+0.118
 cannon+0.116
Neg logit contributions
 She-0.325
 she-0.281
my-0.275
She-0.272
 her-0.261
Token and
Token ID290
Feature activation+7.11e-02

Pos logit contributions
itched+1.681
 tal+1.657
eg+1.616
orse+1.543
izza+1.511
Neg logit contributions
 She-0.968
 she-0.958
 day-0.931
 like-0.847
 sometimes-0.834
Token st
Token ID336
Feature activation-1.21e-01

Pos logit contributions
 she+0.123
 day+0.120
 She+0.117
 sometimes+0.110
 always+0.109
Neg logit contributions
itched-0.157
eg-0.152
 tal-0.152
izza-0.140
ades-0.137
Tokenitched
Token ID10981
Feature activation-6.77e-01

Pos logit contributions
orse+0.124
 tal+0.123
 fin+0.115
 gru+0.111
urger+0.110
Neg logit contributions
 She-0.333
 she-0.292
 like-0.284
She-0.280
 her-0.276
Token until
Token ID1566
Feature activation+3.78e-03

Pos logit contributions
itched+1.684
 tal+1.656
eg+1.607
orse+1.535
izza+1.502
Neg logit contributions
 She-0.969
 she-0.955
 day-0.927
 like-0.850
 sometimes-0.825
Token she
Token ID673
Feature activation+3.98e-01

Pos logit contributions
 She+0.005
 day+0.004
my+0.004
 especially+0.004
 like+0.004
Neg logit contributions
itched-0.010
 tal-0.009
eg-0.009
orse-0.009
ves-0.008
Token and
Token ID290
Feature activation+7.26e-02

Pos logit contributions
itched+0.210
 tal+0.202
eg+0.196
orse+0.186
izza+0.185
Neg logit contributions
 She-0.113
 she-0.112
 day-0.110
 like-0.098
 always-0.096
Token thread
Token ID4704
Feature activation-1.99e-02

Pos logit contributions
 she+0.122
 She+0.118
 day+0.116
 sometimes+0.104
 always+0.103
Neg logit contributions
itched-0.166
 tal-0.157
eg-0.154
orse-0.143
izza-0.142
Token and
Token ID290
Feature activation+7.30e-02

Pos logit contributions
itched+0.046
 tal+0.045
eg+0.044
orse+0.041
izza+0.041
Neg logit contributions
 she-0.031
 She-0.031
 day-0.030
 like-0.027
 always-0.027
Token carefully
Token ID7773
Feature activation-1.72e-01

Pos logit contributions
 She+0.122
 she+0.120
 day+0.120
 like+0.107
 always+0.107
Neg logit contributions
itched-0.162
 tal-0.155
eg-0.147
orse-0.138
izza-0.136
Token st
Token ID336
Feature activation-1.18e-01

Pos logit contributions
eg+0.361
 tal+0.353
itched+0.344
izza+0.327
orse+0.311
Neg logit contributions
 she-0.329
 She-0.301
 like-0.291
 day-0.289
 her-0.284
Tokenitched
Token ID10981
Feature activation-6.76e-01

Pos logit contributions
orse+0.121
eg+0.115
 tal+0.112
 cannon+0.111
urger+0.108
Neg logit contributions
 She-0.319
 she-0.293
 her-0.272
She-0.272
 like-0.263
Token it
Token ID340
Feature activation-7.62e-02

Pos logit contributions
itched+1.679
 tal+1.642
eg+1.618
orse+1.555
izza+1.519
Neg logit contributions
 She-0.966
 she-0.959
 day-0.911
 like-0.848
 sometimes-0.805
Token to
Token ID284
Feature activation-6.75e-02

Pos logit contributions
itched+0.165
 tal+0.160
eg+0.151
orse+0.143
izza+0.140
Neg logit contributions
 She-0.131
 she-0.129
 day-0.128
 like-0.116
 always-0.115
Token the
Token ID262
Feature activation-3.38e-02

Pos logit contributions
itched+0.161
 tal+0.154
eg+0.146
orse+0.139
izza+0.137
Neg logit contributions
 She-0.103
 she-0.101
 day-0.100
 like-0.089
 always-0.089
Token fabric
Token ID9664
Feature activation+5.52e-02

Pos logit contributions
itched+0.076
 tal+0.074
eg+0.067
 fin+0.066
 wounds+0.063
Neg logit contributions
 She-0.052
 she-0.050
 day-0.049
 especially-0.046
my-0.045
Token.
Token ID13
Feature activation-5.87e-02

Pos logit contributions
 She+0.097
 day+0.095
 she+0.094
 especially+0.086
 always+0.085
Neg logit contributions
itched-0.117
 tal-0.111
eg-0.102
orse-0.098
 fin-0.095
Token off
Token ID572
Feature activation-1.87e-01

Pos logit contributions
itched+0.016
 tal+0.016
eg+0.015
orse+0.015
 fin+0.014
Neg logit contributions
 she-0.011
 She-0.011
 day-0.011
 like-0.010
 her-0.009
Token some
Token ID617
Feature activation-1.20e-01

Pos logit contributions
itched+0.480
 tal+0.473
eg+0.457
orse+0.443
 fin+0.429
Neg logit contributions
 she-0.270
 She-0.264
 day-0.252
 her-0.228
 like-0.223
Token fabric
Token ID9664
Feature activation+5.84e-02

Pos logit contributions
itched+0.261
 tal+0.251
eg+0.242
orse+0.228
 fin+0.219
Neg logit contributions
 day-0.210
 she-0.209
 She-0.207
 like-0.189
 always-0.183
Token and
Token ID290
Feature activation+7.54e-02

Pos logit contributions
 she+0.073
 She+0.072
 day+0.070
 like+0.062
 sometimes+0.060
Neg logit contributions
itched-0.155
 tal-0.151
eg-0.144
orse-0.138
izza-0.136
Token st
Token ID336
Feature activation-1.18e-01

Pos logit contributions
 she+0.130
 She+0.126
 day+0.125
 always+0.113
 like+0.113
Neg logit contributions
itched-0.169
 tal-0.162
eg-0.156
orse-0.144
 fin-0.142
Tokenitched
Token ID10981
Feature activation-6.75e-01

Pos logit contributions
 tal+0.139
 fin+0.137
orse+0.131
 gru+0.131
 rifle+0.130
Neg logit contributions
 She-0.305
 she-0.274
She-0.251
 her-0.249
 like-0.248
Token it
Token ID340
Feature activation-7.40e-02

Pos logit contributions
eg+1.736
 tal+1.730
itched+1.702
orse+1.670
urger+1.589
Neg logit contributions
 she-0.950
 She-0.934
 day-0.879
 her-0.859
 like-0.844
Token around
Token ID1088
Feature activation+9.29e-02

Pos logit contributions
itched+0.167
 tal+0.164
eg+0.155
orse+0.149
izza+0.144
Neg logit contributions
 She-0.122
 she-0.120
 day-0.119
 like-0.108
 always-0.106
Token the
Token ID262
Feature activation-3.27e-02

Pos logit contributions
 She+0.141
 day+0.138
 she+0.138
 like+0.122
 always+0.121
Neg logit contributions
itched-0.223
 tal-0.214
eg-0.203
orse-0.193
izza-0.189
Token waist
Token ID16139
Feature activation-1.42e-01

Pos logit contributions
itched+0.066
 tal+0.065
eg+0.061
 fin+0.056
orse+0.055
Neg logit contributions
 She-0.058
 she-0.056
 day-0.054
 sometimes-0.052
 especially-0.051
Token to
Token ID284
Feature activation-6.68e-02

Pos logit contributions
itched+0.297
 tal+0.279
eg+0.263
orse+0.249
izza+0.242
Neg logit contributions
 She-0.252
 day-0.247
 she-0.244
 sometimes-0.222
 always-0.221
Token needle
Token ID17598
Feature activation-8.12e-02

Pos logit contributions
itched+0.173
 tal+0.161
eg+0.156
orse+0.150
izza+0.149
Neg logit contributions
 day-0.141
 she-0.139
 She-0.137
 girl-0.128
my-0.126
Token and
Token ID290
Feature activation+8.04e-02

Pos logit contributions
itched+0.201
 tal+0.192
eg+0.179
orse+0.169
 fin+0.169
Neg logit contributions
 She-0.115
 day-0.114
 she-0.110
 weekend-0.101
 especially-0.099
Token thread
Token ID4704
Feature activation-1.44e-02

Pos logit contributions
 she+0.149
 She+0.135
 day+0.131
 sometimes+0.125
 her+0.124
Neg logit contributions
itched-0.182
eg-0.174
 tal-0.169
izza-0.159
ades-0.158
Token and
Token ID290
Feature activation+8.00e-02

Pos logit contributions
itched+0.033
 tal+0.033
eg+0.032
orse+0.030
izza+0.030
Neg logit contributions
 she-0.022
 She-0.022
 day-0.021
 like-0.019
 sometimes-0.019
Token st
Token ID336
Feature activation-1.15e-01

Pos logit contributions
 she+0.139
 She+0.137
 day+0.134
 sometimes+0.123
 always+0.122
Neg logit contributions
itched-0.177
 tal-0.169
eg-0.162
orse-0.150
izza-0.149
Tokenitched
Token ID10981
Feature activation-6.74e-01

Pos logit contributions
orse+0.128
 crew+0.127
 tal+0.121
 cannon+0.118
 fin+0.114
Neg logit contributions
 She-0.289
 she-0.253
She-0.246
 her-0.239
my-0.236
Token up
Token ID510
Feature activation-3.51e-02

Pos logit contributions
itched+1.840
 tal+1.820
eg+1.794
orse+1.748
izza+1.705
Neg logit contributions
 She-0.825
 she-0.810
 day-0.734
 like-0.700
 her-0.680
Token her
Token ID607
Feature activation+3.20e-01

Pos logit contributions
itched+0.088
 tal+0.085
eg+0.082
orse+0.079
izza+0.078
Neg logit contributions
 She-0.051
 she-0.050
 day-0.048
 like-0.044
 sometimes-0.043
Token knee
Token ID10329
Feature activation-2.54e-01

Pos logit contributions
 day+0.622
 she+0.594
 She+0.567
 like+0.533
 always+0.521
Neg logit contributions
itched-0.645
 tal-0.612
eg-0.591
izza-0.576
orse-0.557
Token.
Token ID13
Feature activation-4.98e-02

Pos logit contributions
itched+0.586
 tal+0.577
eg+0.550
orse+0.527
izza+0.525
Neg logit contributions
 She-0.409
 she-0.409
 day-0.398
 like-0.369
 always-0.360
Token Lily
Token ID20037
Feature activation+1.66e-01

Pos logit contributions
itched+0.140
 tal+0.136
eg+0.129
orse+0.124
 fin+0.121
Neg logit contributions
 She-0.058
 she-0.055
 day-0.053
 always-0.045
 like-0.045
Token,
Token ID11
Feature activation-4.26e-02

Pos logit contributions
itched+0.391
 tal+0.380
eg+0.352
 fin+0.336
orse+0.333
Neg logit contributions
 She-0.220
 day-0.214
 she-0.212
 weekend-0.198
 always-0.194
Token and
Token ID290
Feature activation+7.96e-02

Pos logit contributions
itched+0.112
 tal+0.108
eg+0.102
orse+0.099
 fin+0.096
Neg logit contributions
 She-0.053
 day-0.052
 she-0.051
 sometimes-0.044
 weekend-0.044
Token his
Token ID465
Feature activation-1.21e-01

Pos logit contributions
 she+0.126
 She+0.112
 day+0.110
 like+0.107
 always+0.104
Neg logit contributions
itched-0.204
eg-0.193
 tal-0.193
ades-0.180
izza-0.175
Token nose
Token ID9686
Feature activation-3.05e-01

Pos logit contributions
itched+0.206
cks+0.190
ades+0.186
ves+0.183
ues+0.180
Neg logit contributions
 day-0.279
 She-0.240
 she-0.238
 night-0.237
 morning-0.237
Token tw
Token ID665
Feature activation+1.34e-02

Pos logit contributions
 tal+0.727
itched+0.714
eg+0.699
izza+0.662
orse+0.652
Neg logit contributions
 she-0.463
 She-0.456
 day-0.424
 like-0.411
 always-0.405
Tokenitched
Token ID10981
Feature activation-6.74e-01

Pos logit contributions
 She+0.036
 she+0.035
 always+0.034
 especially+0.034
 like+0.034
Neg logit contributions
 crew-0.011
 cannon-0.010
 tal-0.010
izza-0.010
eg-0.009
Token.
Token ID13
Feature activation-4.73e-02

Pos logit contributions
eg+1.654
 tal+1.627
itched+1.617
orse+1.590
izza+1.562
Neg logit contributions
 like-0.982
 She-0.962
 she-0.920
 day-0.916
 her-0.875
Token He
Token ID679
Feature activation+4.45e-02

Pos logit contributions
itched+0.132
 tal+0.129
ades+0.124
eg+0.122
 wounds+0.121
Neg logit contributions
 She-0.071
 she-0.056
 day-0.051
 always-0.044
 morning-0.043
Token had
Token ID550
Feature activation+9.75e-02

Pos logit contributions
 she+0.066
 She+0.062
 always+0.062
 day+0.061
 especially+0.060
Neg logit contributions
itched-0.111
 tal-0.108
eg-0.104
izza-0.098
ades-0.097
Token never
Token ID1239
Feature activation+5.50e-02

Pos logit contributions
 She+0.146
 she+0.146
 day+0.143
 always+0.137
 like+0.136
Neg logit contributions
itched-0.240
eg-0.223
 tal-0.222
orse-0.207
izza-0.205
Token tasted
Token ID29187
Feature activation-2.31e-02

Pos logit contributions
 She+0.098
 she+0.094
 day+0.094
 sometimes+0.084
 always+0.084
Neg logit contributions
itched-0.115
 tal-0.112
eg-0.102
orse-0.099
izza-0.095
Tokenicked
Token ID9484
Feature activation-4.86e-01

Pos logit contributions
itched+0.044
 tal+0.043
eg+0.041
izza+0.034
orse+0.033
Neg logit contributions
 She-0.136
 she-0.132
 day-0.127
 like-0.125
 always-0.123
Token his
Token ID465
Feature activation-1.20e-01

Pos logit contributions
itched+1.262
 tal+1.200
eg+1.150
orse+1.082
 fin+1.074
Neg logit contributions
 day-0.615
 She-0.598
 she-0.582
 weekend-0.531
 always-0.521
Token lips
Token ID11914
Feature activation-4.40e-01

Pos logit contributions
itched+0.204
izza+0.184
uers+0.181
plug+0.180
eg+0.180
Neg logit contributions
 day-0.246
 She-0.243
 she-0.240
 girl-0.238
 wind-0.236
Token and
Token ID290
Feature activation+7.77e-02

Pos logit contributions
itched+1.054
 tal+0.979
eg+0.932
orse+0.895
 fin+0.879
Neg logit contributions
 day-0.633
 She-0.632
 she-0.614
 weekend-0.574
 week-0.554
Token tw
Token ID665
Feature activation+1.23e-02

Pos logit contributions
 she+0.147
 She+0.136
 day+0.130
 like+0.128
 always+0.126
Neg logit contributions
itched-0.169
eg-0.166
 tal-0.161
izza-0.155
ades-0.152
Tokenitched
Token ID10981
Feature activation-6.73e-01

Pos logit contributions
 She+0.029
 she+0.029
 always+0.028
 day+0.028
 her+0.028
Neg logit contributions
izza-0.014
eg-0.014
 tal-0.014
 cannon-0.013
 rods-0.012
Token his
Token ID465
Feature activation-1.21e-01

Pos logit contributions
 tal+1.588
itched+1.571
eg+1.556
izza+1.493
orse+1.486
Neg logit contributions
 She-1.065
 she-1.032
 like-0.974
 her-0.972
 day-0.955
Token tail
Token ID7894
Feature activation-2.48e-01

Pos logit contributions
itched+0.214
izza+0.202
ades+0.196
eg+0.196
 tal+0.195
Neg logit contributions
 day-0.246
 She-0.239
 she-0.234
 like-0.228
 wind-0.225
Token.
Token ID13
Feature activation-5.03e-02

Pos logit contributions
itched+0.574
 tal+0.564
eg+0.540
orse+0.508
izza+0.505
Neg logit contributions
 She-0.392
 she-0.386
 day-0.377
 like-0.355
 sometimes-0.342
Token He
Token ID679
Feature activation+4.37e-02

Pos logit contributions
itched+0.129
 tal+0.126
eg+0.118
orse+0.113
izza+0.110
Neg logit contributions
 She-0.074
 she-0.069
 day-0.066
 like-0.059
 always-0.058
Token wanted
Token ID2227
Feature activation+1.26e-01

Pos logit contributions
 she+0.069
 She+0.066
 day+0.064
 always+0.063
 especially+0.062
Neg logit contributions
itched-0.106
 tal-0.103
eg-0.098
izza-0.094
ades-0.089
Token them
Token ID606
Feature activation-4.41e-02

Pos logit contributions
 She+0.047
 day+0.047
 she+0.046
 always+0.042
 especially+0.042
Neg logit contributions
itched-0.071
 tal-0.068
eg-0.063
orse-0.060
 fin-0.059
Token.
Token ID13
Feature activation-4.77e-02

Pos logit contributions
itched+0.106
 tal+0.105
eg+0.099
orse+0.093
izza+0.092
Neg logit contributions
 She-0.069
 she-0.067
 day-0.065
 like-0.060
 sometimes-0.059
Token Then
Token ID3244
Feature activation-1.70e-01

Pos logit contributions
itched+0.117
 tal+0.112
eg+0.107
orse+0.102
ves+0.101
Neg logit contributions
 She-0.079
 she-0.071
 day-0.066
 like-0.062
 sometimes-0.060
Token it
Token ID340
Feature activation-7.50e-02

Pos logit contributions
itched+0.412
 tal+0.397
eg+0.375
orse+0.358
izza+0.351
Neg logit contributions
 She-0.245
 day-0.240
 she-0.237
 like-0.210
 always-0.210
Token tw
Token ID665
Feature activation+1.15e-02

Pos logit contributions
itched+0.178
 tal+0.173
eg+0.172
izza+0.165
ades+0.155
Neg logit contributions
 she-0.125
 day-0.116
 She-0.115
 always-0.111
 sometimes-0.107
Tokenitched
Token ID10981
Feature activation-6.73e-01

Pos logit contributions
 She+0.026
 she+0.025
 day+0.024
 always+0.024
 her+0.024
Neg logit contributions
izza-0.015
eg-0.015
 tal-0.014
 cannon-0.014
urger-0.014
Token its
Token ID663
Feature activation-2.00e-01

Pos logit contributions
itched+1.511
 tal+1.476
eg+1.434
orse+1.378
izza+1.348
Neg logit contributions
 She-1.132
 she-1.096
 day-1.080
 like-1.027
 sometimes-0.978
Token nose
Token ID9686
Feature activation-3.08e-01

Pos logit contributions
itched+0.441
eg+0.409
izza+0.400
ades+0.399
 tal+0.394
Neg logit contributions
 day-0.348
 She-0.333
 she-0.319
 like-0.312
 always-0.309
Token and
Token ID290
Feature activation+7.82e-02

Pos logit contributions
itched+0.725
 tal+0.708
eg+0.673
orse+0.636
izza+0.628
Neg logit contributions
 She-0.472
 she-0.464
 day-0.456
 like-0.415
 sometimes-0.406
Token it
Token ID340
Feature activation-7.57e-02

Pos logit contributions
 she+0.142
 She+0.134
 day+0.133
 always+0.120
 like+0.120
Neg logit contributions
itched-0.173
 tal-0.162
eg-0.160
izza-0.151
ades-0.147
Token seemed
Token ID3947
Feature activation-5.25e-02

Pos logit contributions
itched+0.180
 tal+0.175
eg+0.171
izza+0.164
orse+0.155
Neg logit contributions
 she-0.122
 day-0.115
 She-0.114
 always-0.108
 sometimes-0.106
Token hungry
Token ID14720
Feature activation-1.86e-02

Pos logit contributions
itched+0.150
 tal+0.144
 fin+0.131
orse+0.125
 fins+0.123
Neg logit contributions
 She-0.109
 day-0.108
 weekend-0.106
 she-0.103
You-0.098
Token.
Token ID13
Feature activation-5.08e-02

Pos logit contributions
 tal+0.030
itched+0.030
 fin+0.027
orse+0.025
eg+0.025
Neg logit contributions
 She-0.036
 day-0.035
 weekend-0.034
 she-0.033
my-0.033
Token His
Token ID2399
Feature activation-2.79e-01

Pos logit contributions
itched+0.135
 tal+0.129
eg+0.123
orse+0.119
ades+0.116
Neg logit contributions
 She-0.070
 she-0.064
 day-0.062
 like-0.055
 always-0.055
Token nose
Token ID9686
Feature activation-3.06e-01

Pos logit contributions
itched+0.551
 tal+0.518
eg+0.496
ades+0.475
orse+0.475
Neg logit contributions
 day-0.572
 she-0.527
 She-0.527
 always-0.495
 morning-0.483
Token tw
Token ID665
Feature activation+1.34e-02

Pos logit contributions
itched+0.697
 tal+0.674
eg+0.640
orse+0.602
izza+0.595
Neg logit contributions
 She-0.492
 she-0.485
 day-0.478
 always-0.430
 like-0.429
Tokenitched
Token ID10981
Feature activation-6.73e-01

Pos logit contributions
 She+0.036
 she+0.034
 day+0.033
 especially+0.033
 always+0.033
Neg logit contributions
eg-0.013
 tal-0.013
izza-0.012
 cannon-0.012
itched-0.011
Token as
Token ID355
Feature activation+1.49e-03

Pos logit contributions
itched+1.660
 tal+1.608
eg+1.543
orse+1.473
izza+1.442
Neg logit contributions
 She-0.957
 day-0.933
 she-0.931
 like-0.840
 always-0.821
Token he
Token ID339
Feature activation+3.36e-02

Pos logit contributions
 She+0.002
 day+0.002
 she+0.002
my+0.002
 weekend+0.002
Neg logit contributions
itched-0.003
 tal-0.003
eg-0.003
orse-0.003
ves-0.003
Token smelled
Token ID37609
Feature activation-1.17e-02

Pos logit contributions
 she+0.051
 She+0.048
 day+0.047
 always+0.046
 especially+0.045
Neg logit contributions
itched-0.081
 tal-0.078
eg-0.078
izza-0.073
ades-0.071
Token something
Token ID1223
Feature activation-1.63e-01

Pos logit contributions
itched+0.028
 tal+0.027
eg+0.025
orse+0.024
izza+0.024
Neg logit contributions
 She-0.018
 day-0.017
 she-0.017
 always-0.015
 sometimes-0.015
Token in
Token ID287
Feature activation+4.51e-02

Pos logit contributions
itched+0.362
 tal+0.347
eg+0.322
orse+0.307
 fin+0.301
Neg logit contributions
 She-0.267
 day-0.260
 she-0.255
 sometimes-0.232
 weekend-0.232
Token loud
Token ID7812
Feature activation-9.39e-02

Pos logit contributions
itched+0.205
 tal+0.195
uffed+0.181
izza+0.178
rolled+0.178
Neg logit contributions
 day-0.114
 girl-0.102
 She-0.099
 she-0.098
 gloomy-0.095
Token,
Token ID11
Feature activation-4.16e-02

Pos logit contributions
itched+0.225
 tal+0.224
eg+0.215
izza+0.208
rolled+0.201
Neg logit contributions
 She-0.135
 day-0.133
 she-0.130
 like-0.121
 always-0.114
Token high
Token ID1029
Feature activation+5.54e-03

Pos logit contributions
itched+0.101
 tal+0.096
eg+0.092
orse+0.086
izza+0.086
Neg logit contributions
 She-0.062
 she-0.061
 day-0.061
 like-0.055
 always-0.053
Token-
Token ID12
Feature activation-1.81e-01

Pos logit contributions
 day+0.010
 like+0.008
 She+0.008
 she+0.008
 sometimes+0.008
Neg logit contributions
itched-0.012
 tal-0.012
izza-0.011
eg-0.011
orse-0.011
Tokenp
Token ID79
Feature activation-1.34e-01

Pos logit contributions
itched+0.372
 tal+0.358
eg+0.330
orse+0.308
izza+0.305
Neg logit contributions
 She-0.336
 day-0.332
 she-0.332
 like-0.303
 sometimes-0.298
Tokenitched
Token ID10981
Feature activation-6.72e-01

Pos logit contributions
 tal+0.319
eg+0.299
plug+0.292
izza+0.292
itched+0.279
Neg logit contributions
 she-0.197
 like-0.196
 She-0.195
 day-0.184
 always-0.175
Token noise
Token ID7838
Feature activation-6.52e-03

Pos logit contributions
 tal+1.470
eg+1.439
itched+1.412
izza+1.400
orse+1.341
Neg logit contributions
 She-1.110
 like-1.077
 day-1.075
 she-1.044
 her-0.992
Token back
Token ID736
Feature activation-7.61e-02

Pos logit contributions
itched+0.016
 tal+0.016
eg+0.015
izza+0.014
orse+0.014
Neg logit contributions
 She-0.010
 she-0.010
 day-0.009
 like-0.009
 sometimes-0.009
Token.
Token ID13
Feature activation-4.94e-02

Pos logit contributions
itched+0.187
 tal+0.185
eg+0.178
orse+0.170
izza+0.169
Neg logit contributions
 She-0.112
 she-0.111
 day-0.108
 like-0.101
 sometimes-0.097
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
itched+0.133
 tal+0.131
eg+0.123
urger+0.121
rolled+0.116
Neg logit contributions
 She-0.080
 she-0.069
 like-0.060
 day-0.057
 sometimes-0.056
Token
Token ID198
Feature activation-1.29e-01

Pos logit contributions
 tal+0.377
itched+0.369
urger+0.368
eg+0.351
 rifle+0.345
Neg logit contributions
 She-0.172
 she-0.145
 day-0.127
She-0.125
 sometimes-0.114
Token forest
Token ID8222
Feature activation+1.63e-01

Pos logit contributions
 tal+0.055
itched+0.053
 fin+0.048
eg+0.048
 fins+0.045
Neg logit contributions
 she-0.032
 like-0.030
 She-0.030
 especially-0.029
 sometimes-0.029
Token.
Token ID13
Feature activation-4.63e-02

Pos logit contributions
 she+0.261
 She+0.261
 day+0.259
 like+0.231
 always+0.228
Neg logit contributions
itched-0.382
 tal-0.378
eg-0.366
izza-0.340
orse-0.328
Token The
Token ID383
Feature activation-1.46e-01

Pos logit contributions
itched+0.109
 tal+0.105
eg+0.098
orse+0.095
izza+0.093
Neg logit contributions
 day-0.065
 she-0.063
 sometimes-0.059
 She-0.059
 especially-0.058
Token bunny
Token ID44915
Feature activation+4.77e-02

Pos logit contributions
 fin+0.246
itched+0.242
 tal+0.240
eg+0.225
 fins+0.223
Neg logit contributions
 She-0.270
 she-0.265
 like-0.231
 weekend-0.229
reating-0.229
Token tw
Token ID665
Feature activation+1.84e-02

Pos logit contributions
 She+0.069
 she+0.066
 day+0.066
 like+0.059
 weekend+0.058
Neg logit contributions
itched-0.113
 tal-0.109
eg-0.102
orse-0.100
 fin-0.096
Tokenitched
Token ID10981
Feature activation-6.70e-01

Pos logit contributions
 She+0.049
 day+0.048
 she+0.048
 always+0.045
 especially+0.045
Neg logit contributions
itched-0.020
 tal-0.020
eg-0.019
izza-0.017
 cannon-0.016
Token his
Token ID465
Feature activation-1.15e-01

Pos logit contributions
itched+1.431
 tal+1.384
eg+1.377
izza+1.313
orse+1.293
Neg logit contributions
 She-1.183
 day-1.167
 she-1.151
 like-1.072
 always-1.057
Token nose
Token ID9686
Feature activation-3.02e-01

Pos logit contributions
itched+0.227
 tal+0.207
eg+0.201
izza+0.198
orse+0.191
Neg logit contributions
 day-0.232
 She-0.218
 she-0.216
 always-0.205
 like-0.203
Token,
Token ID11
Feature activation-4.02e-02

Pos logit contributions
itched+0.758
 tal+0.737
eg+0.701
orse+0.665
izza+0.659
Neg logit contributions
 She-0.418
 she-0.409
 day-0.406
 like-0.358
 always-0.357
Token making
Token ID1642
Feature activation-1.46e-02

Pos logit contributions
itched+0.083
 tal+0.080
 fin+0.073
orse+0.072
 fins+0.069
Neg logit contributions
 She-0.068
 day-0.064
 she-0.062
 weekend-0.061
 week-0.059
Token tiny
Token ID7009
Feature activation-1.78e-01

Pos logit contributions
itched+0.034
eg+0.033
 tal+0.033
izza+0.031
orse+0.030
Neg logit contributions
 she-0.022
 day-0.022
 She-0.022
 like-0.020
 always-0.020
Token big
Token ID1263
Feature activation-3.15e-02

Pos logit contributions
itched+0.099
eg+0.097
 tal+0.094
izza+0.092
orse+0.091
Neg logit contributions
 She-0.088
 she-0.086
 like-0.080
 day-0.079
 her-0.076
Token eyes
Token ID2951
Feature activation-3.25e-01

Pos logit contributions
itched+0.042
plug+0.042
izza+0.042
ades+0.042
eg+0.041
Neg logit contributions
 She-0.077
 she-0.072
 day-0.071
 like-0.071
 her-0.068
Token.
Token ID13
Feature activation-4.35e-02

Pos logit contributions
 tal+0.754
itched+0.748
eg+0.714
izza+0.666
orse+0.664
Neg logit contributions
 She-0.525
 she-0.518
 day-0.488
 like-0.470
 sometimes-0.457
Token It
Token ID632
Feature activation-4.52e-02

Pos logit contributions
itched+0.105
 tal+0.102
eg+0.096
orse+0.092
izza+0.090
Neg logit contributions
 She-0.066
 she-0.064
 day-0.062
 like-0.056
 sometimes-0.055
Token tw
Token ID665
Feature activation+1.89e-02

Pos logit contributions
itched+0.110
 tal+0.107
eg+0.103
izza+0.100
ades+0.095
Neg logit contributions
 she-0.068
 She-0.068
 day-0.065
 like-0.062
 sometimes-0.061
Tokenitched
Token ID10981
Feature activation-6.69e-01

Pos logit contributions
 She+0.049
 she+0.048
 like+0.046
 especially+0.045
 always+0.045
Neg logit contributions
izza-0.019
 tal-0.019
eg-0.018
 cannon-0.016
 crew-0.016
Token its
Token ID663
Feature activation-1.95e-01

Pos logit contributions
itched+1.433
 tal+1.385
eg+1.312
orse+1.238
izza+1.214
Neg logit contributions
 She-1.183
 she-1.155
 day-1.141
 like-1.049
 sometimes-1.035
Token nose
Token ID9686
Feature activation-2.99e-01

Pos logit contributions
itched+0.340
eg+0.312
izza+0.310
 tal+0.307
ades+0.305
Neg logit contributions
 She-0.410
 day-0.406
 like-0.390
 she-0.390
 always-0.377
Token.
Token ID13
Feature activation-4.42e-02

Pos logit contributions
itched+0.694
 tal+0.671
eg+0.634
orse+0.601
izza+0.592
Neg logit contributions
 She-0.467
 she-0.457
 day-0.454
 like-0.408
 sometimes-0.403
Token Lily
Token ID20037
Feature activation+1.69e-01

Pos logit contributions
itched+0.109
 tal+0.106
eg+0.101
orse+0.095
izza+0.093
Neg logit contributions
 She-0.067
 she-0.064
 day-0.061
 like-0.056
 sometimes-0.054
Token smiled
Token ID13541
Feature activation-2.27e-01

Pos logit contributions
 she+0.269
 She+0.265
 always+0.245
 like+0.245
 sometimes+0.239
Neg logit contributions
 tal-0.404
itched-0.394
eg-0.389
izza-0.381
ades-0.361
Token of
Token ID286
Feature activation+1.50e-01

Pos logit contributions
itched+0.099
 tal+0.088
eg+0.085
ves+0.082
ades+0.081
Neg logit contributions
 day-0.056
 She-0.056
 weekend-0.052
 she-0.052
 week-0.049
Token red
Token ID2266
Feature activation+5.65e-02

Pos logit contributions
 She+0.245
 day+0.239
 she+0.238
 always+0.212
 like+0.212
Neg logit contributions
itched-0.341
 tal-0.327
eg-0.306
orse-0.289
izza-0.284
Token cloth
Token ID16270
Feature activation-5.88e-02

Pos logit contributions
 She+0.099
 day+0.098
 she+0.097
 weekend+0.094
 especially+0.093
Neg logit contributions
itched-0.119
 tal-0.110
eg-0.100
 fin-0.093
 cannon-0.091
Token and
Token ID290
Feature activation+8.83e-02

Pos logit contributions
itched+0.134
 tal+0.122
eg+0.117
 fin+0.108
ves+0.107
Neg logit contributions
 She-0.092
 day-0.091
 she-0.087
 weekend-0.083
 especially-0.082
Token st
Token ID336
Feature activation-1.11e-01

Pos logit contributions
 She+0.152
 day+0.149
 she+0.148
 like+0.134
 always+0.133
Neg logit contributions
itched-0.192
 tal-0.184
eg-0.173
orse-0.163
izza-0.160
Tokenitched
Token ID10981
Feature activation-6.68e-01

Pos logit contributions
 tal+0.138
orse+0.132
 fin+0.122
 gru+0.118
 crew+0.116
Neg logit contributions
 She-0.300
 she-0.264
She-0.249
 like-0.248
 her-0.244
Token her
Token ID607
Feature activation+3.27e-01

Pos logit contributions
itched+1.628
 tal+1.621
eg+1.561
orse+1.518
izza+1.465
Neg logit contributions
 She-0.999
 she-0.978
 day-0.937
 like-0.893
 sometimes-0.853
Token name
Token ID1438
Feature activation-1.91e-01

Pos logit contributions
 day+0.663
 She+0.639
 she+0.637
 like+0.581
 always+0.577
Neg logit contributions
itched-0.608
 tal-0.577
eg-0.561
orse-0.553
izza-0.542
Token on
Token ID319
Feature activation-1.86e-02

Pos logit contributions
itched+0.403
 tal+0.379
eg+0.359
orse+0.334
izza+0.332
Neg logit contributions
 She-0.333
 day-0.329
 she-0.326
 especially-0.296
 always-0.295
Token it
Token ID340
Feature activation-6.87e-02

Pos logit contributions
itched+0.046
 tal+0.045
eg+0.042
orse+0.040
izza+0.040
Neg logit contributions
 She-0.027
 she-0.027
 day-0.026
 like-0.023
 sometimes-0.023
Token.
Token ID13
Feature activation-4.00e-02

Pos logit contributions
itched+0.146
 tal+0.138
eg+0.130
orse+0.122
izza+0.120
Neg logit contributions
 She-0.120
 day-0.118
 she-0.118
 always-0.107
 like-0.106
Token to
Token ID284
Feature activation-5.88e-02

Pos logit contributions
itched+0.009
 tal+0.008
eg+0.008
orse+0.008
izza+0.008
Neg logit contributions
 she-0.005
 She-0.005
 day-0.005
 like-0.004
 sometimes-0.004
Token work
Token ID670
Feature activation+1.59e-02

Pos logit contributions
itched+0.151
eg+0.146
 tal+0.141
ades+0.138
izza+0.138
Neg logit contributions
 she-0.082
 She-0.079
 day-0.079
 her-0.072
 always-0.072
Token and
Token ID290
Feature activation+8.12e-02

Pos logit contributions
 She+0.023
 day+0.022
 she+0.022
 like+0.019
 always+0.019
Neg logit contributions
itched-0.039
 tal-0.038
eg-0.036
orse-0.034
izza-0.033
Token carefully
Token ID7773
Feature activation-1.63e-01

Pos logit contributions
 she+0.132
 day+0.126
 She+0.122
 always+0.115
 sometimes+0.114
Neg logit contributions
itched-0.197
 tal-0.186
eg-0.185
ades-0.170
izza-0.169
Token st
Token ID336
Feature activation-1.12e-01

Pos logit contributions
eg+0.354
 tal+0.349
itched+0.348
izza+0.326
ades+0.317
Neg logit contributions
 she-0.300
 She-0.275
 day-0.269
 like-0.263
 always-0.259
Tokenitched
Token ID10981
Feature activation-6.67e-01

Pos logit contributions
orse+0.128
urger+0.125
 cannon+0.122
 tal+0.119
izza+0.118
Neg logit contributions
 She-0.283
 she-0.259
She-0.238
 her-0.237
 always-0.226
Token the
Token ID262
Feature activation-2.51e-02

Pos logit contributions
eg+1.665
itched+1.646
orse+1.610
 tal+1.592
izza+1.553
Neg logit contributions
 She-0.957
 she-0.948
 day-0.907
 her-0.888
 like-0.888
Token coat
Token ID13209
Feature activation-1.29e-01

Pos logit contributions
itched+0.055
 tal+0.053
eg+0.050
orse+0.047
izza+0.046
Neg logit contributions
 She-0.043
 day-0.042
 she-0.042
 like-0.038
 always-0.038
Token.
Token ID13
Feature activation-4.97e-02

Pos logit contributions
itched+0.293
 tal+0.283
eg+0.267
orse+0.253
izza+0.248
Neg logit contributions
 She-0.210
 she-0.206
 day-0.205
 like-0.184
 always-0.183
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
itched+0.118
 tal+0.113
eg+0.109
urger+0.104
 fin+0.103
Neg logit contributions
 She-0.090
 she-0.080
 day-0.076
 always-0.068
 like-0.066
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
 tal+0.320
itched+0.319
urger+0.310
eg+0.305
 jaws+0.301
Neg logit contributions
 She-0.187
 she-0.166
 day-0.165
She-0.147
 always-0.145
Token was
Token ID373
Feature activation-1.90e-02

Pos logit contributions
itched+0.109
eg+0.106
 tal+0.105
izza+0.104
 rods+0.099
Neg logit contributions
 she-0.055
 She-0.053
 day-0.051
 always-0.050
 sometimes-0.047
Token a
Token ID257
Feature activation-7.49e-02

Pos logit contributions
itched+0.047
eg+0.046
 tal+0.046
izza+0.044
ves+0.043
Neg logit contributions
 she-0.027
 day-0.027
 She-0.027
 like-0.026
 always-0.026
Token high
Token ID1029
Feature activation+9.86e-03

Pos logit contributions
itched+0.186
 tal+0.175
eg+0.165
cks+0.160
ves+0.159
Neg logit contributions
 day-0.116
 she-0.109
 She-0.106
 always-0.098
 girl-0.097
Token-
Token ID12
Feature activation-1.75e-01

Pos logit contributions
 day+0.018
 She+0.018
 she+0.018
 like+0.016
 sometimes+0.016
Neg logit contributions
itched-0.020
 tal-0.019
eg-0.018
orse-0.017
izza-0.017
Tokenp
Token ID79
Feature activation-1.30e-01

Pos logit contributions
itched+0.384
 tal+0.366
eg+0.346
orse+0.331
izza+0.322
Neg logit contributions
 She-0.292
 day-0.283
 she-0.282
 always-0.257
 especially-0.256
Tokenitched
Token ID10981
Feature activation-6.67e-01

Pos logit contributions
 tal+0.254
itched+0.241
eg+0.240
izza+0.229
 rods+0.219
Neg logit contributions
 she-0.244
 day-0.241
 She-0.237
 like-0.226
 always-0.224
Token,
Token ID11
Feature activation-3.80e-02

Pos logit contributions
itched+1.586
 tal+1.542
eg+1.483
orse+1.410
izza+1.400
Neg logit contributions
 day-1.007
 She-0.992
 she-0.961
 like-0.895
 always-0.883
Token sque
Token ID35776
Feature activation-2.17e-01

Pos logit contributions
itched+0.091
 tal+0.087
eg+0.082
orse+0.079
 fin+0.077
Neg logit contributions
 She-0.057
 day-0.055
 she-0.055
 sometimes-0.048
 always-0.048
Tokenaky
Token ID15492
Feature activation+1.61e-02

Pos logit contributions
itched+0.390
 tal+0.359
eg+0.318
ades+0.309
 fin+0.307
Neg logit contributions
 she-0.481
 day-0.465
 She-0.463
 weekend-0.427
 sometimes-0.423
Token noise
Token ID7838
Feature activation-3.09e-03

Pos logit contributions
 day+0.028
 She+0.027
 she+0.027
 like+0.025
 always+0.024
Neg logit contributions
itched-0.035
 tal-0.033
eg-0.032
izza-0.030
 rods-0.030
Token.
Token ID13
Feature activation-4.70e-02

Pos logit contributions
itched+0.007
 tal+0.007
eg+0.007
orse+0.006
izza+0.006
Neg logit contributions
 She-0.005
 she-0.005
 day-0.005
 like-0.004
 always-0.004
Token loud
Token ID7812
Feature activation-8.94e-02

Pos logit contributions
 she+0.029
 day+0.028
 her+0.028
 She+0.026
 like+0.025
Neg logit contributions
itched-0.055
 tal-0.055
eg-0.053
izza-0.050
orse-0.050
Token,
Token ID11
Feature activation-3.77e-02

Pos logit contributions
itched+0.172
 tal+0.168
eg+0.162
izza+0.147
orse+0.146
Neg logit contributions
 She-0.178
 she-0.174
 day-0.173
 like-0.170
 sometimes-0.164
Token high
Token ID1029
Feature activation+8.88e-03

Pos logit contributions
itched+0.097
 tal+0.094
eg+0.089
orse+0.085
izza+0.084
Neg logit contributions
 She-0.049
 day-0.048
 she-0.047
 always-0.041
 sometimes-0.041
Token-
Token ID12
Feature activation-1.77e-01

Pos logit contributions
 day+0.014
 She+0.013
 she+0.013
 like+0.012
 sometimes+0.012
Neg logit contributions
itched-0.021
 tal-0.021
eg-0.020
orse-0.019
izza-0.019
Tokenp
Token ID79
Feature activation-1.30e-01

Pos logit contributions
itched+0.348
 tal+0.335
eg+0.306
orse+0.282
izza+0.281
Neg logit contributions
 She-0.347
 she-0.343
 day-0.343
 like-0.316
 sometimes-0.311
Tokenitched
Token ID10981
Feature activation-6.67e-01

Pos logit contributions
 tal+0.313
eg+0.301
plug+0.286
izza+0.284
itched+0.281
Neg logit contributions
 she-0.189
 She-0.188
 like-0.185
 day-0.172
 always-0.162
Token noises
Token ID26782
Feature activation-2.15e-01

Pos logit contributions
 tal+1.536
eg+1.507
itched+1.483
orse+1.439
izza+1.428
Neg logit contributions
 She-1.067
 like-1.031
 she-1.024
 day-0.997
 sometimes-0.944
Token.
Token ID13
Feature activation-4.62e-02

Pos logit contributions
itched+0.506
 tal+0.496
eg+0.468
orse+0.438
izza+0.437
Neg logit contributions
 She-0.331
 she-0.328
 day-0.324
 like-0.301
 sometimes-0.291
Token They
Token ID1119
Feature activation+6.98e-02

Pos logit contributions
 tal+0.130
itched+0.129
eg+0.122
urger+0.118
ves+0.114
Neg logit contributions
 She-0.066
 she-0.054
 day-0.049
 like-0.047
 sometimes-0.045
Token sounded
Token ID14846
Feature activation+2.58e-02

Pos logit contributions
 she+0.099
 She+0.097
 day+0.096
 always+0.094
 like+0.094
Neg logit contributions
itched-0.176
 tal-0.170
eg-0.160
izza-0.154
orse-0.148
Token like
Token ID588
Feature activation+3.63e-01

Pos logit contributions
 She+0.009
 day+0.008
 she+0.008
 like+0.005
 always+0.004
Neg logit contributions
itched-0.092
 tal-0.090
eg-0.087
orse-0.084
izza-0.083
Token She
Token ID1375
Feature activation+4.18e-01

Pos logit contributions
itched+0.139
 tal+0.134
eg+0.129
izza+0.124
orse+0.122
Neg logit contributions
 day-0.029
 she-0.025
 She-0.023
 especially-0.021
 sometimes-0.021
Token se
Token ID384
Feature activation-1.51e-01

Pos logit contributions
 she+0.660
 day+0.627
 always+0.618
 She+0.615
 especially+0.608
Neg logit contributions
itched-0.989
 tal-0.974
eg-0.932
izza-0.868
 cannon-0.858
Tokenwed
Token ID19103
Feature activation-1.45e-01

Pos logit contributions
itched+0.269
 tal+0.254
eg+0.234
orse+0.215
izza+0.212
Neg logit contributions
 She-0.327
 she-0.325
 day-0.319
 sometimes-0.293
 especially-0.292
Token,
Token ID11
Feature activation-3.63e-02

Pos logit contributions
itched+0.338
 tal+0.324
eg+0.306
orse+0.289
izza+0.284
Neg logit contributions
 She-0.224
 day-0.219
 she-0.218
 always-0.194
 like-0.193
Token st
Token ID336
Feature activation-1.11e-01

Pos logit contributions
itched+0.077
 tal+0.072
eg+0.067
orse+0.066
 fin+0.062
Neg logit contributions
 She-0.064
 day-0.063
 she-0.060
 weekend-0.056
 week-0.056
Tokenitched
Token ID10981
Feature activation-6.66e-01

Pos logit contributions
 tal+0.138
orse+0.121
 fin+0.110
 cannon+0.105
 wounds+0.105
Neg logit contributions
 She-0.297
 she-0.267
my-0.249
 like-0.249
She-0.248
Token,
Token ID11
Feature activation-3.66e-02

Pos logit contributions
itched+1.601
 tal+1.578
eg+1.509
orse+1.448
izza+1.423
Neg logit contributions
 She-0.990
 she-0.984
 day-0.952
 like-0.883
 sometimes-0.850
Token and
Token ID290
Feature activation+8.54e-02

Pos logit contributions
itched+0.088
 tal+0.084
eg+0.079
orse+0.076
 fin+0.074
Neg logit contributions
 She-0.054
 day-0.053
 she-0.052
 sometimes-0.046
 like-0.046
Token pinned
Token ID25711
Feature activation-2.82e-01

Pos logit contributions
 She+0.139
 day+0.134
 she+0.132
 like+0.119
 always+0.118
Neg logit contributions
itched-0.193
 tal-0.185
eg-0.173
orse-0.166
izza-0.161
Token her
Token ID607
Feature activation+3.24e-01

Pos logit contributions
itched+0.619
 tal+0.589
eg+0.548
 fin+0.505
izza+0.505
Neg logit contributions
 She-0.446
 day-0.437
 she-0.417
 weekend-0.398
 always-0.398
Token masterpiece
Token ID30669
Feature activation-2.82e-01

Pos logit contributions
 day+0.597
 she+0.583
 She+0.574
 like+0.526
my+0.525
Neg logit contributions
itched-0.684
 tal-0.647
eg-0.602
orse-0.593
izza-0.577
Token its
Token ID663
Feature activation-1.89e-01

Pos logit contributions
 she+0.150
 day+0.146
 She+0.141
 like+0.137
 always+0.137
Neg logit contributions
itched-0.225
eg-0.214
 tal-0.209
izza-0.199
orse-0.192
Token mother
Token ID2802
Feature activation-1.47e-01

Pos logit contributions
itched+0.426
 tal+0.414
eg+0.384
orse+0.363
 fin+0.357
Neg logit contributions
 She-0.310
 she-0.300
 day-0.295
 especially-0.264
 sometimes-0.264
Token who
Token ID508
Feature activation-4.31e-02

Pos logit contributions
itched+0.313
 tal+0.302
eg+0.280
orse+0.268
izza+0.260
Neg logit contributions
 She-0.257
 day-0.248
 she-0.248
 always-0.222
 sometimes-0.222
Token had
Token ID550
Feature activation+1.05e-01

Pos logit contributions
itched+0.100
 tal+0.096
eg+0.089
orse+0.087
izza+0.085
Neg logit contributions
 She-0.064
 day-0.062
 she-0.059
 weekend-0.055
 especially-0.055
Token st
Token ID336
Feature activation-1.09e-01

Pos logit contributions
 she+0.162
 day+0.157
 She+0.149
 always+0.147
 like+0.143
Neg logit contributions
itched-0.255
eg-0.246
 tal-0.241
izza-0.226
orse-0.221
Tokenitched
Token ID10981
Feature activation-6.65e-01

Pos logit contributions
 tal+0.118
 cannon+0.116
 rods+0.116
eg+0.114
orse+0.112
Neg logit contributions
 She-0.281
 she-0.252
my-0.248
 always-0.245
 like-0.244
Token the
Token ID262
Feature activation-2.57e-02

Pos logit contributions
itched+1.514
 tal+1.457
eg+1.363
orse+1.290
izza+1.268
Neg logit contributions
 She-1.065
 day-1.042
 she-1.040
 always-0.923
 like-0.922
Token egg
Token ID5935
Feature activation-1.18e-01

Pos logit contributions
itched+0.049
 tal+0.047
eg+0.043
orse+0.040
 fin+0.040
Neg logit contributions
 She-0.051
 she-0.050
 day-0.049
 like-0.046
 especially-0.045
Token together
Token ID1978
Feature activation-1.66e-01

Pos logit contributions
itched+0.254
 tal+0.244
eg+0.227
orse+0.216
izza+0.210
Neg logit contributions
 She-0.202
 day-0.197
 she-0.195
 especially-0.176
 always-0.176
Token.
Token ID13
Feature activation-5.09e-02

Pos logit contributions
itched+0.344
 tal+0.329
eg+0.301
orse+0.289
 fin+0.281
Neg logit contributions
 She-0.296
 day-0.286
 she-0.282
 weekend-0.257
 especially-0.257
Token<|endoftext|>
Token ID50256
Feature activation-2.70e-01

Pos logit contributions
itched+0.108
 tal+0.103
eg+0.097
orse+0.092
izza+0.090
Neg logit contributions
 She-0.092
 she-0.090
 day-0.089
 like-0.080
 always-0.080
Token sweet
Token ID6029
Feature activation+7.11e-02

Pos logit contributions
itched+0.177
 tal+0.166
eg+0.161
orse+0.152
izza+0.151
Neg logit contributions
 day-0.108
 She-0.106
 she-0.105
 like-0.093
 always-0.092
Token,
Token ID11
Feature activation-3.18e-02

Pos logit contributions
 She+0.135
 she+0.132
 day+0.131
 sometimes+0.120
 like+0.120
Neg logit contributions
itched-0.141
 tal-0.135
eg-0.126
orse-0.118
izza-0.115
Token high
Token ID1029
Feature activation+1.43e-02

Pos logit contributions
itched+0.071
 tal+0.068
eg+0.064
orse+0.061
izza+0.060
Neg logit contributions
 She-0.052
 day-0.051
 she-0.050
 sometimes-0.045
 always-0.045
Token-
Token ID12
Feature activation-1.70e-01

Pos logit contributions
 She+0.025
 she+0.025
 day+0.025
 like+0.022
 always+0.022
Neg logit contributions
itched-0.031
 tal-0.029
eg-0.028
orse-0.026
izza-0.025
Tokenp
Token ID79
Feature activation-1.25e-01

Pos logit contributions
itched+0.354
 tal+0.339
eg+0.322
orse+0.307
izza+0.297
Neg logit contributions
 She-0.301
 day-0.293
 she-0.292
 sometimes-0.270
 always-0.268
Tokenitched
Token ID10981
Feature activation-6.62e-01

Pos logit contributions
 tal+0.254
itched+0.253
eg+0.247
izza+0.230
 rods+0.223
Neg logit contributions
 she-0.223
 She-0.222
 day-0.216
 like-0.200
 always-0.197
Token voice
Token ID3809
Feature activation-1.82e-01

Pos logit contributions
itched+1.400
 tal+1.338
eg+1.284
orse+1.212
izza+1.196
Neg logit contributions
 She-1.180
 day-1.155
 she-1.153
 like-1.053
 always-1.034
Token.
Token ID13
Feature activation-3.80e-02

Pos logit contributions
itched+0.411
 tal+0.397
eg+0.378
orse+0.355
izza+0.353
Neg logit contributions
 She-0.307
 she-0.305
 day-0.296
 like-0.277
 always-0.266
Token �
Token ID6184
Feature activation-1.54e-01

Pos logit contributions
itched+0.093
 tal+0.090
eg+0.085
orse+0.081
izza+0.079
Neg logit contributions
 She-0.057
 she-0.055
 day-0.053
 like-0.048
 always-0.047
Token�
Token ID95
Feature activation-1.66e-01

Pos logit contributions
itched+0.281
 tal+0.274
eg+0.248
 fin+0.232
orse+0.231
Neg logit contributions
 She-0.324
 she-0.314
 day-0.307
 like-0.290
 always-0.285
Token€
Token ID26391
Feature activation+6.28e-02

Pos logit contributions
itched+0.363
 tal+0.345
eg+0.324
orse+0.306
 fin+0.303
Neg logit contributions
 She-0.291
 day-0.278
 she-0.274
 like-0.254
 always-0.253
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
 She+0.503
 day+0.501
 she+0.500
 always+0.439
 like+0.438
Neg logit contributions
itched-0.699
 tal-0.674
eg-0.637
orse-0.605
izza-0.596
Token<|endoftext|>
Token ID50256
Feature activation-1.90e-01

Pos logit contributions
 She+0.043
 she+0.042
 day+0.042
 like+0.037
 sometimes+0.036
Neg logit contributions
itched-0.075
 tal-0.072
eg-0.069
orse-0.065
izza-0.064
TokenOnce
Token ID7454
Feature activation+2.01e-01

Pos logit contributions
itched+0.439
 tal+0.426
eg+0.403
urger+0.393
izza+0.385
Neg logit contributions
 She-0.329
 day-0.319
 she-0.305
my-0.276
 week-0.266
Token upon
Token ID2402
Feature activation+1.16e-01

Pos logit contributions
 She+0.251
 she+0.246
 day+0.246
 like+0.208
 always+0.208
Neg logit contributions
itched-0.531
 tal-0.515
eg-0.489
orse-0.465
izza-0.460
Token a
Token ID257
Feature activation-1.85e-02

Pos logit contributions
 She+0.230
 day+0.227
 she+0.224
 weekend+0.210
 week+0.208
Neg logit contributions
itched-0.205
 tal-0.195
orse-0.175
eg-0.175
 fin-0.166
Token time
Token ID640
Feature activation+2.73e-01

Pos logit contributions
itched+0.052
 tal+0.050
eg+0.048
orse+0.047
izza+0.045
Neg logit contributions
 She-0.020
 she-0.020
 day-0.017
 sometimes-0.016
 like-0.015
Token,
Token ID11
Feature activation+1.02e-02

Pos logit contributions
 She+0.466
 she+0.456
 day+0.456
 like+0.409
 always+0.407
Neg logit contributions
itched-0.598
 tal-0.574
eg-0.540
orse-0.509
izza-0.500
Token there
Token ID612
Feature activation+7.99e-02

Pos logit contributions
 She+0.015
 she+0.014
 day+0.014
 like+0.013
 especially+0.013
Neg logit contributions
itched-0.025
 tal-0.023
eg-0.022
orse-0.021
izza-0.021
Token was
Token ID373
Feature activation+3.16e-02

Pos logit contributions
 She+0.133
 she+0.129
 day+0.129
 like+0.116
 especially+0.116
Neg logit contributions
itched-0.177
 tal-0.168
eg-0.158
orse-0.150
izza-0.145
Token a
Token ID257
Feature activation-2.84e-02

Pos logit contributions
 She+0.065
 she+0.063
 day+0.062
 matter+0.061
my+0.059
Neg logit contributions
itched-0.054
 tal-0.051
orse-0.045
eg-0.045
izza-0.042
Token little
Token ID1310
Feature activation+3.81e-02

Pos logit contributions
itched+0.064
 tal+0.061
eg+0.059
orse+0.056
 fin+0.054
Neg logit contributions
 She-0.046
 she-0.044
 day-0.044
 sometimes-0.040
 like-0.039
Token said
Token ID531
Feature activation-1.34e-01

Pos logit contributions
itched+0.360
 tal+0.340
eg+0.326
ades+0.312
izza+0.310
Neg logit contributions
 She-0.225
 she-0.223
my-0.201
 always-0.194
 sometimes-0.191
Token.
Token ID13
Feature activation-4.34e-02

Pos logit contributions
 tal+0.364
itched+0.344
eg+0.336
izza+0.316
orse+0.313
Neg logit contributions
 she-0.199
 She-0.193
 day-0.166
 her-0.155
 like-0.153
Token
Token ID198
Feature activation-1.28e-01

Pos logit contributions
itched+0.111
 tal+0.108
eg+0.101
urger+0.098
izza+0.097
Neg logit contributions
 She-0.074
 she-0.068
 day-0.060
 sometimes-0.056
 like-0.055
Token
Token ID198
Feature activation-1.29e-01

Pos logit contributions
 tal+0.345
itched+0.338
urger+0.333
eg+0.326
 jaws+0.318
Neg logit contributions
 She-0.189
 she-0.169
 day-0.156
She-0.148
my-0.144
Token"
Token ID1
Feature activation-1.19e-01

Pos logit contributions
itched+0.279
 tal+0.268
eg+0.251
orse+0.235
izza+0.232
Neg logit contributions
 She-0.229
 she-0.223
 day-0.221
 sometimes-0.201
 like-0.200
TokenYou
Token ID1639
Feature activation+3.02e-01

Pos logit contributions
itched+0.322
orse+0.300
eg+0.292
ves+0.290
ades+0.289
Neg logit contributions
 day-0.108
 She-0.106
my-0.105
 she-0.094
 week-0.092
Token are
Token ID389
Feature activation+1.33e-01

Pos logit contributions
 She+0.349
 she+0.339
 day+0.339
 sometimes+0.280
 especially+0.280
Neg logit contributions
itched-0.826
 tal-0.799
eg-0.767
orse-0.730
izza-0.722
Token welcome
Token ID7062
Feature activation+1.67e-01

Pos logit contributions
 She+0.187
 she+0.184
 day+0.184
 weekend+0.162
 week+0.160
Neg logit contributions
itched-0.321
 tal-0.311
eg-0.298
orse-0.279
izza-0.277
Token.
Token ID13
Feature activation-4.50e-02

Pos logit contributions
 She+0.278
 she+0.272
 day+0.260
 like+0.244
 sometimes+0.236
Neg logit contributions
itched-0.392
 tal-0.374
eg-0.355
orse-0.343
izza-0.334
Token We
Token ID775
Feature activation-9.54e-02

Pos logit contributions
itched+0.111
 tal+0.109
eg+0.104
orse+0.100
izza+0.099
Neg logit contributions
 day-0.057
 she-0.056
 She-0.053
 especially-0.050
 week-0.049
Token are
Token ID389
Feature activation+1.32e-01

Pos logit contributions
itched+0.231
 tal+0.223
eg+0.221
orse+0.205
izza+0.203
Neg logit contributions
 She-0.128
 she-0.127
 day-0.113
 weekend-0.106
 week-0.102
Token and
Token ID290
Feature activation+1.60e-01

Pos logit contributions
itched+0.394
 tal+0.380
eg+0.360
orse+0.342
izza+0.337
Neg logit contributions
 She-0.229
 she-0.223
 day-0.223
 like-0.196
 always-0.195
Token thanked
Token ID26280
Feature activation-1.34e-01

Pos logit contributions
 she+0.292
 She+0.277
 day+0.273
 always+0.250
 like+0.243
Neg logit contributions
itched-0.353
 tal-0.334
eg-0.331
izza-0.308
ades-0.304
Token Miss
Token ID4544
Feature activation+7.17e-02

Pos logit contributions
itched+0.358
 tal+0.343
eg+0.334
izza+0.316
orse+0.314
Neg logit contributions
 she-0.174
 She-0.173
 day-0.166
 always-0.143
 like-0.141
Token Rose
Token ID8049
Feature activation+2.86e-02

Pos logit contributions
 She+0.118
 day+0.116
 she+0.115
 like+0.103
 always+0.103
Neg logit contributions
itched-0.159
 tal-0.153
eg-0.144
orse-0.136
izza-0.134
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
 She+0.043
 she+0.043
 day+0.043
 like+0.038
 sometimes+0.038
Neg logit contributions
itched-0.068
 tal-0.066
eg-0.062
orse-0.059
izza-0.058
Token She
Token ID1375
Feature activation+4.64e-01

Pos logit contributions
 She+0.014
 she+0.013
 day+0.012
 sometimes+0.011
 always+0.011
Neg logit contributions
itched-0.027
 tal-0.026
eg-0.025
orse-0.024
 fin-0.024
Token felt
Token ID2936
Feature activation-1.72e-03

Pos logit contributions
 she+0.767
 She+0.736
 always+0.711
 day+0.696
 especially+0.666
Neg logit contributions
itched-1.102
 tal-1.037
eg-1.027
izza-0.963
ades-0.946
Token good
Token ID922
Feature activation+1.10e-01

Pos logit contributions
itched+0.004
 tal+0.004
eg+0.003
orse+0.003
 fin+0.003
Neg logit contributions
 She-0.003
 day-0.003
 she-0.003
 weekend-0.002
my-0.002
Token and
Token ID290
Feature activation+1.23e-01

Pos logit contributions
 She+0.163
 day+0.154
 she+0.152
 especially+0.141
 weekend+0.139
Neg logit contributions
itched-0.264
 tal-0.254
eg-0.235
orse-0.228
 fin-0.223
Token wanted
Token ID2227
Feature activation+1.69e-01

Pos logit contributions
 She+0.212
 day+0.207
 she+0.196
 weekend+0.193
 week+0.190
Neg logit contributions
itched-0.253
 tal-0.244
eg-0.220
orse-0.216
 fin-0.206
Token to
Token ID284
Feature activation-2.40e-02

Pos logit contributions
 She+0.291
 day+0.284
 she+0.283
 like+0.255
 always+0.253
Neg logit contributions
itched-0.366
 tal-0.351
eg-0.329
orse-0.311
izza-0.305
Token Ben
Token ID3932
Feature activation-6.83e-03

Pos logit contributions
 She+0.139
 she+0.137
 day+0.134
 sometimes+0.119
 like+0.119
Neg logit contributions
itched-0.218
 tal-0.210
eg-0.198
orse-0.188
izza-0.185
Token learned
Token ID4499
Feature activation-6.68e-02

Pos logit contributions
itched+0.019
 tal+0.019
eg+0.018
izza+0.018
alks+0.017
Neg logit contributions
 like-0.008
 she-0.008
 She-0.008
 always-0.007
 sometimes-0.007
Token a
Token ID257
Feature activation-6.84e-02

Pos logit contributions
itched+0.171
 tal+0.164
eg+0.161
orse+0.159
urger+0.150
Neg logit contributions
 she-0.105
 She-0.102
 her-0.093
 day-0.091
 sometimes-0.090
Token lesson
Token ID11483
Feature activation-3.90e-02

Pos logit contributions
itched+0.170
 tal+0.163
eg+0.152
orse+0.149
izza+0.144
Neg logit contributions
 day-0.101
 She-0.100
 she-0.098
 always-0.087
 week-0.086
Token that
Token ID326
Feature activation-1.13e-02

Pos logit contributions
itched+0.080
 tal+0.076
eg+0.071
orse+0.068
izza+0.066
Neg logit contributions
 She-0.071
 day-0.069
 she-0.068
 especially-0.063
 always-0.063
Token day
Token ID1110
Feature activation+4.30e-01

Pos logit contributions
orse+0.033
itched+0.032
 fin+0.032
 tal+0.032
 cannon+0.032
Neg logit contributions
 She-0.007
She-0.005
heart-0.005
 she-0.004
 especially-0.004
Token.
Token ID13
Feature activation-3.93e-02

Pos logit contributions
 She+0.679
 she+0.673
 day+0.654
 sometimes+0.593
 like+0.592
Neg logit contributions
itched-1.011
 tal-1.003
eg-0.957
orse-0.895
izza-0.893
Token They
Token ID1119
Feature activation+7.49e-02

Pos logit contributions
itched+0.099
 tal+0.095
eg+0.091
orse+0.086
izza+0.086
Neg logit contributions
 day-0.053
 she-0.052
 She-0.051
 especially-0.046
 always-0.046
Token learned
Token ID4499
Feature activation-6.88e-02

Pos logit contributions
 She+0.117
 day+0.116
 she+0.114
 weekend+0.103
 week+0.102
Neg logit contributions
itched-0.168
 tal-0.165
eg-0.156
orse-0.147
 fin-0.143
Token that
Token ID326
Feature activation-1.24e-02

Pos logit contributions
itched+0.179
 tal+0.171
eg+0.165
orse+0.162
izza+0.155
Neg logit contributions
 she-0.100
 She-0.099
 day-0.093
 sometimes-0.089
 like-0.089
Token not
Token ID407
Feature activation-9.95e-02

Pos logit contributions
itched+0.030
 tal+0.029
orse+0.027
eg+0.027
 fin+0.027
Neg logit contributions
 She-0.017
 day-0.015
 she-0.015
my-0.014
 like-0.014
Token<|endoftext|>
Token ID50256
Feature activation-2.42e-01

Pos logit contributions
itched+0.041
 tal+0.040
eg+0.038
orse+0.036
izza+0.035
Neg logit contributions
 She-0.027
 day-0.027
 she-0.027
 like-0.024
 always-0.024
TokenS
Token ID50
Feature activation+8.77e-02

Pos logit contributions
itched+0.504
 tal+0.486
eg+0.454
orse+0.429
izza+0.419
Neg logit contributions
 She-0.453
 day-0.442
 she-0.436
 like-0.394
 sometimes-0.392
Tokenara
Token ID3301
Feature activation+5.60e-02

Pos logit contributions
 She+0.138
 day+0.137
 she+0.135
my+0.130
 week+0.121
Neg logit contributions
itched-0.204
 tal-0.202
 fin-0.182
eg-0.179
orse-0.177
Token and
Token ID290
Feature activation+1.11e-01

Pos logit contributions
 She+0.080
 she+0.079
 day+0.077
 especially+0.070
 weekend+0.070
Neg logit contributions
itched-0.133
 tal-0.127
eg-0.121
orse-0.115
izza-0.111
Token Ben
Token ID3932
Feature activation+1.13e-02

Pos logit contributions
 day+0.172
 She+0.162
 matter+0.161
 weekend+0.160
 especially+0.159
Neg logit contributions
itched-0.233
 tal-0.232
orse-0.210
eg-0.208
 fin-0.197
Token like
Token ID588
Feature activation+3.88e-01

Pos logit contributions
 day+0.015
 she+0.015
 She+0.015
 weekend+0.014
 week+0.014
Neg logit contributions
itched-0.026
 tal-0.025
eg-0.024
orse-0.023
izza-0.022
Token to
Token ID284
Feature activation-3.81e-02

Pos logit contributions
 She+0.664
 day+0.650
 she+0.650
 like+0.584
 always+0.582
Neg logit contributions
itched-0.844
 tal-0.809
eg-0.761
orse-0.718
izza-0.704
Token play
Token ID711
Feature activation+1.15e-01

Pos logit contributions
itched+0.097
 tal+0.093
eg+0.088
orse+0.085
 fin+0.082
Neg logit contributions
 She-0.050
 day-0.049
 she-0.049
 sometimes-0.043
 always-0.042
Token in
Token ID287
Feature activation+7.42e-02

Pos logit contributions
 day+0.157
 She+0.155
 she+0.155
 like+0.145
 sometimes+0.138
Neg logit contributions
 tal-0.295
itched-0.293
eg-0.279
izza-0.265
orse-0.263
Token the
Token ID262
Feature activation-3.96e-03

Pos logit contributions
 She+0.128
 she+0.124
 day+0.124
 always+0.114
 especially+0.114
Neg logit contributions
itched-0.158
 tal-0.150
eg-0.139
orse-0.133
 fin-0.130
Token park
Token ID3952
Feature activation+2.17e-01

Pos logit contributions
itched+0.008
 tal+0.008
eg+0.008
 rods+0.008
 fin+0.008
Neg logit contributions
 She-0.006
 she-0.006
 matter-0.006
 especially-0.005
 like-0.005
Token go
Token ID467
Feature activation+1.63e-01

Pos logit contributions
itched+0.047
 tal+0.045
eg+0.044
izza+0.041
orse+0.040
Neg logit contributions
 she-0.028
 day-0.028
 She-0.028
 like-0.026
 always-0.025
Token and
Token ID290
Feature activation+1.17e-01

Pos logit contributions
 She+0.292
 day+0.285
 she+0.281
 especially+0.258
 always+0.257
Neg logit contributions
itched-0.330
 tal-0.321
eg-0.290
orse-0.279
 fin-0.272
Token put
Token ID1234
Feature activation-2.15e-02

Pos logit contributions
 She+0.173
 she+0.172
 day+0.167
 like+0.150
 sometimes+0.150
Neg logit contributions
itched-0.288
 tal-0.276
eg-0.264
orse-0.247
izza-0.245
Token something
Token ID1223
Feature activation-1.21e-01

Pos logit contributions
itched+0.050
 tal+0.047
eg+0.046
orse+0.044
izza+0.043
Neg logit contributions
 she-0.034
 day-0.034
 She-0.034
 like-0.031
 sometimes-0.030
Token great
Token ID1049
Feature activation+3.15e-02

Pos logit contributions
itched+0.302
 tal+0.285
eg+0.281
orse+0.262
izza+0.258
Neg logit contributions
 she-0.182
 day-0.177
 She-0.170
 like-0.164
 sometimes-0.156
Token there
Token ID612
Feature activation+6.05e-02

Pos logit contributions
 She+0.052
 she+0.052
 day+0.052
 like+0.047
 sometimes+0.046
Neg logit contributions
itched-0.070
 tal-0.067
eg-0.064
orse-0.060
izza-0.059
Token to
Token ID284
Feature activation-2.47e-02

Pos logit contributions
 She+0.109
 day+0.106
 she+0.106
 especially+0.096
 always+0.096
Neg logit contributions
itched-0.124
 tal-0.119
eg-0.111
orse-0.105
izza-0.103
Token help
Token ID1037
Feature activation-4.89e-02

Pos logit contributions
itched+0.059
 tal+0.057
eg+0.054
izza+0.051
orse+0.051
Neg logit contributions
 She-0.037
 she-0.037
 day-0.037
 like-0.033
 always-0.033
Token it
Token ID340
Feature activation-3.47e-02

Pos logit contributions
itched+0.122
 tal+0.118
eg+0.111
orse+0.106
izza+0.104
Neg logit contributions
 She-0.068
 day-0.066
 she-0.066
 always-0.057
 like-0.057
Token."
Token ID526
Feature activation-5.23e-02

Pos logit contributions
itched+0.080
 tal+0.077
eg+0.074
orse+0.069
izza+0.068
Neg logit contributions
 She-0.056
 she-0.055
 day-0.054
 like-0.050
 always-0.049
Token
Token ID220
Feature activation-1.89e-01

Pos logit contributions
itched+0.117
 tal+0.111
eg+0.107
ades+0.100
urger+0.100
Neg logit contributions
 She-0.098
 she-0.094
 day-0.089
my-0.079
 always-0.077
Token.
Token ID13
Feature activation-3.53e-02

Pos logit contributions
 day+0.595
 She+0.591
 she+0.576
 like+0.533
 always+0.529
Neg logit contributions
itched-0.844
 tal-0.817
eg-0.771
izza-0.734
ades-0.720
Token Tim
Token ID5045
Feature activation+9.36e-03

Pos logit contributions
itched+0.068
 tal+0.059
eg+0.059
izza+0.056
orse+0.054
Neg logit contributions
 she-0.066
 day-0.063
 girl-0.060
 weekend-0.060
 always-0.059
Tokenmy
Token ID1820
Feature activation+3.66e-01

Pos logit contributions
 she+0.008
 She+0.007
 weekend+0.005
 day+0.005
 week+0.004
Neg logit contributions
itched-0.028
 tal-0.027
eg-0.026
orse-0.025
urger-0.025
Token loved
Token ID6151
Feature activation+8.56e-02

Pos logit contributions
 She+0.486
 she+0.477
 day+0.452
 weekend+0.414
 like+0.404
Neg logit contributions
itched-0.922
 tal-0.881
eg-0.852
orse-0.821
 fin-0.786
Token to
Token ID284
Feature activation-5.23e-02

Pos logit contributions
 She+0.148
 she+0.145
 day+0.144
 like+0.131
 sometimes+0.130
Neg logit contributions
itched-0.184
 tal-0.177
eg-0.166
orse-0.157
izza-0.154
Token play
Token ID711
Feature activation+9.79e-02

Pos logit contributions
itched+0.142
 tal+0.138
eg+0.130
orse+0.124
izza+0.123
Neg logit contributions
 She-0.063
 she-0.062
 day-0.062
 like-0.053
 always-0.053
Token games
Token ID1830
Feature activation+8.16e-02

Pos logit contributions
 She+0.115
 she+0.113
 day+0.113
 like+0.101
 always+0.098
Neg logit contributions
 tal-0.269
itched-0.267
eg-0.250
izza-0.241
orse-0.240
Token with
Token ID351
Feature activation-4.51e-02

Pos logit contributions
 She+0.162
 day+0.153
 matter+0.151
 she+0.149
 weekend+0.148
Neg logit contributions
itched-0.143
 tal-0.123
eg-0.121
ves-0.120
orse-0.117
Token his
Token ID465
Feature activation-1.12e-01

Pos logit contributions
itched+0.100
 tal+0.100
eg+0.090
orse+0.087
izza+0.086
Neg logit contributions
 day-0.079
 She-0.078
 she-0.078
 especially-0.071
 sometimes-0.070
Token friends
Token ID2460
Feature activation-1.43e-01

Pos logit contributions
itched+0.267
 tal+0.264
orse+0.235
eg+0.232
izza+0.229
Neg logit contributions
 day-0.192
 she-0.177
 She-0.172
 girl-0.156
 always-0.155
Token.
Token ID13
Feature activation-3.77e-02

Pos logit contributions
itched+0.287
 tal+0.267
eg+0.255
orse+0.237
 fin+0.233
Neg logit contributions
 She-0.265
 she-0.260
 day-0.254
 weekend-0.231
 especially-0.230
Token with
Token ID351
Feature activation-3.61e-02

Pos logit contributions
itched+0.138
 tal+0.138
eg+0.126
orse+0.120
 fin+0.120
Neg logit contributions
 She-0.120
 she-0.113
 day-0.112
 always-0.102
 weekend-0.101
Token you
Token ID345
Feature activation+2.06e-01

Pos logit contributions
itched+0.103
 tal+0.099
eg+0.095
orse+0.091
izza+0.089
Neg logit contributions
 She-0.038
 day-0.038
 she-0.037
 like-0.032
 always-0.031
Token."
Token ID526
Feature activation-6.37e-02

Pos logit contributions
 day+0.340
 She+0.335
 she+0.334
 like+0.312
 sometimes+0.303
Neg logit contributions
itched-0.473
 tal-0.455
eg-0.432
orse-0.401
ades-0.393
Token
Token ID198
Feature activation-1.08e-01

Pos logit contributions
itched+0.158
 tal+0.145
eg+0.141
ves+0.141
cks+0.138
Neg logit contributions
 She-0.114
 she-0.100
 day-0.095
my-0.088
 always-0.082
Token
Token ID198
Feature activation-1.08e-01

Pos logit contributions
 jaws+0.291
itched+0.289
 tal+0.283
sed+0.282
 fins+0.281
Neg logit contributions
 She-0.144
 day-0.130
 she-0.128
She-0.118
my-0.114
TokenThe
Token ID464
Feature activation-4.29e-02

Pos logit contributions
itched+0.260
 tal+0.252
eg+0.237
 fin+0.220
 cannon+0.219
Neg logit contributions
 She-0.170
 she-0.166
 day-0.162
 especially-0.150
 always-0.149
Token little
Token ID1310
Feature activation+9.15e-03

Pos logit contributions
itched+0.105
 tal+0.101
eg+0.095
orse+0.090
izza+0.089
Neg logit contributions
 day-0.064
 She-0.063
 she-0.062
 always-0.055
 sometimes-0.055
Token boy
Token ID2933
Feature activation+1.66e-01

Pos logit contributions
 She+0.010
 she+0.010
 day+0.009
 especially+0.008
 always+0.008
Neg logit contributions
itched-0.025
 tal-0.025
eg-0.023
orse-0.022
 fin-0.022
Token smiled
Token ID13541
Feature activation-2.10e-01

Pos logit contributions
 she+0.263
 always+0.259
 She+0.258
 day+0.252
 especially+0.237
Neg logit contributions
itched-0.395
 tal-0.384
eg-0.363
cks-0.347
ades-0.345
Token and
Token ID290
Feature activation+9.70e-02

Pos logit contributions
itched+0.564
 tal+0.553
eg+0.536
orse+0.512
izza+0.510
Neg logit contributions
 She-0.268
 she-0.256
 day-0.245
 like-0.230
 sometimes-0.217
Token was
Token ID373
Feature activation-1.05e-02

Pos logit contributions
 she+0.181
 She+0.168
 day+0.163
 always+0.153
 her+0.144
Neg logit contributions
itched-0.220
eg-0.206
 tal-0.203
ades-0.198
izza-0.194
Token they
Token ID484
Feature activation+1.95e-02

Pos logit contributions
 She+0.167
 day+0.163
 she+0.161
 like+0.146
 sometimes+0.145
Neg logit contributions
itched-0.234
 tal-0.224
eg-0.210
orse-0.201
izza-0.196
Token played
Token ID2826
Feature activation+1.83e-02

Pos logit contributions
 She+0.031
 day+0.030
 she+0.030
 weekend+0.027
 week+0.027
Neg logit contributions
itched-0.044
 tal-0.043
eg-0.040
orse-0.038
izza-0.037
Token together
Token ID1978
Feature activation-1.43e-01

Pos logit contributions
 She+0.032
 she+0.032
 day+0.032
 like+0.030
 always+0.029
Neg logit contributions
itched-0.040
 tal-0.039
eg-0.037
orse-0.034
izza-0.034
Token every
Token ID790
Feature activation+1.13e-01

Pos logit contributions
itched+0.354
 tal+0.340
eg+0.322
orse+0.307
izza+0.301
Neg logit contributions
 She-0.205
 she-0.198
 day-0.198
 like-0.173
 always-0.173
Token day
Token ID1110
Feature activation+4.45e-01

Pos logit contributions
 She+0.049
 she+0.033
 like+0.014
 especially+0.010
 always+0.010
Neg logit contributions
itched-0.388
 tal-0.383
orse-0.366
eg-0.358
 fin-0.357
Token.
Token ID13
Feature activation-2.89e-02

Pos logit contributions
 She+0.761
 she+0.752
 day+0.748
 like+0.673
 sometimes+0.667
Neg logit contributions
itched-0.973
 tal-0.938
eg-0.887
orse-0.827
izza-0.819
Token<|endoftext|>
Token ID50256
Feature activation-2.52e-01

Pos logit contributions
itched+0.059
 tal+0.057
eg+0.053
orse+0.050
izza+0.049
Neg logit contributions
 She-0.052
 she-0.052
 day-0.052
 like-0.047
 especially-0.047
TokenOnce
Token ID7454
Feature activation+1.48e-01

Pos logit contributions
itched+0.591
 tal+0.572
eg+0.540
urger+0.519
orse+0.514
Neg logit contributions
 She-0.430
 day-0.420
 she-0.400
 like-0.362
my-0.355
Token upon
Token ID2402
Feature activation+6.70e-02

Pos logit contributions
 She+0.194
 day+0.188
 she+0.188
 like+0.163
 always+0.162
Neg logit contributions
itched-0.379
 tal-0.366
eg-0.347
orse-0.332
izza-0.326
Token a
Token ID257
Feature activation-5.73e-02

Pos logit contributions
 She+0.130
 day+0.128
 she+0.127
 weekend+0.118
 week+0.116
Neg logit contributions
itched-0.124
 tal-0.116
eg-0.106
orse-0.105
 fin-0.100
Token time
Token ID640
Feature activation+2.34e-01

Pos logit contributions
itched+0.162
 tal+0.157
eg+0.148
orse+0.146
izza+0.141
Neg logit contributions
 She-0.060
 she-0.059
 day-0.052
 sometimes-0.048
 like-0.044
Token The
Token ID383
Feature activation-1.48e-01

Pos logit contributions
itched+0.109
 tal+0.104
eg+0.100
orse+0.094
 fin+0.092
Neg logit contributions
 She-0.085
 she-0.082
 day-0.079
 always-0.071
 sometimes-0.071
Token little
Token ID1310
Feature activation-6.33e-03

Pos logit contributions
itched+0.299
 tal+0.280
eg+0.259
 fin+0.256
orse+0.253
Neg logit contributions
 She-0.264
 she-0.249
 day-0.235
 like-0.231
 always-0.231
Token girl
Token ID2576
Feature activation+3.39e-01

Pos logit contributions
 tal+0.016
itched+0.015
 fin+0.015
 fist+0.014
 fins+0.014
Neg logit contributions
 She-0.006
 always-0.006
 especially-0.006
 weekend-0.006
ock-0.005
Token noticed
Token ID6810
Feature activation-6.43e-02

Pos logit contributions
 she+0.453
 She+0.446
 always+0.436
 day+0.424
 especially+0.398
Neg logit contributions
itched-0.886
 tal-0.864
eg-0.843
izza-0.806
ades-0.801
Token too
Token ID1165
Feature activation+9.58e-02

Pos logit contributions
itched+0.150
 tal+0.146
eg+0.142
orse+0.131
izza+0.130
Neg logit contributions
 she-0.103
 She-0.102
 day-0.099
 sometimes-0.090
 like-0.089
Token and
Token ID290
Feature activation+8.03e-02

Pos logit contributions
 She+0.151
 day+0.149
 she+0.147
 always+0.132
 weekend+0.131
Neg logit contributions
itched-0.221
 tal-0.211
eg-0.198
orse-0.189
izza-0.184
Token said
Token ID531
Feature activation-1.33e-01

Pos logit contributions
 she+0.124
 She+0.120
 day+0.108
 always+0.104
 sometimes+0.102
Neg logit contributions
itched-0.202
 tal-0.198
eg-0.193
izza-0.178
ades-0.175
Token,
Token ID11
Feature activation-4.23e-02

Pos logit contributions
 tal+0.336
itched+0.331
eg+0.325
urger+0.303
orse+0.301
Neg logit contributions
 she-0.216
 She-0.205
 day-0.178
 like-0.172
 sometimes-0.168
Token "
Token ID366
Feature activation-1.44e-01

Pos logit contributions
 tal+0.096
itched+0.095
eg+0.092
ades+0.084
izza+0.083
Neg logit contributions
 She-0.077
 she-0.077
 day-0.068
 always-0.064
 like-0.063
TokenOh
Token ID5812
Feature activation+1.71e-01

Pos logit contributions
itched+0.340
 tal+0.332
 fin+0.302
 pri+0.302
orse+0.302
Neg logit contributions
 day-0.189
 she-0.180
 She-0.173
 weekend-0.165
 week-0.162
Token no
Token ID645
Feature activation-5.12e-02

Pos logit contributions
 she+0.249
 She+0.231
 day+0.227
 like+0.210
 always+0.210
Neg logit contributions
itched-0.436
eg-0.415
 tal-0.409
ades-0.399
 rods-0.390
Token fly
Token ID6129
Feature activation+1.90e-03

Pos logit contributions
itched+0.090
 tal+0.087
eg+0.080
orse+0.076
 fin+0.075
Neg logit contributions
 She-0.076
 day-0.074
 she-0.073
 weekend-0.067
 week-0.067
Token away
Token ID1497
Feature activation-1.55e-02

Pos logit contributions
 She+0.003
 day+0.003
 she+0.003
 weekend+0.003
 week+0.003
Neg logit contributions
itched-0.004
 tal-0.004
eg-0.004
 fin-0.003
orse-0.003
Token,
Token ID11
Feature activation-2.58e-02

Pos logit contributions
itched+0.035
 tal+0.034
eg+0.032
orse+0.030
izza+0.030
Neg logit contributions
 She-0.025
 she-0.025
 day-0.025
 like-0.022
 always-0.022
Token but
Token ID475
Feature activation+1.88e-01

Pos logit contributions
itched+0.071
 tal+0.070
eg+0.065
orse+0.064
 fin+0.063
Neg logit contributions
 day-0.027
 She-0.027
 she-0.025
 weekend-0.023
 week-0.022
Token he
Token ID339
Feature activation+5.26e-02

Pos logit contributions
 She+0.309
 day+0.298
 she+0.295
 like+0.267
 especially+0.265
Neg logit contributions
itched-0.420
 tal-0.407
eg-0.379
orse-0.363
 fin-0.352
Token hurt
Token ID5938
Feature activation-1.00e-01

Pos logit contributions
 she+0.087
 day+0.086
 She+0.083
 always+0.080
 especially+0.077
Neg logit contributions
itched-0.119
 tal-0.115
eg-0.110
izza-0.107
ades-0.104
Token his
Token ID465
Feature activation-1.05e-01

Pos logit contributions
itched+0.193
 tal+0.184
eg+0.172
orse+0.161
izza+0.157
Neg logit contributions
 She-0.200
 she-0.196
 day-0.196
 like-0.179
 always-0.179
Token wing
Token ID8539
Feature activation-2.89e-01

Pos logit contributions
itched+0.184
 tal+0.166
eg+0.164
izza+0.162
ades+0.159
Neg logit contributions
 day-0.229
 She-0.215
 she-0.213
 always-0.207
 like-0.205
Token.
Token ID13
Feature activation-3.73e-02

Pos logit contributions
itched+0.640
 tal+0.613
eg+0.566
orse+0.531
 fin+0.527
Neg logit contributions
 She-0.479
 day-0.469
 she-0.467
 weekend-0.427
 week-0.417
Token Ups
Token ID35949
Feature activation-1.41e-01

Pos logit contributions
itched+0.089
 tal+0.085
eg+0.083
urger+0.080
orse+0.080
Neg logit contributions
 She-0.067
 she-0.058
 day-0.055
 always-0.051
 sometimes-0.048
Tokenet
Token ID316
Feature activation+3.63e-02

Pos logit contributions
 tal+0.282
itched+0.275
cks+0.246
eg+0.245
orse+0.236
Neg logit contributions
 She-0.258
 she-0.258
 day-0.242
I-0.226
 weekend-0.223
Token for
Token ID329
Feature activation+9.84e-02

Pos logit contributions
itched+0.094
 tal+0.090
eg+0.085
orse+0.081
 fin+0.079
Neg logit contributions
 She-0.070
 day-0.068
 she-0.067
my-0.061
 always-0.061
Token Spot
Token ID15899
Feature activation-9.65e-02

Pos logit contributions
 she+0.075
 She+0.072
 day+0.068
 always+0.053
 sometimes+0.050
Neg logit contributions
itched-0.312
 tal-0.307
eg-0.298
izza-0.285
orse-0.283
Token.
Token ID13
Feature activation-3.60e-02

Pos logit contributions
itched+0.208
 tal+0.199
eg+0.187
orse+0.177
izza+0.173
Neg logit contributions
 She-0.167
 day-0.163
 she-0.163
 like-0.146
 always-0.146
Token She
Token ID1375
Feature activation+4.26e-01

Pos logit contributions
itched+0.091
 tal+0.087
eg+0.083
orse+0.079
izza+0.078
Neg logit contributions
 She-0.049
 day-0.048
 she-0.048
 like-0.042
 always-0.042
Token used
Token ID973
Feature activation-7.17e-02

Pos logit contributions
 day+0.606
 she+0.600
 always+0.597
 She+0.581
 especially+0.555
Neg logit contributions
itched-1.053
 tal-1.043
eg-0.967
izza-0.914
eed-0.890
Token some
Token ID617
Feature activation-1.01e-01

Pos logit contributions
itched+0.171
 tal+0.166
eg+0.159
orse+0.151
izza+0.148
Neg logit contributions
 She-0.109
 she-0.107
 day-0.106
 like-0.094
 always-0.093
Token paper
Token ID3348
Feature activation-1.04e-01

Pos logit contributions
itched+0.213
 tal+0.204
eg+0.191
orse+0.180
izza+0.177
Neg logit contributions
 She-0.181
 she-0.177
 day-0.177
 like-0.159
 always-0.159
Token and
Token ID290
Feature activation+9.28e-02

Pos logit contributions
itched+0.244
 tal+0.238
eg+0.224
orse+0.215
izza+0.209
Neg logit contributions
 She-0.161
 she-0.160
 day-0.155
 like-0.141
 sometimes-0.140
Token cr
Token ID1067
Feature activation-1.80e-01

Pos logit contributions
 she+0.172
 She+0.168
 day+0.165
 sometimes+0.153
 like+0.150
Neg logit contributions
itched-0.195
 tal-0.185
eg-0.179
orse-0.165
izza-0.162
Tokenay
Token ID323
Feature activation-2.51e-02

Pos logit contributions
itched+0.412
 tal+0.400
eg+0.375
orse+0.361
 fin+0.350
Neg logit contributions
 She-0.288
 she-0.276
 day-0.274
 like-0.248
 always-0.245
Tokenons
Token ID684
Feature activation-2.44e-01

Pos logit contributions
 tal+0.042
itched+0.042
eg+0.040
 fin+0.038
 fist+0.036
Neg logit contributions
 she-0.053
 She-0.052
 day-0.052
my-0.049
 like-0.048
Token never
Token ID1239
Feature activation+5.71e-02

Pos logit contributions
 She+0.293
 day+0.286
 she+0.286
 like+0.249
 sometimes+0.248
Neg logit contributions
itched-0.529
 tal-0.509
eg-0.483
orse-0.460
izza-0.452
Token go
Token ID467
Feature activation+1.18e-01

Pos logit contributions
 She+0.077
 she+0.074
 day+0.074
 weekend+0.064
 sometimes+0.063
Neg logit contributions
itched-0.142
 tal-0.140
eg-0.130
orse-0.128
 fin-0.124
Token near
Token ID1474
Feature activation+6.45e-02

Pos logit contributions
 She+0.209
 day+0.202
 she+0.195
 weekend+0.183
 week+0.182
Neg logit contributions
itched-0.241
 tal-0.234
eg-0.207
orse-0.206
 fin-0.201
Token the
Token ID262
Feature activation-3.38e-02

Pos logit contributions
 She+0.099
 she+0.099
 day+0.097
 like+0.087
 sometimes+0.086
Neg logit contributions
itched-0.154
 tal-0.147
eg-0.143
orse-0.134
izza-0.133
Token river
Token ID7850
Feature activation-3.84e-03

Pos logit contributions
itched+0.081
 tal+0.077
eg+0.073
orse+0.069
izza+0.068
Neg logit contributions
 She-0.052
 day-0.052
 she-0.051
 like-0.046
 always-0.046
Token again
Token ID757
Feature activation-1.47e-01

Pos logit contributions
itched+0.008
 tal+0.007
eg+0.007
orse+0.007
izza+0.006
Neg logit contributions
 She-0.007
 she-0.007
 day-0.007
 like-0.006
 always-0.006
Token.
Token ID13
Feature activation-5.92e-02

Pos logit contributions
itched+0.304
 tal+0.296
eg+0.262
orse+0.259
 fin+0.250
Neg logit contributions
 She-0.257
 day-0.249
 she-0.245
 always-0.224
 weekend-0.223
Token She
Token ID1375
Feature activation+4.07e-01

Pos logit contributions
itched+0.157
 tal+0.153
eg+0.144
izza+0.137
orse+0.137
Neg logit contributions
 day-0.069
 she-0.067
 She-0.065
 like-0.060
 especially-0.060
Token was
Token ID373
Feature activation-3.02e-02

Pos logit contributions
 day+0.563
 she+0.555
 always+0.541
 She+0.535
 especially+0.513
Neg logit contributions
itched-1.044
 tal-0.971
eg-0.967
izza-0.918
ades-0.896
Token too
Token ID1165
Feature activation+8.43e-02

Pos logit contributions
itched+0.078
 tal+0.075
eg+0.072
orse+0.068
izza+0.068
Neg logit contributions
 She-0.040
 she-0.039
 day-0.039
 always-0.035
 like-0.035
Token scared
Token ID12008
Feature activation-3.72e-02

Pos logit contributions
 She+0.119
 she+0.117
 day+0.115
 like+0.107
 always+0.105
Neg logit contributions
itched-0.212
 tal-0.205
eg-0.200
izza-0.189
ves-0.185
Token called
Token ID1444
Feature activation-2.79e-02

Pos logit contributions
 she+0.595
 She+0.595
 day+0.564
 always+0.561
 like+0.534
Neg logit contributions
itched-1.009
 tal-0.969
eg-0.922
izza-0.896
ades-0.868
Token his
Token ID465
Feature activation-1.27e-01

Pos logit contributions
itched+0.070
 tal+0.067
eg+0.064
orse+0.061
izza+0.060
Neg logit contributions
 She-0.039
 she-0.038
 day-0.038
 like-0.033
 always-0.033
Token name
Token ID1438
Feature activation-2.03e-01

Pos logit contributions
itched+0.282
 tal+0.263
orse+0.259
ves+0.239
eg+0.238
Neg logit contributions
 day-0.238
 She-0.223
 she-0.214
 like-0.211
 girl-0.206
Token.
Token ID13
Feature activation-5.24e-02

Pos logit contributions
itched+0.471
 tal+0.446
eg+0.423
orse+0.397
izza+0.394
Neg logit contributions
 She-0.305
 day-0.303
 she-0.297
 especially-0.268
 always-0.266
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
 tal+0.120
itched+0.119
eg+0.110
orse+0.105
urger+0.103
Neg logit contributions
 She-0.094
 she-0.088
 day-0.081
 like-0.075
 always-0.074
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
 tal+0.357
itched+0.349
urger+0.344
eg+0.333
 jaws+0.328
Neg logit contributions
 She-0.205
 she-0.186
 day-0.174
She-0.152
 week-0.146
Token"
Token ID1
Feature activation-1.27e-01

Pos logit contributions
itched+0.291
 tal+0.279
eg+0.262
orse+0.246
izza+0.242
Neg logit contributions
 She-0.238
 she-0.234
 day-0.233
 like-0.210
 always-0.209
TokenBen
Token ID11696
Feature activation+1.26e-02

Pos logit contributions
itched+0.278
 tal+0.265
orse+0.256
ves+0.251
eg+0.251
Neg logit contributions
 day-0.187
 She-0.185
 she-0.172
 like-0.169
 always-0.163
Token,
Token ID11
Feature activation-4.82e-02

Pos logit contributions
 She+0.019
 she+0.019
 day+0.018
my+0.017
 always+0.017
Neg logit contributions
itched-0.031
 tal-0.030
eg-0.029
ades-0.027
orse-0.027
Token wait
Token ID4043
Feature activation+1.04e-01

Pos logit contributions
itched+0.104
 tal+0.104
eg+0.099
orse+0.098
 fin+0.096
Neg logit contributions
 She-0.072
 day-0.068
 she-0.063
 weekend-0.063
 week-0.062
Token for
Token ID329
Feature activation+7.43e-02

Pos logit contributions
 She+0.174
 day+0.172
 she+0.172
 like+0.157
 always+0.153
Neg logit contributions
itched-0.234
 tal-0.224
eg-0.214
orse-0.199
izza-0.196
Token"
Token ID1
Feature activation-1.26e-01

Pos logit contributions
itched+0.319
 tal+0.312
eg+0.291
orse+0.274
 fin+0.271
Neg logit contributions
 She-0.215
 she-0.210
 day-0.207
 like-0.185
 sometimes-0.185
TokenTom
Token ID13787
Feature activation-4.16e-03

Pos logit contributions
itched+0.269
 tal+0.260
eg+0.250
 rods+0.247
ades+0.243
Neg logit contributions
 She-0.188
 she-0.186
 day-0.184
 always-0.166
 especially-0.161
Token!
Token ID0
Feature activation-1.19e-01

Pos logit contributions
itched+0.011
 tal+0.011
eg+0.010
orse+0.010
izza+0.010
Neg logit contributions
 She-0.005
 day-0.005
 she-0.005
 like-0.004
my-0.004
Token Lily
Token ID20037
Feature activation+1.66e-01

Pos logit contributions
itched+0.289
 tal+0.280
eg+0.259
ves+0.249
orse+0.248
Neg logit contributions
 She-0.189
 she-0.175
 day-0.174
 like-0.154
 sometimes-0.151
Token!
Token ID0
Feature activation-1.20e-01

Pos logit contributions
 She+0.298
 she+0.292
 day+0.292
 like+0.264
 always+0.263
Neg logit contributions
itched-0.350
 tal-0.336
eg-0.315
orse-0.297
izza-0.291
Token What
Token ID1867
Feature activation-9.71e-02

Pos logit contributions
itched+0.286
 tal+0.275
eg+0.260
orse+0.247
izza+0.242
Neg logit contributions
 She-0.182
 she-0.177
 day-0.177
 like-0.157
 sometimes-0.155
Token are
Token ID389
Feature activation+1.26e-01

Pos logit contributions
itched+0.250
 tal+0.241
eg+0.230
orse+0.219
izza+0.216
Neg logit contributions
 She-0.128
 day-0.124
 she-0.124
 like-0.107
 sometimes-0.106
Token you
Token ID345
Feature activation+1.81e-01

Pos logit contributions
 She+0.136
 day+0.130
my+0.119
 she+0.113
 especially+0.111
Neg logit contributions
itched-0.342
 tal-0.326
eg-0.315
ves-0.307
orse-0.306
Token doing
Token ID1804
Feature activation+1.11e-01

Pos logit contributions
 day+0.177
 she+0.171
 She+0.170
 always+0.150
 like+0.147
Neg logit contributions
itched-0.528
 tal-0.523
eg-0.501
izza-0.478
orse-0.471
Token?"
Token ID1701
Feature activation-6.80e-02

Pos logit contributions
 She+0.183
 day+0.179
 she+0.179
 like+0.160
 always+0.159
Neg logit contributions
itched-0.248
 tal-0.238
eg-0.224
orse-0.212
izza-0.208
Token Mom
Token ID11254
Feature activation-1.12e-01

Pos logit contributions
itched+0.127
 tal+0.119
eg+0.111
orse+0.106
izza+0.101
Neg logit contributions
 day-0.134
 She-0.133
 she-0.129
 like-0.123
 always-0.122
Token said
Token ID531
Feature activation-1.39e-01

Pos logit contributions
itched+0.232
eg+0.227
 tal+0.226
 cannon+0.209
izza+0.208
Neg logit contributions
 she-0.150
 She-0.137
 day-0.134
 always-0.130
 sometimes-0.126
Token.
Token ID13
Feature activation-5.79e-02

Pos logit contributions
 tal+0.392
eg+0.380
itched+0.367
 rods+0.354
ades+0.352
Neg logit contributions
 she-0.189
 She-0.173
 like-0.147
 day-0.146
 her-0.140
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
itched+0.137
 tal+0.131
eg+0.129
ves+0.124
 wounds+0.123
Neg logit contributions
 She-0.106
 she-0.093
 day-0.082
 always-0.075
 sometimes-0.075
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
 tal+0.360
urger+0.356
itched+0.353
 fist+0.345
eg+0.345
Neg logit contributions
 She-0.173
 day-0.154
 she-0.148
She-0.132
 always-0.123
TokenP
Token ID47
Feature activation+2.70e-02

Pos logit contributions
itched+0.329
 tal+0.319
eg+0.304
izza+0.281
orse+0.278
Neg logit contributions
 She-0.196
 she-0.188
 day-0.187
 sometimes-0.170
 always-0.169
Tokenete
Token ID14471
Feature activation-4.35e-01

Pos logit contributions
 She+0.060
 day+0.059
 she+0.059
 always+0.056
 week+0.055
Neg logit contributions
itched-0.039
 tal-0.035
 wounds-0.033
eg-0.032
 fin-0.032
Token nodded
Token ID14464
Feature activation-2.27e-01

Pos logit contributions
 tal+1.166
itched+1.164
eg+1.113
cks+1.062
ades+1.042
Neg logit contributions
 always-0.533
 She-0.533
 she-0.532
 day-0.506
 sometimes-0.493
Token.
Token ID13
Feature activation-5.88e-02

Pos logit contributions
 tal+0.603
eg+0.593
itched+0.588
izza+0.566
engu+0.548
Neg logit contributions
 she-0.295
 She-0.293
 day-0.277
 like-0.271
 sometimes-0.258
Token Together
Token ID17083
Feature activation-1.77e-01

Pos logit contributions
itched+0.141
 tal+0.137
eg+0.129
ves+0.126
orse+0.124
Neg logit contributions
 She-0.103
 she-0.089
 day-0.085
 always-0.077
 sometimes-0.076
Token,
Token ID11
Feature activation-5.09e-02

Pos logit contributions
itched+0.450
 tal+0.447
eg+0.435
ades+0.405
cks+0.401
Neg logit contributions
 she-0.256
 day-0.253
 She-0.245
 sometimes-0.222
 always-0.206
Token they
Token ID484
Feature activation-1.46e-02

Pos logit contributions
itched+0.137
 tal+0.133
eg+0.132
urger+0.121
ades+0.121
Neg logit contributions
 she-0.069
 day-0.065
 She-0.064
 sometimes-0.057
 like-0.054
Token special
Token ID2041
Feature activation-2.95e-02

Pos logit contributions
itched+0.407
 tal+0.392
eg+0.371
orse+0.352
izza+0.346
Neg logit contributions
 She-0.253
 day-0.247
 she-0.247
 like-0.218
 always-0.217
Token with
Token ID351
Feature activation-6.38e-02

Pos logit contributions
itched+0.062
 tal+0.060
eg+0.056
orse+0.053
 fin+0.052
Neg logit contributions
 She-0.051
 she-0.048
 day-0.048
 especially-0.044
my-0.044
Token him
Token ID683
Feature activation+4.22e-03

Pos logit contributions
itched+0.142
 tal+0.137
eg+0.129
orse+0.123
izza+0.119
Neg logit contributions
 She-0.107
 day-0.107
 she-0.106
 like-0.098
 always-0.095
Token -
Token ID532
Feature activation-9.39e-02

Pos logit contributions
 she+0.007
 day+0.007
 She+0.007
 like+0.006
 always+0.006
Neg logit contributions
itched-0.010
 tal-0.010
eg-0.009
orse-0.009
izza-0.008
Token a
Token ID257
Feature activation-9.03e-02

Pos logit contributions
itched+0.171
 tal+0.163
eg+0.152
 fin+0.147
orse+0.146
Neg logit contributions
 She-0.178
 day-0.175
 she-0.166
 week-0.161
 weekend-0.160
Token hook
Token ID8011
Feature activation-4.15e-01

Pos logit contributions
itched+0.205
 tal+0.196
eg+0.184
orse+0.175
izza+0.172
Neg logit contributions
 She-0.147
 day-0.146
 she-0.146
 like-0.129
 always-0.129
Token.
Token ID13
Feature activation-5.96e-02

Pos logit contributions
itched+0.898
 tal+0.861
eg+0.809
orse+0.764
izza+0.749
Neg logit contributions
 She-0.712
 day-0.698
 she-0.698
 like-0.628
 always-0.625
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
itched+0.150
 tal+0.146
urger+0.136
 wounds+0.136
eg+0.135
Neg logit contributions
 She-0.099
 she-0.081
 day-0.080
my-0.075
 like-0.072
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
itched+0.343
 tal+0.339
eg+0.318
urger+0.318
 jaws+0.310
Neg logit contributions
 She-0.210
 day-0.197
 she-0.191
my-0.175
 week-0.165
TokenSam
Token ID16305
Feature activation-7.93e-02

Pos logit contributions
itched+0.322
 tal+0.312
eg+0.290
izza+0.275
orse+0.274
Neg logit contributions
 She-0.219
 day-0.211
 she-0.208
 like-0.188
my-0.186
Token wanted
Token ID2227
Feature activation+1.21e-01

Pos logit contributions
itched+0.266
 tal+0.260
eg+0.248
orse+0.241
izza+0.235
Neg logit contributions
 She-0.036
 she-0.034
 day-0.033
 like-0.022
 weekend-0.021
Token into
Token ID656
Feature activation-9.91e-02

Pos logit contributions
itched+0.137
 tal+0.134
eg+0.128
orse+0.124
izza+0.121
Neg logit contributions
 She-0.077
 she-0.076
 day-0.075
 like-0.072
 sometimes-0.067
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
itched+0.260
 tal+0.248
eg+0.246
orse+0.233
izza+0.231
Neg logit contributions
 she-0.133
 day-0.132
 She-0.131
 like-0.116
 her-0.116
Token pond
Token ID16723
Feature activation-1.35e-02

Pos logit contributions
 She+0.041
 she+0.040
 day+0.039
 always+0.036
 sometimes+0.036
Neg logit contributions
itched-0.054
 tal-0.053
eg-0.050
orse-0.046
 fin-0.046
Token and
Token ID290
Feature activation+1.31e-01

Pos logit contributions
itched+0.036
 tal+0.035
eg+0.034
izza+0.031
orse+0.031
Neg logit contributions
 day-0.017
 She-0.017
 she-0.017
 like-0.015
 sometimes-0.015
Token sw
Token ID1509
Feature activation-1.77e-01

Pos logit contributions
 she+0.225
 day+0.217
 She+0.213
 like+0.202
 sometimes+0.198
Neg logit contributions
itched-0.309
 tal-0.290
eg-0.282
izza-0.262
ades-0.261
Tokenam
Token ID321
Feature activation-4.09e-01

Pos logit contributions
 tal+0.236
izza+0.226
itched+0.226
eg+0.219
orse+0.199
Neg logit contributions
 day-0.373
 like-0.363
 She-0.361
 always-0.361
ie-0.360
Token together
Token ID1978
Feature activation-1.24e-01

Pos logit contributions
itched+0.995
 tal+0.958
eg+0.915
izza+0.861
orse+0.856
Neg logit contributions
 She-0.616
 day-0.615
 she-0.610
 like-0.556
 sometimes-0.535
Token.
Token ID13
Feature activation+1.90e-03

Pos logit contributions
itched+0.308
 tal+0.301
eg+0.298
izza+0.277
ades+0.268
Neg logit contributions
 day-0.185
 she-0.184
 She-0.175
 like-0.170
 sometimes-0.156
Token They
Token ID1119
Feature activation+1.11e-01

Pos logit contributions
 She+0.003
 she+0.003
 day+0.003
 sometimes+0.002
 like+0.002
Neg logit contributions
itched-0.005
 tal-0.005
eg-0.004
urger-0.004
ades-0.004
Token became
Token ID2627
Feature activation+3.47e-02

Pos logit contributions
 day+0.160
 she+0.159
 like+0.154
 always+0.154
 especially+0.151
Neg logit contributions
itched-0.282
 tal-0.268
eg-0.253
izza-0.247
ades-0.238
Token best
Token ID1266
Feature activation+1.31e-01

Pos logit contributions
 She+0.054
 she+0.052
 day+0.052
 sometimes+0.046
 always+0.046
Neg logit contributions
itched-0.081
 tal-0.078
eg-0.073
orse-0.070
 fin-0.068
Token.
Token ID13
Feature activation-5.19e-02

Pos logit contributions
itched+0.188
 tal+0.180
eg+0.176
izza+0.167
orse+0.162
Neg logit contributions
 day-0.122
 She-0.118
 she-0.117
 like-0.107
 sometimes-0.103
Token Together
Token ID17083
Feature activation-1.75e-01

Pos logit contributions
itched+0.122
 tal+0.117
eg+0.112
ades+0.105
 fin+0.105
Neg logit contributions
 She-0.095
 she-0.088
 day-0.080
 always-0.073
 like-0.071
Token,
Token ID11
Feature activation-4.45e-02

Pos logit contributions
itched+0.418
 tal+0.411
eg+0.390
orse+0.369
izza+0.362
Neg logit contributions
 she-0.274
 She-0.272
 day-0.271
 sometimes-0.237
 always-0.231
Token they
Token ID484
Feature activation-1.34e-02

Pos logit contributions
itched+0.111
 tal+0.108
eg+0.103
orse+0.096
izza+0.095
Neg logit contributions
 she-0.065
 She-0.064
 day-0.063
 sometimes-0.055
 like-0.055
Token sw
Token ID1509
Feature activation-2.30e-01

Pos logit contributions
itched+0.031
 tal+0.030
eg+0.027
izza+0.027
 wounds+0.025
Neg logit contributions
 day-0.023
 always-0.022
 like-0.022
 sometimes-0.022
 especially-0.022
Tokenam
Token ID321
Feature activation-4.59e-01

Pos logit contributions
 tal+0.298
itched+0.278
eg+0.277
izza+0.266
orse+0.254
Neg logit contributions
 day-0.514
 always-0.500
 She-0.482
 afternoon-0.477
ie-0.474
Token off
Token ID572
Feature activation-1.87e-01

Pos logit contributions
itched+1.177
 tal+1.134
eg+1.079
orse+1.025
izza+1.018
Neg logit contributions
 She-0.627
 day-0.625
 she-0.615
 like-0.551
 sometimes-0.538
Token to
Token ID284
Feature activation-6.54e-02

Pos logit contributions
itched+0.501
 tal+0.491
eg+0.484
urger+0.471
izza+0.468
Neg logit contributions
 day-0.254
 she-0.254
 She-0.246
 like-0.221
 her-0.207
Token the
Token ID262
Feature activation-3.12e-02

Pos logit contributions
itched+0.178
eg+0.165
 tal+0.164
izza+0.160
ades+0.159
Neg logit contributions
 day-0.093
 she-0.085
 She-0.083
 like-0.081
 always-0.078
Token sea
Token ID5417
Feature activation+2.52e-02

Pos logit contributions
itched+0.068
 tal+0.064
eg+0.059
izza+0.056
ves+0.054
Neg logit contributions
 day-0.061
 she-0.056
 She-0.054
 sometimes-0.053
 like-0.052
Token.
Token ID13
Feature activation-5.36e-02

Pos logit contributions
 day+0.032
 she+0.029
 like+0.027
 always+0.026
 sometimes+0.025
Neg logit contributions
itched-0.073
 tal-0.070
eg-0.069
plug-0.064
izza-0.064
Token their
Token ID511
Feature activation-6.47e-02

Pos logit contributions
itched+0.027
 tal+0.026
eg+0.025
orse+0.023
izza+0.023
Neg logit contributions
 She-0.021
 she-0.021
 day-0.021
 like-0.019
 always-0.019
Token dad
Token ID9955
Feature activation-1.94e-01

Pos logit contributions
itched+0.140
 tal+0.130
eg+0.124
ves+0.116
orse+0.116
Neg logit contributions
 day-0.127
 she-0.112
 She-0.109
 summer-0.106
 morning-0.103
Token.
Token ID13
Feature activation-8.06e-03

Pos logit contributions
itched+0.436
 tal+0.418
eg+0.393
orse+0.371
izza+0.362
Neg logit contributions
 She-0.324
 day-0.323
 she-0.318
 like-0.289
 sometimes-0.286
Token They
Token ID1119
Feature activation+1.07e-01

Pos logit contributions
itched+0.020
 tal+0.019
eg+0.018
orse+0.017
izza+0.017
Neg logit contributions
 she-0.011
 day-0.011
 She-0.010
 always-0.009
my-0.009
Token have
Token ID423
Feature activation+1.05e-01

Pos logit contributions
 She+0.125
 she+0.118
 day+0.111
 weekend+0.103
 week+0.101
Neg logit contributions
itched-0.270
 tal-0.264
orse-0.258
eg-0.257
 fin-0.249
Token rods
Token ID32858
Feature activation-4.86e-01

Pos logit contributions
 day+0.173
 She+0.167
 she+0.167
 always+0.157
 like+0.154
Neg logit contributions
itched-0.248
 tal-0.233
eg-0.226
izza-0.208
orse-0.205
Token and
Token ID290
Feature activation+1.22e-01

Pos logit contributions
itched+1.245
 tal+1.213
eg+1.144
orse+1.085
izza+1.059
Neg logit contributions
 day-0.650
 She-0.647
 she-0.643
 like-0.588
 sometimes-0.569
Token hooks
Token ID26569
Feature activation-3.76e-01

Pos logit contributions
 She+0.256
 day+0.255
 she+0.255
 like+0.236
 sometimes+0.235
Neg logit contributions
itched-0.221
 tal-0.206
eg-0.192
orse-0.175
izza-0.172
Token and
Token ID290
Feature activation+1.20e-01

Pos logit contributions
itched+0.984
 tal+0.973
eg+0.930
orse+0.867
urger+0.857
Neg logit contributions
 day-0.498
 she-0.496
 like-0.494
 She-0.475
 sometimes-0.461
Token worms
Token ID29174
Feature activation-5.09e-02

Pos logit contributions
 day+0.234
 she+0.233
 She+0.230
 like+0.221
 sometimes+0.217
Neg logit contributions
itched-0.244
 tal-0.224
eg-0.212
ades-0.192
orse-0.191
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
itched+0.124
 tal+0.122
eg+0.117
izza+0.108
orse+0.108
Neg logit contributions
 she-0.076
 She-0.074
 day-0.074
 like-0.069
 sometimes-0.067