TOP ACTIVATIONS
MAX = 8.625

not play with the ash tr ay . It is dangerous
not played with the ash tr ay . They wish they
mean to break the ash tr ay . They did not
the top of the ash tr ay fell off . Bill
did you touch my ash tr ay ? Do you know
" And ash tr ays are not hats ,"
The poor ash tr ay was broken and it
She saw the broken ash tr ay and the mess on
they also see an ash tr ay on the table .
should never touch an ash tr ay ." S
looked at the empty ash tr ay on Sara 's head
not played with the ash tr ay . They wished they
They took off the ash tr ay and the book .
, Lily found an ash tr ay in the world behind
room and saw an ash tr ay . She remembered her
backyard there was an ash tr ay . It was the
He picks up the ash tr ay and shakes it .
around town on his ash tr ay , z ipping everywhere
, he saw an ash tr ay on the table .
tried to fix the ash tr ay , but it was

MIN ACTIVATIONS
MIN = -9.543

too and he was taken aback by how attractive her wings
The little boy was taken aback and felt guilty . He
The man was so taken aback by Maria 's charming request
the entrance and was taken aback by how beautiful the enchanted
His mom was taken aback . She said calmly ,
the little girl was taken aback . Inside the room ,
The small boy was taken aback . He thanked the saw
Jane , a little taken aback , thought for a moment
The bear was so taken aback by such kindness it gave
touched !" Lily was taken aback and stopped in her tracks
." B uster felt so proud and hum
. B uster thought for a moment .
. B uster looked and saw a small
the forest looking for all sorts of exciting things . She
so much fun . K ait lyn was so happy to
so happy to see K ait lyn with a smile on
, thrilled to discover all sorts of new things .
they both were out of breath . B
match her moves with her breath . One day , while
things . They met all kinds of animals , from tiny

INTERVAL 4.083 - 8.625
CONTAINS 0.494%

moral of their story : Just because something is difficult ,
in his garden . The angel was very pretty and had
and buy a bright purple je ep . It was so
's face . He was smiling and holding something in his
of the trees . The giant had long hair and long

INTERVAL -0.459 - 4.083
CONTAINS 71.118%

snow house . Even when the weather was cold , they
the bed , she hopped on the sofa , she hopped
was important . He learned that day that if you make
and whispers in their ears . He says the secret is
, using his reversing powers to help out . He was

INTERVAL -5.001 - -0.459
CONTAINS 28.288%

a time , there was a little girl named Lily .
and started to cry . Lily felt bad but she still
Lily said , rubbing her belly . Sam felt
yellow scarf was soft and warm . His mom gave it
is not scared of the dog . He walks to the

INTERVAL -9.543 - -5.001
CONTAINS 0.100%

with him . Then an idea came to him . He
desk , and a wet spot on the rug . Who
, but Jamie had an idea . He said
to put it on . First , her mom helped her
Suddenly , Molly had an idea . She went inside her
Token not
Token ID407
Feature activation+1.05e+00

Pos logit contributions
 ost+0.092
ric+0.087
 highlight+0.084
work+0.083
 peac+0.083
Neg logit contributions
iddled-0.128
 aback-0.117
ocated-0.112
uster-0.112
bench-0.109
Token play
Token ID711
Feature activation-7.10e-03

Pos logit contributions
 ost+0.065
ric+0.062
 highlight+0.061
 ostr+0.059
 End+0.058
Neg logit contributions
iddled-0.057
 aback-0.052
ocated-0.047
zip-0.047
uster-0.046
Token with
Token ID351
Feature activation-4.59e-01

Pos logit contributions
iddled+0.000
uster+0.000
 aback+0.000
bench+0.000
wn+0.000
Neg logit contributions
 ost-0.000
ric-0.000
 ostr-0.000
 zoo-0.000
 rob-0.000
Token the
Token ID262
Feature activation+7.73e-01

Pos logit contributions
iddled+0.027
 aback+0.023
uster+0.022
 tant+0.021
ocated+0.021
Neg logit contributions
 ost-0.029
ric-0.028
 peac-0.026
 ostr-0.026
work-0.026
Token ash
Token ID12530
Feature activation+6.48e+00

Pos logit contributions
orse+0.048
 highlight+0.048
work+0.047
ric+0.047
riage+0.045
Neg logit contributions
 tant-0.034
iddled-0.031
 aback-0.029
 cloth-0.029
 scissors-0.029
Tokentr
Token ID2213
Feature activation+8.62e+00

Pos logit contributions
 ost+0.269
ric+0.254
 peac+0.238
 highlight+0.238
 ostr+0.226
Neg logit contributions
iddled-0.497
 aback-0.454
 tant-0.435
uster-0.433
ocated-0.425
Tokenay
Token ID323
Feature activation-1.82e+00

Pos logit contributions
ric+0.637
work+0.617
 ost+0.608
 ostr+0.571
 peac+0.570
Neg logit contributions
iddled-0.396
 aback-0.335
uster-0.313
ocated-0.282
bench-0.281
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
iddled+0.101
 aback+0.087
uster+0.084
bench+0.076
 tant+0.076
Neg logit contributions
 ost-0.119
ric-0.116
 ostr-0.111
work-0.110
 peac-0.109
Token It
Token ID632
Feature activation-8.27e-01

Pos logit contributions
 ost+0.010
ric+0.009
 highlight+0.009
 ostr+0.009
 peac+0.009
Neg logit contributions
iddled-0.008
 aback-0.007
uster-0.006
ocated-0.006
 tant-0.006
Token is
Token ID318
Feature activation-8.00e-03

Pos logit contributions
iddled+0.046
 aback+0.042
ocated+0.038
 tant+0.038
sc+0.036
Neg logit contributions
 ost-0.049
ric-0.049
 highlight-0.048
 peac-0.047
 End-0.045
Token dangerous
Token ID4923
Feature activation+1.89e-01

Pos logit contributions
iddled+0.000
 aback+0.000
ocated+0.000
wn+0.000
bench+0.000
Neg logit contributions
 ost-0.000
ric-0.000
 peac-0.000
work-0.000
 highlight-0.000
Token not
Token ID407
Feature activation+8.20e-01

Pos logit contributions
ric+0.170
 ost+0.169
 peac+0.157
 ostr+0.155
work+0.150
Neg logit contributions
iddled-0.230
 aback-0.206
ocated-0.191
bench-0.190
uster-0.189
Token played
Token ID2826
Feature activation-5.10e-01

Pos logit contributions
ric+0.051
 ost+0.050
 peac+0.046
 ostr+0.046
 flaming+0.046
Neg logit contributions
iddled-0.045
 aback-0.041
wn-0.037
bench-0.036
 tant-0.036
Token with
Token ID351
Feature activation-5.73e-01

Pos logit contributions
iddled+0.033
 aback+0.028
uster+0.028
bench+0.025
 tant+0.025
Neg logit contributions
 ost-0.029
work-0.027
ric-0.027
 zoo-0.026
 moral-0.026
Token the
Token ID262
Feature activation+5.21e-01

Pos logit contributions
iddled+0.025
 aback+0.021
 tant+0.020
uster+0.019
ocated+0.017
Neg logit contributions
ric-0.041
 peac-0.040
 ost-0.040
 moral-0.039
 highlight-0.039
Token ash
Token ID12530
Feature activation+6.38e+00

Pos logit contributions
ric+0.034
 ost+0.032
 peac+0.031
orse+0.030
work+0.029
Neg logit contributions
iddled-0.027
 tant-0.025
 aback-0.024
bench-0.023
uster-0.023
Tokentr
Token ID2213
Feature activation+8.58e+00

Pos logit contributions
 ost+0.421
ric+0.417
 peac+0.394
 highlight+0.393
 rob+0.384
Neg logit contributions
iddled-0.320
 aback-0.284
 tant-0.274
bench-0.264
uster-0.260
Tokenay
Token ID323
Feature activation-1.96e+00

Pos logit contributions
ric+0.632
work+0.626
 ost+0.604
 peac+0.568
 ostr+0.565
Neg logit contributions
iddled-0.382
 aback-0.321
uster-0.296
ocated-0.277
bench-0.270
Token.
Token ID13
Feature activation+3.81e-02

Pos logit contributions
iddled+0.094
 aback+0.077
 tant+0.072
uster+0.071
bench+0.071
Neg logit contributions
 ost-0.142
ric-0.138
 peac-0.138
 highlight-0.134
 ostr-0.133
Token They
Token ID1119
Feature activation-1.89e-01

Pos logit contributions
 ost+0.003
ric+0.003
 ostr+0.003
 peac+0.003
 rob+0.003
Neg logit contributions
iddled-0.002
 aback-0.002
uster-0.001
bench-0.001
 tant-0.001
Token wish
Token ID4601
Feature activation-1.15e-02

Pos logit contributions
iddled+0.012
 aback+0.011
 tant+0.010
bench+0.010
ocated+0.010
Neg logit contributions
 ost-0.010
ric-0.010
work-0.010
 peac-0.009
 flaming-0.009
Token they
Token ID484
Feature activation+8.35e-01

Pos logit contributions
iddled+0.001
bench+0.000
ows+0.000
fully+0.000
uster+0.000
Neg logit contributions
ric-0.001
 highlight-0.001
 rob-0.001
 ost-0.001
 ostr-0.001
Token mean
Token ID1612
Feature activation+3.16e+00

Pos logit contributions
 ost+0.046
ric+0.042
 ostr+0.042
 peac+0.042
 moral+0.040
Neg logit contributions
iddled-0.069
uster-0.059
 aback-0.059
ocated-0.056
 tant-0.055
Token to
Token ID284
Feature activation+8.49e-02

Pos logit contributions
 ost+0.170
ric+0.155
 ostr+0.151
 peac+0.145
 moral+0.143
Neg logit contributions
iddled-0.225
uster-0.192
 aback-0.187
bench-0.181
ocated-0.174
Token break
Token ID2270
Feature activation-1.62e+00

Pos logit contributions
 ost+0.004
ric+0.004
 ostr+0.004
 peac+0.004
 rob+0.004
Neg logit contributions
iddled-0.006
 aback-0.006
uster-0.005
bench-0.005
wn-0.005
Token the
Token ID262
Feature activation+6.09e-01

Pos logit contributions
iddled+0.103
 aback+0.089
uster+0.086
bench+0.082
ocated+0.080
Neg logit contributions
 ost-0.098
ric-0.093
 ostr-0.089
 peac-0.087
work-0.086
Token ash
Token ID12530
Feature activation+6.44e+00

Pos logit contributions
 highlight+0.031
ric+0.031
 ost+0.030
orse+0.029
work+0.028
Neg logit contributions
iddled-0.037
 tant-0.034
 aback-0.034
bench-0.032
ocated-0.032
Tokentr
Token ID2213
Feature activation+8.55e+00

Pos logit contributions
 ost+0.187
ric+0.173
 ostr+0.155
 peac+0.155
work+0.145
Neg logit contributions
iddled-0.592
 aback-0.542
uster-0.527
 tant-0.508
bench-0.507
Tokenay
Token ID323
Feature activation-1.89e+00

Pos logit contributions
ric+0.603
work+0.585
 ost+0.565
 je+0.537
 ostr+0.531
Neg logit contributions
iddled-0.410
 aback-0.359
uster-0.330
bench-0.301
ocated-0.298
Token.
Token ID13
Feature activation+7.99e-02

Pos logit contributions
iddled+0.116
 aback+0.101
uster+0.097
 tant+0.090
ocated+0.089
Neg logit contributions
 ost-0.113
ric-0.109
 ostr-0.104
work-0.104
 peac-0.103
Token They
Token ID1119
Feature activation-5.72e-02

Pos logit contributions
 ost+0.005
ric+0.005
 ostr+0.005
 peac+0.005
work+0.004
Neg logit contributions
iddled-0.005
 aback-0.004
uster-0.004
 tant-0.004
bench-0.004
Token did
Token ID750
Feature activation+3.56e-01

Pos logit contributions
iddled+0.004
 aback+0.004
uster+0.004
bench+0.003
ocated+0.003
Neg logit contributions
 ost-0.003
 ostr-0.003
ric-0.003
 peac-0.003
 moral-0.003
Token not
Token ID407
Feature activation+9.08e-01

Pos logit contributions
 ost+0.020
 peac+0.018
 ostr+0.018
ric+0.018
 rob+0.017
Neg logit contributions
iddled-0.023
 aback-0.021
ocated-0.020
 tant-0.020
bench-0.019
Token the
Token ID262
Feature activation+5.03e-01

Pos logit contributions
iddled+0.004
 aback+0.004
 tant+0.003
ocated+0.003
uster+0.003
Neg logit contributions
ric-0.006
 ost-0.006
 highlight-0.006
work-0.006
oral-0.006
Token top
Token ID1353
Feature activation+4.43e+00

Pos logit contributions
ric+0.032
 highlight+0.030
orse+0.030
riage+0.029
 ost+0.029
Neg logit contributions
 tant-0.021
 cloth-0.020
iddled-0.019
 aback-0.019
 scissors-0.019
Token of
Token ID286
Feature activation+8.54e-01

Pos logit contributions
 ost+0.285
ric+0.283
 highlight+0.261
 peac+0.261
 ostr+0.258
Neg logit contributions
iddled-0.253
 aback-0.211
uster-0.202
bench-0.199
 tant-0.199
Token the
Token ID262
Feature activation+5.00e-01

Pos logit contributions
 ost+0.061
ric+0.059
 highlight+0.059
work+0.058
 peac+0.058
Neg logit contributions
iddled-0.039
 aback-0.033
uster-0.029
 tant-0.026
bench-0.026
Token ash
Token ID12530
Feature activation+6.39e+00

Pos logit contributions
ric+0.032
orse+0.029
 highlight+0.029
 ost+0.029
riage+0.029
Neg logit contributions
 tant-0.023
 cloth-0.020
 away-0.019
 aback-0.019
iddled-0.019
Tokentr
Token ID2213
Feature activation+8.54e+00

Pos logit contributions
 ost+0.233
ric+0.214
 peac+0.203
 highlight+0.200
 moral+0.197
Neg logit contributions
iddled-0.533
 aback-0.481
uster-0.463
bench-0.460
 tant-0.455
Tokenay
Token ID323
Feature activation-1.93e+00

Pos logit contributions
ric+0.615
work+0.595
 ost+0.587
 ostr+0.555
 peac+0.552
Neg logit contributions
iddled-0.380
 aback-0.335
uster-0.314
bench-0.287
ocated-0.284
Token fell
Token ID3214
Feature activation+9.45e-02

Pos logit contributions
iddled+0.106
 aback+0.089
uster+0.085
bench+0.080
ocated+0.079
Neg logit contributions
 ost-0.130
ric-0.126
 peac-0.120
 highlight-0.119
 moral-0.118
Token off
Token ID572
Feature activation-1.05e+00

Pos logit contributions
 ost+0.006
ric+0.006
work+0.006
 ostr+0.005
 peac+0.005
Neg logit contributions
iddled-0.005
 aback-0.004
uster-0.004
 tant-0.004
bench-0.004
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
iddled+0.062
 aback+0.054
uster+0.052
 tant+0.048
bench+0.048
Neg logit contributions
 ost-0.065
ric-0.062
 ostr-0.060
 peac-0.059
work-0.058
Token Bill
Token ID3941
Feature activation+7.47e-01

Pos logit contributions
 highlight+0.017
work+0.017
 ost+0.017
 wedding+0.016
 flaming+0.016
Neg logit contributions
iddled-0.013
 aback-0.013
uster-0.010
bench-0.010
ocated-0.009
Token did
Token ID750
Feature activation+3.67e-01

Pos logit contributions
 ost+0.172
ric+0.163
 ostr+0.159
 peac+0.159
work+0.153
Neg logit contributions
iddled-0.151
 aback-0.128
uster-0.120
 tant-0.118
ocated-0.115
Token you
Token ID345
Feature activation+2.49e+00

Pos logit contributions
ric+0.024
 ost+0.024
 highlight+0.023
 ostr+0.023
work+0.023
Neg logit contributions
iddled-0.018
 aback-0.015
ocated-0.015
 tant-0.014
uster-0.014
Token touch
Token ID3638
Feature activation+1.61e+00

Pos logit contributions
 ost+0.152
ric+0.145
 ostr+0.139
 peac+0.138
work+0.135
Neg logit contributions
iddled-0.151
 aback-0.132
uster-0.126
 tant-0.119
ocated-0.118
Token my
Token ID616
Feature activation+5.72e-01

Pos logit contributions
 ost+0.103
ric+0.099
 ostr+0.095
 peac+0.094
work+0.092
Neg logit contributions
iddled-0.093
 aback-0.081
uster-0.077
 tant-0.072
bench-0.072
Token ash
Token ID12530
Feature activation+6.41e+00

Pos logit contributions
 highlight+0.032
 ost+0.031
ric+0.030
 Whale+0.028
 peac+0.028
Neg logit contributions
iddled-0.031
 tant-0.031
 aback-0.029
 away-0.027
uster-0.026
Tokentr
Token ID2213
Feature activation+8.53e+00

Pos logit contributions
 ost+0.186
ric+0.170
 ostr+0.153
 peac+0.153
work+0.141
Neg logit contributions
iddled-0.590
 aback-0.540
uster-0.525
 tant-0.508
bench-0.505
Tokenay
Token ID323
Feature activation-1.86e+00

Pos logit contributions
ric+0.635
work+0.611
 ost+0.603
 peac+0.572
 ostr+0.568
Neg logit contributions
iddled-0.387
 aback-0.327
uster-0.307
ocated-0.279
bench-0.278
Token?
Token ID30
Feature activation+9.26e-01

Pos logit contributions
iddled+0.128
 aback+0.113
uster+0.111
 tant+0.103
ocated+0.103
Neg logit contributions
ric-0.094
 ost-0.093
work-0.092
 ostr-0.086
 peac-0.085
Token Do
Token ID2141
Feature activation+2.88e+00

Pos logit contributions
 ost+0.067
 highlight+0.065
 ostr+0.063
ric+0.062
 peac+0.062
Neg logit contributions
iddled-0.046
 aback-0.038
uster-0.036
ocated-0.033
zip-0.032
Token you
Token ID345
Feature activation+2.50e+00

Pos logit contributions
 ost+0.180
ric+0.176
work+0.175
 highlight+0.175
 North+0.174
Neg logit contributions
iddled-0.143
ocated-0.120
 aback-0.114
 tant-0.112
olls-0.109
Token know
Token ID760
Feature activation-7.90e-01

Pos logit contributions
 ost+0.153
ric+0.145
 ostr+0.140
 peac+0.138
work+0.137
Neg logit contributions
iddled-0.152
 aback-0.134
uster-0.127
 tant-0.122
bench-0.119
Token
Token ID198
Feature activation-2.73e-01

Pos logit contributions
iddled+0.007
 aback+0.006
uster+0.006
ocated+0.006
bench+0.006
Neg logit contributions
 ost-0.005
ric-0.004
 ostr-0.004
 peac-0.004
 moral-0.004
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
iddled+0.020
 aback+0.018
uster+0.017
 tant+0.016
bench+0.016
Neg logit contributions
 ost-0.013
ric-0.013
 ostr-0.012
 peac-0.012
 moral-0.012
Token"
Token ID1
Feature activation-1.10e+00

Pos logit contributions
iddled+0.011
 aback+0.009
uster+0.009
 tant+0.008
bench+0.008
Neg logit contributions
 ost-0.015
ric-0.014
 ostr-0.014
 peac-0.014
work-0.013
TokenAnd
Token ID1870
Feature activation+1.44e+00

Pos logit contributions
iddled+0.066
 aback+0.057
uster+0.054
 tant+0.052
ocated+0.052
Neg logit contributions
ric-0.067
 ost-0.067
 ostr-0.062
 peac-0.061
work-0.061
Token ash
Token ID12530
Feature activation+6.42e+00

Pos logit contributions
ric+0.096
 ost+0.091
 peac+0.087
 flaming+0.085
 highlight+0.085
Neg logit contributions
iddled-0.072
 aback-0.070
uster-0.060
ocated-0.059
 away-0.056
Tokentr
Token ID2213
Feature activation+8.52e+00

Pos logit contributions
 ost+0.281
ric+0.266
 peac+0.251
 ostr+0.248
 highlight+0.239
Neg logit contributions
iddled-0.495
 aback-0.446
uster-0.430
 tant-0.412
bench-0.411
Tokenays
Token ID592
Feature activation-7.60e-01

Pos logit contributions
ric+0.594
work+0.578
 ost+0.562
 peac+0.516
 ostr+0.516
Neg logit contributions
iddled-0.399
 aback-0.354
bench-0.335
uster-0.333
ocated-0.311
Token are
Token ID389
Feature activation+2.16e-01

Pos logit contributions
iddled+0.047
 aback+0.040
uster+0.040
ocated+0.037
bench+0.037
Neg logit contributions
 ost-0.045
ric-0.043
 ostr-0.042
 peac-0.041
 moral-0.040
Token not
Token ID407
Feature activation+9.00e-01

Pos logit contributions
ric+0.013
 ost+0.013
 peac+0.012
 ostr+0.012
work+0.012
Neg logit contributions
iddled-0.012
 aback-0.011
uster-0.010
 tant-0.010
ocated-0.010
Token hats
Token ID23910
Feature activation-2.32e+00

Pos logit contributions
 ost+0.056
ric+0.054
 ostr+0.052
 peac+0.051
work+0.050
Neg logit contributions
iddled-0.054
 aback-0.047
uster-0.045
 tant-0.042
bench-0.041
Token,"
Token ID553
Feature activation+6.74e-01

Pos logit contributions
iddled+0.133
 aback+0.115
uster+0.110
 tant+0.103
bench+0.102
Neg logit contributions
 ost-0.148
ric-0.143
 ostr-0.137
 peac-0.136
work-0.133
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
 ost+0.019
 highlight+0.019
work+0.019
 peac+0.019
 ostr+0.018
Neg logit contributions
iddled-0.010
 aback-0.010
bench-0.008
uster-0.007
ocated-0.007
Token
Token ID198
Feature activation-8.49e-02

Pos logit contributions
iddled+0.008
 aback+0.007
uster+0.007
bench+0.007
ocated+0.006
Neg logit contributions
 ost-0.009
work-0.009
 highlight-0.009
ric-0.009
 ostr-0.009
TokenThe
Token ID464
Feature activation+2.91e+00

Pos logit contributions
iddled+0.003
 aback+0.003
uster+0.003
bench+0.002
zip+0.002
Neg logit contributions
work-0.007
ric-0.007
 wedding-0.006
 highlight-0.006
 ost-0.006
Token poor
Token ID3595
Feature activation+1.18e+00

Pos logit contributions
ric+0.203
work+0.176
 highlight+0.169
 Clown+0.166
field+0.165
Neg logit contributions
 cloth-0.107
 tant-0.106
 mess-0.099
 breath-0.097
 scissors-0.095
Token ash
Token ID12530
Feature activation+6.38e+00

Pos logit contributions
ric+0.080
 highlight+0.079
work+0.070
riage+0.065
 happiest+0.065
Neg logit contributions
iddled-0.049
 cloth-0.047
 tant-0.047
ly-0.045
 aback-0.044
Tokentr
Token ID2213
Feature activation+8.49e+00

Pos logit contributions
 ost+0.285
ric+0.275
 highlight+0.258
 peac+0.243
 North+0.237
Neg logit contributions
iddled-0.475
 aback-0.429
bench-0.409
ocated-0.403
 tant-0.401
Tokenay
Token ID323
Feature activation-1.93e+00

Pos logit contributions
ric+0.622
work+0.608
 ost+0.603
 peac+0.574
 ostr+0.570
Neg logit contributions
iddled-0.360
 aback-0.313
uster-0.296
bench-0.276
ocated-0.263
Token was
Token ID373
Feature activation+3.73e-01

Pos logit contributions
iddled+0.127
 aback+0.106
uster+0.098
ocated+0.097
bench+0.094
Neg logit contributions
 ost-0.112
ric-0.110
 highlight-0.107
 peac-0.102
 North-0.099
Token broken
Token ID5445
Feature activation+9.59e-01

Pos logit contributions
 ost+0.021
ric+0.020
 ostr+0.019
 peac+0.019
work+0.018
Neg logit contributions
iddled-0.025
 aback-0.022
uster-0.021
bench-0.020
 tant-0.020
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
 ost+0.050
ric+0.048
work+0.048
 ostr+0.046
 peac+0.045
Neg logit contributions
iddled-0.064
 aback-0.055
uster-0.054
 tant-0.052
wn-0.050
Token it
Token ID340
Feature activation-9.07e-01

Pos logit contributions
ric+0.001
 ost+0.001
 flaming+0.001
 highlight+0.001
work+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
 tant-0.001
bench-0.001
ocated-0.001
Token She
Token ID1375
Feature activation+2.00e-01

Pos logit contributions
 ost+0.005
ric+0.005
 ostr+0.005
 peac+0.005
 moral+0.005
Neg logit contributions
iddled-0.005
uster-0.004
 aback-0.004
 tant-0.004
wn-0.004
Token saw
Token ID2497
Feature activation+4.51e-01

Pos logit contributions
 ost+0.009
 ostr+0.008
ric+0.008
 peac+0.008
 moral+0.008
Neg logit contributions
iddled-0.015
uster-0.014
 aback-0.013
 tant-0.013
bench-0.013
Token the
Token ID262
Feature activation+6.27e-01

Pos logit contributions
 ost+0.027
ric+0.026
 ostr+0.025
 peac+0.025
work+0.024
Neg logit contributions
iddled-0.028
 aback-0.024
uster-0.024
bench-0.022
 tant-0.022
Token broken
Token ID5445
Feature activation+1.02e+00

Pos logit contributions
ric+0.046
 highlight+0.046
 ost+0.046
riage+0.045
orse+0.045
Neg logit contributions
 tant-0.023
iddled-0.021
 aback-0.019
bench-0.016
ocated-0.016
Token ash
Token ID12530
Feature activation+6.40e+00

Pos logit contributions
 ost+0.054
 highlight+0.054
ric+0.053
 happiest+0.047
 North+0.047
Neg logit contributions
iddled-0.064
 aback-0.057
 tant-0.056
bench-0.053
uster-0.052
Tokentr
Token ID2213
Feature activation+8.49e+00

Pos logit contributions
 ost+0.243
ric+0.227
 peac+0.213
 ostr+0.209
 highlight+0.202
Neg logit contributions
iddled-0.530
 aback-0.480
uster-0.464
bench-0.450
 tant-0.450
Tokenay
Token ID323
Feature activation-1.93e+00

Pos logit contributions
ric+0.590
work+0.575
 ost+0.546
 je+0.521
 peac+0.512
Neg logit contributions
iddled-0.399
 aback-0.362
uster-0.329
bench-0.307
wn-0.302
Token and
Token ID290
Feature activation+9.56e-04

Pos logit contributions
iddled+0.106
 aback+0.091
uster+0.086
 tant+0.080
bench+0.080
Neg logit contributions
 ost-0.129
ric-0.124
 ostr-0.119
 peac-0.119
work-0.116
Token the
Token ID262
Feature activation+5.65e-01

Pos logit contributions
 ost+0.000
ric+0.000
 ostr+0.000
 peac+0.000
work+0.000
Neg logit contributions
iddled-0.000
 aback-0.000
uster-0.000
 tant-0.000
bench-0.000
Token mess
Token ID2085
Feature activation-3.38e+00

Pos logit contributions
 highlight+0.036
 ost+0.035
ric+0.035
orse+0.035
riage+0.034
Neg logit contributions
 tant-0.027
iddled-0.024
 aback-0.023
bench-0.022
 away-0.020
Token on
Token ID319
Feature activation+1.05e+00

Pos logit contributions
iddled+0.226
 aback+0.211
uster+0.200
 tant+0.190
wn+0.180
Neg logit contributions
 ost-0.169
ric-0.163
work-0.163
 ostr-0.151
 moral-0.149
Token they
Token ID484
Feature activation+8.12e-01

Pos logit contributions
ric+0.003
oral+0.003
 North+0.003
 rob+0.003
str+0.003
Neg logit contributions
iddled-0.002
 socks-0.002
 away-0.001
 her-0.001
inn-0.001
Token also
Token ID635
Feature activation+3.09e+00

Pos logit contributions
 ost+0.041
ric+0.039
 peac+0.038
work+0.037
 ostr+0.036
Neg logit contributions
iddled-0.056
 aback-0.050
uster-0.047
 tant-0.047
bench-0.047
Token see
Token ID766
Feature activation-1.37e-01

Pos logit contributions
 ost+0.211
ric+0.204
 peac+0.198
 ostr+0.194
work+0.193
Neg logit contributions
iddled-0.160
 aback-0.142
bench-0.129
 tant-0.127
uster-0.125
Token an
Token ID281
Feature activation-3.02e-01

Pos logit contributions
iddled+0.006
 aback+0.005
 tant+0.004
uster+0.004
bench+0.004
Neg logit contributions
ric-0.010
 ost-0.010
 highlight-0.009
str-0.009
 peac-0.009
Token ash
Token ID12530
Feature activation+6.33e+00

Pos logit contributions
iddled+0.020
 aback+0.018
uster+0.017
 tant+0.017
bench+0.017
Neg logit contributions
 ost-0.016
ric-0.016
 peac-0.015
 ostr-0.014
 highlight-0.014
Tokentr
Token ID2213
Feature activation+8.47e+00

Pos logit contributions
 ost+0.223
ric+0.209
 highlight+0.198
 peac+0.195
 moral+0.188
Neg logit contributions
iddled-0.526
 aback-0.466
uster-0.457
bench-0.457
ocated-0.448
Tokenay
Token ID323
Feature activation-1.99e+00

Pos logit contributions
work+0.574
ric+0.556
 ost+0.509
 je+0.486
 chim+0.481
Neg logit contributions
iddled-0.418
 aback-0.382
uster-0.360
ocated-0.330
wn-0.327
Token on
Token ID319
Feature activation+1.02e+00

Pos logit contributions
iddled+0.109
 aback+0.091
uster+0.088
bench+0.083
ocated+0.082
Neg logit contributions
 ost-0.133
ric-0.130
 peac-0.124
 ostr-0.123
 highlight-0.121
Token the
Token ID262
Feature activation+3.69e-01

Pos logit contributions
 ost+0.057
ric+0.055
 ostr+0.052
work+0.051
 peac+0.051
Neg logit contributions
iddled-0.069
 aback-0.061
uster-0.059
ocated-0.055
 tant-0.054
Token table
Token ID3084
Feature activation-2.14e+00

Pos logit contributions
 ost+0.025
ric+0.024
 peac+0.023
 rob+0.022
 highlight+0.022
Neg logit contributions
iddled-0.019
 aback-0.016
uster-0.016
bench-0.015
 tant-0.015
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
iddled+0.125
 aback+0.107
uster+0.102
bench+0.097
 tant+0.096
Neg logit contributions
 ost-0.135
ric-0.130
 peac-0.125
 ostr-0.125
work-0.121
Token should
Token ID815
Feature activation+1.75e+00

Pos logit contributions
 ost+0.163
ric+0.156
 highlight+0.153
 peac+0.151
 ostr+0.151
Neg logit contributions
iddled-0.148
 aback-0.138
uster-0.125
 tant-0.123
ocated-0.121
Token never
Token ID1239
Feature activation+1.80e+00

Pos logit contributions
 ost+0.096
 highlight+0.092
work+0.092
ric+0.089
 peac+0.089
Neg logit contributions
iddled-0.098
 aback-0.090
uster-0.087
ocated-0.086
bench-0.086
Token touch
Token ID3638
Feature activation+1.49e+00

Pos logit contributions
 ost+0.128
ric+0.119
 End+0.118
 highlight+0.118
work+0.117
Neg logit contributions
iddled-0.074
 aback-0.067
 tant-0.063
wn-0.063
zip-0.062
Token an
Token ID281
Feature activation-1.15e-01

Pos logit contributions
 ost+0.104
ric+0.102
 highlight+0.099
 ostr+0.099
 peac+0.099
Neg logit contributions
iddled-0.069
 aback-0.062
uster-0.055
 tant-0.055
ocated-0.049
Token ash
Token ID12530
Feature activation+6.38e+00

Pos logit contributions
iddled+0.008
 aback+0.007
uster+0.007
 tant+0.007
bench+0.007
Neg logit contributions
 ost-0.005
ric-0.005
 highlight-0.005
 peac-0.005
work-0.005
Tokentr
Token ID2213
Feature activation+8.45e+00

Pos logit contributions
 ost+0.224
ric+0.208
 peac+0.190
 ostr+0.186
 highlight+0.186
Neg logit contributions
iddled-0.540
 aback-0.495
uster-0.481
 tant-0.468
ocated-0.463
Tokenay
Token ID323
Feature activation-1.91e+00

Pos logit contributions
ric+0.618
work+0.605
 ost+0.585
 peac+0.558
 ostr+0.551
Neg logit contributions
iddled-0.391
 aback-0.324
uster-0.306
bench-0.282
ocated-0.280
Token."
Token ID526
Feature activation-1.36e-01

Pos logit contributions
iddled+0.112
 aback+0.098
uster+0.093
 tant+0.088
bench+0.087
Neg logit contributions
 ost-0.120
ric-0.116
 ostr-0.110
 peac-0.110
 highlight-0.107
Token
Token ID198
Feature activation-2.71e-01

Pos logit contributions
iddled+0.010
 aback+0.009
uster+0.008
 tant+0.008
bench+0.008
Neg logit contributions
 ost-0.007
ric-0.006
 ostr-0.006
 peac-0.006
 moral-0.006
Token
Token ID198
Feature activation-2.19e-01

Pos logit contributions
iddled+0.021
 aback+0.018
uster+0.018
 tant+0.017
ocated+0.017
Neg logit contributions
 ost-0.013
ric-0.012
 ostr-0.011
 peac-0.011
 moral-0.011
TokenS
Token ID50
Feature activation+1.96e+00

Pos logit contributions
iddled+0.012
 aback+0.010
uster+0.010
 tant+0.009
bench+0.009
Neg logit contributions
 ost-0.015
ric-0.014
 ostr-0.014
 peac-0.014
 moral-0.014
Token looked
Token ID3114
Feature activation+1.49e+00

Pos logit contributions
 ost+0.042
ric+0.039
 ostr+0.038
 peac+0.038
work+0.037
Neg logit contributions
iddled-0.052
 aback-0.047
uster-0.046
 tant-0.044
bench-0.043
Token at
Token ID379
Feature activation+1.34e+00

Pos logit contributions
 ost+0.080
 ostr+0.074
 moral+0.074
ric+0.069
 hipp+0.068
Neg logit contributions
iddled-0.093
ocated-0.087
uster-0.085
bench-0.083
 aback-0.079
Token the
Token ID262
Feature activation+6.26e-01

Pos logit contributions
 ost+0.090
ric+0.087
 ostr+0.084
 peac+0.082
work+0.081
Neg logit contributions
iddled-0.076
 aback-0.064
uster-0.061
bench-0.058
ocated-0.058
Token empty
Token ID6565
Feature activation-1.08e-01

Pos logit contributions
 ost+0.037
ric+0.035
 peac+0.034
 ostr+0.033
 highlight+0.032
Neg logit contributions
iddled-0.039
 aback-0.035
 tant-0.033
uster-0.033
bench-0.032
Token ash
Token ID12530
Feature activation+6.45e+00

Pos logit contributions
iddled+0.008
 aback+0.007
uster+0.007
 tant+0.006
bench+0.006
Neg logit contributions
 ost-0.005
ric-0.005
 ostr-0.005
 peac-0.005
work-0.005
Tokentr
Token ID2213
Feature activation+8.45e+00

Pos logit contributions
 ost+0.251
ric+0.233
 peac+0.220
 highlight+0.219
 ostr+0.211
Neg logit contributions
iddled-0.522
 aback-0.470
bench-0.454
uster-0.454
 tant-0.446
Tokenay
Token ID323
Feature activation-1.88e+00

Pos logit contributions
ric+0.596
work+0.589
 ost+0.553
 je+0.527
 peac+0.523
Neg logit contributions
iddled-0.386
 aback-0.346
uster-0.324
ocated-0.300
wn-0.293
Token on
Token ID319
Feature activation+1.07e+00

Pos logit contributions
iddled+0.093
 aback+0.078
uster+0.073
bench+0.072
 tant+0.068
Neg logit contributions
 ost-0.135
ric-0.131
 peac-0.128
 highlight-0.125
 rob-0.125
Token Sara
Token ID24799
Feature activation-3.55e-01

Pos logit contributions
 ost+0.054
 ostr+0.050
 zoo+0.049
ric+0.049
 moral+0.047
Neg logit contributions
iddled-0.080
 aback-0.068
uster-0.068
wn-0.064
iddling-0.064
Token's
Token ID338
Feature activation+2.51e+00

Pos logit contributions
iddled+0.024
 aback+0.021
uster+0.021
bench+0.020
ocated+0.019
Neg logit contributions
 ost-0.019
ric-0.018
 peac-0.017
 ostr-0.017
 highlight-0.017
Token head
Token ID1182
Feature activation-1.56e+00

Pos logit contributions
 ost+0.155
ric+0.147
 peac+0.141
 highlight+0.141
work+0.138
Neg logit contributions
iddled-0.146
 aback-0.129
uster-0.125
 tant-0.122
bench-0.119
Token not
Token ID407
Feature activation+8.69e-01

Pos logit contributions
 ost+0.157
ric+0.152
 ostr+0.142
 peac+0.141
work+0.137
Neg logit contributions
iddled-0.250
 aback-0.225
uster-0.212
bench-0.207
ocated-0.207
Token played
Token ID2826
Feature activation-4.86e-01

Pos logit contributions
ric+0.055
 ost+0.055
work+0.051
 North+0.051
 ostr+0.051
Neg logit contributions
iddled-0.048
 aback-0.041
wn-0.037
ocated-0.037
bench-0.036
Token with
Token ID351
Feature activation-5.14e-01

Pos logit contributions
iddled+0.032
uster+0.028
 aback+0.028
bench+0.024
 tant+0.024
Neg logit contributions
 ost-0.028
work-0.025
ric-0.025
 zoo-0.025
 peac-0.024
Token the
Token ID262
Feature activation+5.06e-01

Pos logit contributions
iddled+0.025
 aback+0.020
 tant+0.020
uster+0.019
ocated+0.018
Neg logit contributions
 ost-0.035
ric-0.035
 peac-0.034
 highlight-0.033
 ostr-0.033
Token ash
Token ID12530
Feature activation+6.39e+00

Pos logit contributions
ric+0.029
 highlight+0.028
orse+0.028
work+0.027
 ost+0.027
Neg logit contributions
iddled-0.026
 tant-0.025
 aback-0.024
bench-0.022
ocated-0.021
Tokentr
Token ID2213
Feature activation+8.45e+00

Pos logit contributions
 ost+0.238
ric+0.225
 highlight+0.208
 peac+0.207
 rob+0.197
Neg logit contributions
iddled-0.517
 aback-0.477
 tant-0.455
uster-0.454
bench-0.452
Tokenay
Token ID323
Feature activation-1.98e+00

Pos logit contributions
ric+0.625
work+0.608
 ost+0.600
 peac+0.568
 ostr+0.563
Neg logit contributions
iddled-0.380
 aback-0.321
uster-0.298
ocated-0.271
bench-0.267
Token.
Token ID13
Feature activation-1.74e-02

Pos logit contributions
iddled+0.107
 aback+0.091
uster+0.086
 tant+0.083
bench+0.082
Neg logit contributions
 ost-0.133
ric-0.128
 peac-0.126
 ostr-0.124
 highlight-0.122
Token They
Token ID1119
Feature activation-1.25e-01

Pos logit contributions
iddled+0.001
 aback+0.001
uster+0.001
 tant+0.001
bench+0.001
Neg logit contributions
 ost-0.001
ric-0.001
 ostr-0.001
 peac-0.001
work-0.001
Token wished
Token ID16555
Feature activation-1.10e+00

Pos logit contributions
iddled+0.008
 aback+0.007
 tant+0.007
uster+0.007
bench+0.007
Neg logit contributions
 ost-0.007
ric-0.007
work-0.006
 peac-0.006
 ostr-0.006
Token they
Token ID484
Feature activation+8.63e-01

Pos logit contributions
iddled+0.039
 her+0.035
fully+0.035
 them+0.032
 him+0.030
Neg logit contributions
ric-0.081
 ostr-0.080
 ost-0.079
str-0.078
 rob-0.078
Token They
Token ID1119
Feature activation-5.93e-02

Pos logit contributions
 ost+0.020
ric+0.019
 peac+0.019
 ostr+0.018
 highlight+0.018
Neg logit contributions
iddled-0.014
 aback-0.012
uster-0.012
 tant-0.010
bench-0.010
Token took
Token ID1718
Feature activation+3.68e-01

Pos logit contributions
iddled+0.004
uster+0.004
 aback+0.004
bench+0.004
 tant+0.004
Neg logit contributions
 ost-0.003
 ostr-0.003
 peac-0.003
ric-0.003
 moral-0.003
Token off
Token ID572
Feature activation-9.57e-01

Pos logit contributions
 ost+0.020
 ostr+0.018
work+0.018
ric+0.018
 highlight+0.017
Neg logit contributions
iddled-0.025
uster-0.021
bench-0.021
 aback-0.021
ocated-0.021
Token the
Token ID262
Feature activation+6.94e-01

Pos logit contributions
iddled+0.043
 aback+0.037
 tant+0.033
uster+0.033
bench+0.030
Neg logit contributions
ric-0.072
 ost-0.069
 peac-0.066
 highlight-0.066
 ostr-0.065
Token ash
Token ID12530
Feature activation+6.39e+00

Pos logit contributions
ric+0.035
 ost+0.034
 highlight+0.033
work+0.031
 peac+0.031
Neg logit contributions
iddled-0.047
 aback-0.043
 tant-0.041
uster-0.040
bench-0.039
Tokentr
Token ID2213
Feature activation+8.44e+00

Pos logit contributions
 ost+0.158
ric+0.145
 ostr+0.132
 peac+0.127
work+0.124
Neg logit contributions
iddled-0.620
 aback-0.566
uster-0.553
bench-0.530
 tant-0.529
Tokenay
Token ID323
Feature activation-1.91e+00

Pos logit contributions
ric+0.556
work+0.549
 je+0.506
 ost+0.505
 peac+0.478
Neg logit contributions
iddled-0.409
 aback-0.360
ocated-0.335
uster-0.333
bench-0.319
Token and
Token ID290
Feature activation-8.82e-02

Pos logit contributions
iddled+0.098
 aback+0.086
uster+0.081
bench+0.076
 tant+0.075
Neg logit contributions
 ost-0.132
ric-0.127
 peac-0.124
 highlight-0.123
 ostr-0.122
Token the
Token ID262
Feature activation+6.67e-01

Pos logit contributions
iddled+0.005
 aback+0.004
uster+0.004
 tant+0.004
bench+0.004
Neg logit contributions
 ost-0.006
ric-0.006
 peac-0.006
 ostr-0.005
 highlight-0.005
Token book
Token ID1492
Feature activation+2.12e+00

Pos logit contributions
ric+0.042
 highlight+0.042
orse+0.041
work+0.041
 ost+0.040
Neg logit contributions
 tant-0.030
iddled-0.029
 cloth-0.026
 aback-0.026
bench-0.025
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
 ost+0.122
ric+0.114
 ostr+0.112
 peac+0.111
work+0.111
Neg logit contributions
iddled-0.135
 aback-0.118
uster-0.115
 tant-0.105
ocated-0.104
Token,
Token ID11
Feature activation+7.76e-02

Pos logit contributions
 ost+0.080
 ostr+0.073
 peac+0.072
ric+0.071
 moral+0.069
Neg logit contributions
iddled-0.112
 aback-0.098
uster-0.096
bench-0.094
ocated-0.089
Token Lily
Token ID20037
Feature activation-1.52e+00

Pos logit contributions
 ost+0.004
 ostr+0.004
 moral+0.004
 peac+0.004
 flaming+0.004
Neg logit contributions
iddled-0.005
 aback-0.005
uster-0.005
bench-0.004
wn-0.004
Token found
Token ID1043
Feature activation-2.45e+00

Pos logit contributions
iddled+0.101
 aback+0.089
uster+0.085
bench+0.081
ocated+0.080
Neg logit contributions
 ost-0.083
ric-0.081
 peac-0.075
 ostr-0.074
work-0.073
Token an
Token ID281
Feature activation-5.01e-01

Pos logit contributions
iddled+0.180
uster+0.159
 aback+0.155
bench+0.153
 tant+0.151
Neg logit contributions
 ost-0.119
 ostr-0.110
 peac-0.107
ric-0.105
 rob-0.104
Token ash
Token ID12530
Feature activation+6.19e+00

Pos logit contributions
iddled+0.035
 aback+0.031
uster+0.030
 tant+0.029
bench+0.029
Neg logit contributions
 ost-0.026
ric-0.024
 ostr-0.024
 peac-0.023
work-0.022
Tokentr
Token ID2213
Feature activation+8.44e+00

Pos logit contributions
 ost+0.210
ric+0.200
 peac+0.177
 highlight+0.176
 ostr+0.169
Neg logit contributions
iddled-0.528
 aback-0.477
uster-0.467
bench-0.458
 tant-0.455
Tokenay
Token ID323
Feature activation-2.13e+00

Pos logit contributions
work+0.564
ric+0.549
 ost+0.513
 je+0.497
 peac+0.494
Neg logit contributions
iddled-0.413
 aback-0.368
uster-0.337
ocated-0.317
bench-0.315
Token in
Token ID287
Feature activation+4.08e-01

Pos logit contributions
iddled+0.104
 aback+0.083
uster+0.080
bench+0.076
ocated+0.076
Neg logit contributions
 ost-0.156
ric-0.153
 peac-0.146
 highlight-0.144
 rob-0.143
Token the
Token ID262
Feature activation+3.48e-01

Pos logit contributions
 ost+0.022
 zoo+0.020
 ostr+0.020
ric+0.020
 rob+0.020
Neg logit contributions
iddled-0.029
uster-0.026
 aback-0.025
wn-0.024
 tant-0.023
Token world
Token ID995
Feature activation+9.64e-01

Pos logit contributions
ric+0.018
 ost+0.018
work+0.017
 peac+0.016
orse+0.016
Neg logit contributions
iddled-0.022
 aback-0.021
uster-0.019
 tant-0.019
bench-0.019
Token behind
Token ID2157
Feature activation+1.19e+00

Pos logit contributions
 ost+0.064
ric+0.062
 peac+0.059
 ostr+0.059
 highlight+0.058
Neg logit contributions
iddled-0.053
 aback-0.046
uster-0.042
bench-0.041
ocated-0.040
Token room
Token ID2119
Feature activation-1.97e+00

Pos logit contributions
 ost+0.017
ric+0.016
 peac+0.015
work+0.015
 flaming+0.015
Neg logit contributions
iddled-0.022
 aback-0.020
uster-0.020
 tant-0.019
ocated-0.018
Token and
Token ID290
Feature activation-2.82e-01

Pos logit contributions
iddled+0.117
 aback+0.101
uster+0.098
 tant+0.092
bench+0.090
Neg logit contributions
 ost-0.120
ric-0.115
 ostr-0.111
 peac-0.111
work-0.110
Token saw
Token ID2497
Feature activation+9.30e-02

Pos logit contributions
iddled+0.016
 aback+0.014
uster+0.012
ocated+0.012
 tant+0.012
Neg logit contributions
 ost-0.019
ric-0.018
 ostr-0.017
 peac-0.017
 flaming-0.017
Token an
Token ID281
Feature activation-4.90e-01

Pos logit contributions
 ost+0.006
ric+0.006
 peac+0.006
 ostr+0.005
work+0.005
Neg logit contributions
iddled-0.005
 aback-0.005
uster-0.004
 tant-0.004
ocated-0.004
Token ash
Token ID12530
Feature activation+6.14e+00

Pos logit contributions
iddled+0.031
 aback+0.028
uster+0.027
 tant+0.025
bench+0.025
Neg logit contributions
ric-0.027
 ost-0.027
 peac-0.025
work-0.025
 highlight-0.024
Tokentr
Token ID2213
Feature activation+8.44e+00

Pos logit contributions
 ost+0.233
ric+0.220
 peac+0.210
 highlight+0.207
 moral+0.205
Neg logit contributions
iddled-0.493
 aback-0.434
bench-0.428
uster-0.426
ocated-0.420
Tokenay
Token ID323
Feature activation-2.11e+00

Pos logit contributions
work+0.557
ric+0.555
 ost+0.504
 je+0.488
 chim+0.484
Neg logit contributions
iddled-0.409
 aback-0.360
uster-0.340
ocated-0.318
wn-0.315
Token.
Token ID13
Feature activation-7.82e-02

Pos logit contributions
iddled+0.110
 aback+0.088
uster+0.086
ocated+0.082
bench+0.080
Neg logit contributions
 ost-0.149
ric-0.144
 peac-0.142
 ostr-0.139
 rob-0.138
Token She
Token ID1375
Feature activation-1.58e-01

Pos logit contributions
iddled+0.005
 aback+0.004
 tant+0.004
bench+0.004
uster+0.004
Neg logit contributions
 ost-0.004
ric-0.004
 peac-0.004
 ostr-0.004
 moral-0.004
Token remembered
Token ID12086
Feature activation+7.66e-01

Pos logit contributions
iddled+0.010
 aback+0.008
uster+0.008
 tant+0.008
ocated+0.008
Neg logit contributions
 ost-0.009
ric-0.009
work-0.009
 peac-0.008
 highlight-0.008
Token her
Token ID607
Feature activation-1.53e+00

Pos logit contributions
ric+0.056
 ost+0.055
work+0.054
 highlight+0.053
 flaming+0.052
Neg logit contributions
iddled-0.036
 aback-0.030
uster-0.024
ocated-0.024
 tant-0.024
Token backyard
Token ID24296
Feature activation-3.38e-01

Pos logit contributions
ric+0.019
 ost+0.019
work+0.017
 peac+0.017
 flaming+0.017
Neg logit contributions
iddled-0.023
 aback-0.020
uster-0.020
 tant-0.019
bench-0.019
Token there
Token ID612
Feature activation-1.12e+00

Pos logit contributions
iddled+0.013
 aback+0.009
bench+0.008
ocated+0.007
anked+0.007
Neg logit contributions
 highlight-0.026
ric-0.026
 ost-0.026
 peac-0.025
 flaming-0.025
Token was
Token ID373
Feature activation-9.39e-02

Pos logit contributions
iddled+0.084
 aback+0.073
ocated+0.067
bench+0.066
uster+0.066
Neg logit contributions
 ost-0.053
ric-0.051
 peac-0.048
 ostr-0.046
work-0.045
Token an
Token ID281
Feature activation-6.29e-01

Pos logit contributions
iddled+0.004
 aback+0.003
ocated+0.003
bench+0.003
 tant+0.003
Neg logit contributions
ric-0.007
 ost-0.007
work-0.007
 peac-0.007
orse-0.007
Token ash
Token ID12530
Feature activation+6.10e+00

Pos logit contributions
iddled+0.034
uster+0.029
 aback+0.028
 tant+0.027
bench+0.027
Neg logit contributions
ric-0.041
work-0.034
 highlight-0.034
fly-0.033
 ost-0.033
Tokentr
Token ID2213
Feature activation+8.42e+00

Pos logit contributions
 ost+0.257
ric+0.252
 highlight+0.241
 moral+0.230
 peac+0.229
Neg logit contributions
iddled-0.443
bench-0.391
 aback-0.388
uster-0.381
 tant-0.377
Tokenay
Token ID323
Feature activation-2.18e+00

Pos logit contributions
work+0.589
ric+0.586
 ost+0.563
 peac+0.537
 ostr+0.532
Neg logit contributions
iddled-0.383
 aback-0.341
uster-0.309
ocated-0.296
 tant-0.291
Token.
Token ID13
Feature activation+1.05e-01

Pos logit contributions
iddled+0.106
uster+0.081
 aback+0.079
bench+0.078
ocated+0.075
Neg logit contributions
 ost-0.157
ric-0.156
 highlight-0.150
 rob-0.146
 peac-0.146
Token It
Token ID632
Feature activation-1.21e+00

Pos logit contributions
 ost+0.006
ric+0.006
 peac+0.006
 ostr+0.006
work+0.006
Neg logit contributions
iddled-0.007
 aback-0.006
uster-0.005
bench-0.005
ocated-0.005
Token was
Token ID373
Feature activation-8.07e-02

Pos logit contributions
iddled+0.077
 aback+0.065
bench+0.061
 tant+0.059
ocated+0.058
Neg logit contributions
 ost-0.067
ric-0.067
 highlight-0.064
 peac-0.061
work-0.060
Token the
Token ID262
Feature activation+3.07e-01

Pos logit contributions
iddled+0.005
 aback+0.005
uster+0.004
bench+0.004
 tant+0.004
Neg logit contributions
 ost-0.005
ric-0.004
 peac-0.004
 ostr-0.004
work-0.004
Token He
Token ID679
Feature activation-1.87e-01

Pos logit contributions
 ost+0.004
ric+0.004
 ostr+0.003
 peac+0.003
 flaming+0.003
Neg logit contributions
iddled-0.005
 aback-0.005
uster-0.004
 tant-0.004
ocated-0.004
Token picks
Token ID11103
Feature activation+1.14e+00

Pos logit contributions
iddled+0.012
 aback+0.011
uster+0.011
 tant+0.010
bench+0.010
Neg logit contributions
 ost-0.010
ric-0.010
 ostr-0.009
 peac-0.009
 moral-0.009
Token up
Token ID510
Feature activation+1.64e+00

Pos logit contributions
 ost+0.066
ric+0.063
 ostr+0.062
work+0.061
 rob+0.060
Neg logit contributions
iddled-0.068
uster-0.062
 aback-0.058
bench-0.057
 tant-0.057
Token the
Token ID262
Feature activation+4.87e-01

Pos logit contributions
 ost+0.082
 ostr+0.074
ric+0.074
 peac+0.074
 flaming+0.072
Neg logit contributions
iddled-0.115
uster-0.104
 aback-0.100
ocated-0.099
bench-0.095
Token ash
Token ID12530
Feature activation+6.27e+00

Pos logit contributions
 ost+0.023
ric+0.023
 highlight+0.022
 peac+0.021
work+0.021
Neg logit contributions
iddled-0.034
 aback-0.031
 tant-0.029
uster-0.028
bench-0.027
Tokentr
Token ID2213
Feature activation+8.41e+00

Pos logit contributions
 ost+0.195
ric+0.179
 peac+0.163
 ostr+0.159
 highlight+0.157
Neg logit contributions
iddled-0.563
 aback-0.516
uster-0.498
 tant-0.483
bench-0.483
Tokenay
Token ID323
Feature activation-1.98e+00

Pos logit contributions
work+0.536
ric+0.514
 je+0.454
 ost+0.448
 chim+0.435
Neg logit contributions
iddled-0.430
 aback-0.386
uster-0.369
ocated-0.358
wn-0.349
Token and
Token ID290
Feature activation-4.56e-01

Pos logit contributions
iddled+0.107
 aback+0.091
uster+0.085
bench+0.080
 tant+0.079
Neg logit contributions
 ost-0.135
ric-0.130
 peac-0.126
 ostr-0.125
 highlight-0.124
Token shakes
Token ID29959
Feature activation-1.98e+00

Pos logit contributions
iddled+0.026
 aback+0.022
uster+0.021
 tant+0.020
bench+0.020
Neg logit contributions
 ost-0.029
ric-0.028
 ostr-0.027
 peac-0.027
work-0.026
Token it
Token ID340
Feature activation-8.28e-01

Pos logit contributions
iddled+0.126
uster+0.117
 aback+0.111
ocated+0.106
bench+0.105
Neg logit contributions
ric-0.109
 ost-0.109
 ostr-0.099
 moral-0.098
 flaming-0.097
Token.
Token ID13
Feature activation-4.60e-02

Pos logit contributions
iddled+0.059
uster+0.053
 aback+0.051
 tant+0.047
ocated+0.047
Neg logit contributions
 ost-0.038
work-0.037
 moral-0.037
ric-0.035
 ostr-0.035
Token around
Token ID1088
Feature activation-2.28e+00

Pos logit contributions
 ost+0.062
 ostr+0.058
 peac+0.057
work+0.057
ric+0.057
Neg logit contributions
iddled-0.043
uster-0.036
ocated-0.034
bench-0.034
 aback-0.034
Token town
Token ID3240
Feature activation-1.19e-01

Pos logit contributions
iddled+0.116
 aback+0.103
uster+0.089
 tant+0.088
bench+0.086
Neg logit contributions
 ost-0.159
ric-0.158
 highlight-0.148
 ostr-0.147
 peac-0.146
Token on
Token ID319
Feature activation+8.72e-01

Pos logit contributions
iddled+0.005
 aback+0.004
bench+0.004
 away+0.003
uster+0.003
Neg logit contributions
 ost-0.009
ric-0.009
 highlight-0.009
 moral-0.009
 peac-0.008
Token his
Token ID465
Feature activation-1.33e+00

Pos logit contributions
 ost+0.063
ric+0.062
 ostr+0.059
 peac+0.059
 highlight+0.058
Neg logit contributions
iddled-0.041
 aback-0.037
 tant-0.032
uster-0.031
bench-0.030
Token ash
Token ID12530
Feature activation+6.27e+00

Pos logit contributions
 breath+0.054
 away+0.052
iddled+0.049
 tant+0.048
 apr+0.048
Neg logit contributions
ric-0.087
riage-0.080
 ost-0.080
 rob-0.079
oral-0.079
Tokentr
Token ID2213
Feature activation+8.41e+00

Pos logit contributions
 ost+0.250
 highlight+0.224
ric+0.222
 moral+0.221
 rob+0.214
Neg logit contributions
iddled-0.486
 aback-0.438
bench-0.427
uster-0.426
 tant-0.418
Tokenay
Token ID323
Feature activation-2.06e+00

Pos logit contributions
ric+0.604
work+0.575
 ost+0.560
 peac+0.536
 je+0.531
Neg logit contributions
iddled-0.380
 aback-0.336
uster-0.310
ocated-0.300
bench-0.289
Token,
Token ID11
Feature activation+8.99e-02

Pos logit contributions
iddled+0.096
 aback+0.079
uster+0.075
bench+0.072
 tant+0.065
Neg logit contributions
 ost-0.157
ric-0.145
 peac-0.145
 highlight-0.145
 ostr-0.144
Token z
Token ID1976
Feature activation+1.35e+00

Pos logit contributions
 ost+0.005
ric+0.005
 moral+0.005
 ostr+0.005
 peac+0.005
Neg logit contributions
iddled-0.006
 aback-0.005
uster-0.005
bench-0.004
ocated-0.004
Tokenipping
Token ID4501
Feature activation-1.18e+00

Pos logit contributions
 ost+0.092
ric+0.090
 peac+0.086
 ostr+0.085
work+0.084
Neg logit contributions
iddled-0.071
 aback-0.062
uster-0.057
bench-0.055
 tant-0.055
Token everywhere
Token ID8347
Feature activation-3.64e+00

Pos logit contributions
iddled+0.060
uster+0.050
 aback+0.049
ocated+0.046
bench+0.046
Neg logit contributions
 ost-0.082
ric-0.077
 ostr-0.077
 peac-0.076
work-0.075
Token,
Token ID11
Feature activation+9.50e-02

Pos logit contributions
 ost+0.081
 ostr+0.074
ric+0.072
 moral+0.072
 peac+0.071
Neg logit contributions
iddled-0.108
uster-0.097
 aback-0.095
 tant-0.089
ocated-0.089
Token he
Token ID339
Feature activation-2.16e-01

Pos logit contributions
 ost+0.004
 moral+0.004
 ostr+0.004
 highlight+0.004
work+0.004
Neg logit contributions
iddled-0.007
uster-0.007
 aback-0.006
ocated-0.006
bench-0.006
Token saw
Token ID2497
Feature activation+1.51e-02

Pos logit contributions
iddled+0.011
 aback+0.009
 tant+0.009
bench+0.008
ocated+0.008
Neg logit contributions
ric-0.015
 ost-0.015
work-0.014
 highlight-0.013
 peac-0.013
Token an
Token ID281
Feature activation-5.76e-01

Pos logit contributions
 ost+0.001
ric+0.001
 peac+0.001
 highlight+0.001
work+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
uster-0.001
 tant-0.001
bench-0.001
Token ash
Token ID12530
Feature activation+6.16e+00

Pos logit contributions
iddled+0.037
 aback+0.032
uster+0.032
 tant+0.030
bench+0.029
Neg logit contributions
ric-0.032
 ost-0.032
 peac-0.029
 highlight-0.029
work-0.029
Tokentr
Token ID2213
Feature activation+8.41e+00

Pos logit contributions
 ost+0.237
ric+0.225
 highlight+0.214
 peac+0.208
 moral+0.204
Neg logit contributions
iddled-0.485
 aback-0.424
bench-0.422
uster-0.416
 tant-0.411
Tokenay
Token ID323
Feature activation-2.13e+00

Pos logit contributions
work+0.560
ric+0.554
 ost+0.511
 je+0.496
 peac+0.485
Neg logit contributions
iddled-0.409
 aback-0.371
uster-0.341
ocated-0.318
wn-0.314
Token on
Token ID319
Feature activation+7.74e-01

Pos logit contributions
iddled+0.105
 aback+0.082
uster+0.080
bench+0.077
ocated+0.077
Neg logit contributions
 ost-0.154
ric-0.152
 peac-0.144
 highlight-0.144
 rob-0.142
Token the
Token ID262
Feature activation+3.42e-01

Pos logit contributions
 ost+0.042
ric+0.041
 ostr+0.040
 peac+0.038
 zoo+0.038
Neg logit contributions
iddled-0.053
 aback-0.046
uster-0.045
ocated-0.042
bench-0.042
Token table
Token ID3084
Feature activation-2.11e+00

Pos logit contributions
ric+0.021
 ost+0.021
 peac+0.020
orse+0.020
work+0.019
Neg logit contributions
iddled-0.016
uster-0.015
 aback-0.015
bench-0.015
ocated-0.014
Token.
Token ID13
Feature activation+4.98e-02

Pos logit contributions
iddled+0.115
 aback+0.097
uster+0.092
bench+0.091
 tant+0.087
Neg logit contributions
 ost-0.141
ric-0.136
 peac-0.131
 ostr-0.130
 rob-0.126
Token tried
Token ID3088
Feature activation-1.68e+00

Pos logit contributions
iddled+0.001
 aback+0.001
uster+0.001
 tant+0.001
ocated+0.001
Neg logit contributions
 ost-0.001
ric-0.001
work-0.001
 highlight-0.001
 peac-0.001
Token to
Token ID284
Feature activation-7.82e-02

Pos logit contributions
iddled+0.081
 aback+0.074
uster+0.062
 tant+0.061
bench+0.059
Neg logit contributions
 ost-0.124
ric-0.118
 ostr-0.118
 peac-0.115
work-0.112
Token fix
Token ID4259
Feature activation-4.39e-01

Pos logit contributions
iddled+0.005
 aback+0.005
uster+0.005
bench+0.005
 tant+0.004
Neg logit contributions
 ost-0.004
ric-0.004
 ostr-0.004
 rob-0.004
 moral-0.004
Token the
Token ID262
Feature activation+4.67e-01

Pos logit contributions
iddled+0.026
uster+0.022
 aback+0.022
bench+0.020
 tant+0.020
Neg logit contributions
 ost-0.028
ric-0.027
 ostr-0.026
 peac-0.025
 flaming-0.024
Token ash
Token ID12530
Feature activation+6.29e+00

Pos logit contributions
ric+0.027
 highlight+0.027
orse+0.027
 Whale+0.026
 ost+0.026
Neg logit contributions
iddled-0.023
 aback-0.023
 tant-0.022
ocated-0.021
 away-0.021
Tokentr
Token ID2213
Feature activation+8.41e+00

Pos logit contributions
 ost+0.190
ric+0.174
 peac+0.159
 ostr+0.157
 highlight+0.148
Neg logit contributions
iddled-0.570
 aback-0.524
uster-0.507
 tant-0.490
bench-0.489
Tokenay
Token ID323
Feature activation-2.03e+00

Pos logit contributions
ric+0.608
work+0.580
 ost+0.573
 peac+0.539
 ostr+0.539
Neg logit contributions
iddled-0.385
 aback-0.326
uster-0.307
bench-0.282
ocated-0.277
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
iddled+0.117
 aback+0.102
uster+0.096
 tant+0.090
bench+0.090
Neg logit contributions
 ost-0.131
ric-0.125
 peac-0.121
 ostr-0.120
 highlight-0.117
Token but
Token ID475
Feature activation-1.40e+00

Pos logit contributions
 ost+0.014
ric+0.014
 ostr+0.013
 peac+0.013
work+0.013
Neg logit contributions
iddled-0.008
 aback-0.007
uster-0.006
 tant-0.006
bench-0.006
Token it
Token ID340
Feature activation-9.38e-01

Pos logit contributions
iddled+0.047
 aback+0.040
ocated+0.031
 away+0.028
uster+0.027
Neg logit contributions
ric-0.118
 ost-0.117
 flaming-0.113
 peac-0.112
 zoo-0.111
Token was
Token ID373
Feature activation+3.83e-01

Pos logit contributions
iddled+0.061
 aback+0.055
ocated+0.050
 tant+0.049
uster+0.049
Neg logit contributions
 ost-0.053
ric-0.051
 peac-0.048
 zoo-0.047
 highlight-0.047
Token too
Token ID1165
Feature activation-7.67e-02

Pos logit contributions
 ost+0.128
ric+0.123
riage+0.121
 highlight+0.120
 North+0.119
Neg logit contributions
iddled-0.048
 aback-0.043
 away-0.040
ly-0.031
acks-0.031
Token and
Token ID290
Feature activation-9.36e-02

Pos logit contributions
iddled+0.003
 aback+0.003
uster+0.003
bench+0.002
 tant+0.002
Neg logit contributions
 ost-0.006
ric-0.006
 highlight-0.005
work-0.005
 peac-0.005
Token he
Token ID339
Feature activation-2.45e-01

Pos logit contributions
iddled+0.005
 aback+0.004
 tant+0.004
uster+0.004
ocated+0.003
Neg logit contributions
ric-0.006
 ost-0.006
 highlight-0.006
work-0.006
 North-0.006
Token was
Token ID373
Feature activation-1.12e-01

Pos logit contributions
iddled+0.014
 aback+0.012
 tant+0.010
uster+0.010
zip+0.010
Neg logit contributions
 ost-0.016
ric-0.016
 highlight-0.015
work-0.015
 zoo-0.015
Token taken
Token ID2077
Feature activation-1.74e+00

Pos logit contributions
iddled+0.006
 aback+0.005
uster+0.004
bench+0.004
 tant+0.004
Neg logit contributions
 ost-0.007
ric-0.007
work-0.007
oral-0.007
 peac-0.007
Token aback
Token ID50147
Feature activation-8.41e+00

Pos logit contributions
iddled+0.104
uster+0.088
bench+0.085
ocated+0.081
 tant+0.077
Neg logit contributions
 ost-0.103
 rob-0.097
 ostr-0.096
 peac-0.096
 moral-0.094
Token by
Token ID416
Feature activation+9.84e-01

Pos logit contributions
iddled+0.492
 aback+0.424
uster+0.406
 tant+0.379
bench+0.379
Neg logit contributions
 ost-0.532
ric-0.512
 ostr-0.491
 peac-0.488
work-0.476
Token how
Token ID703
Feature activation-1.75e+00

Pos logit contributions
 ost+0.075
 highlight+0.074
oral+0.072
str+0.070
work+0.070
Neg logit contributions
iddled-0.037
 aback-0.032
 tant-0.025
uster-0.025
 breath-0.024
Token attractive
Token ID10966
Feature activation+9.47e-01

Pos logit contributions
iddled+0.101
 aback+0.090
uster+0.078
 tant+0.078
bench+0.076
Neg logit contributions
ric-0.112
 ost-0.112
work-0.105
 ostr-0.104
 peac-0.104
Token her
Token ID607
Feature activation-1.85e+00

Pos logit contributions
ric+0.072
 ost+0.071
work+0.067
 peac+0.067
 highlight+0.066
Neg logit contributions
iddled-0.042
 aback-0.035
uster-0.031
 tant-0.029
bench-0.028
Token wings
Token ID12098
Feature activation-2.00e+00

Pos logit contributions
iddled+0.064
 aback+0.059
 knot+0.056
 breath+0.055
 away+0.053
Neg logit contributions
ric-0.137
 ost-0.136
 highlight-0.125
 zoo-0.124
 North-0.123
Token The
Token ID383
Feature activation+2.32e+00

Pos logit contributions
iddled+0.000
 aback+0.000
uster+0.000
 tant+0.000
ocated+0.000
Neg logit contributions
 ost-0.000
 peac-0.000
work-0.000
ric-0.000
 ostr-0.000
Token little
Token ID1310
Feature activation-7.49e-02

Pos logit contributions
ric+0.186
 ost+0.178
work+0.159
 peac+0.159
fly+0.155
Neg logit contributions
 tant-0.092
iddled-0.084
 aback-0.078
uster-0.076
ly-0.072
Token boy
Token ID2933
Feature activation-8.92e-01

Pos logit contributions
iddled+0.004
 aback+0.004
uster+0.004
 tant+0.004
bench+0.003
Neg logit contributions
ric-0.005
 ost-0.005
 peac-0.004
 highlight-0.004
work-0.004
Token was
Token ID373
Feature activation+2.04e-01

Pos logit contributions
iddled+0.041
 aback+0.039
 away+0.034
 tant+0.033
 shoved+0.032
Neg logit contributions
ric-0.064
 ost-0.063
 highlight-0.061
 peac-0.057
 North-0.057
Token taken
Token ID2077
Feature activation-1.76e+00

Pos logit contributions
 ost+0.013
ric+0.013
 peac+0.013
 ostr+0.013
work+0.013
Neg logit contributions
iddled-0.011
 aback-0.010
 away-0.008
 tant-0.008
bench-0.008
Token aback
Token ID50147
Feature activation-8.25e+00

Pos logit contributions
iddled+0.084
uster+0.068
bench+0.066
ocated+0.065
iddling+0.058
Neg logit contributions
 ost-0.116
 rob-0.110
 moral-0.110
 ostr-0.109
 happiest-0.108
Token and
Token ID290
Feature activation-1.70e-01

Pos logit contributions
iddled+0.472
 aback+0.402
uster+0.386
bench+0.361
 tant+0.359
Neg logit contributions
 ost-0.534
ric-0.514
 ostr-0.495
 peac-0.489
work-0.478
Token felt
Token ID2936
Feature activation-3.51e-01

Pos logit contributions
iddled+0.009
 aback+0.009
 tant+0.007
uster+0.007
ocated+0.007
Neg logit contributions
ric-0.012
 ost-0.011
 peac-0.010
 highlight-0.010
work-0.010
Token guilty
Token ID6717
Feature activation-1.48e-02

Pos logit contributions
iddled+0.023
 aback+0.022
uster+0.020
 tant+0.019
bench+0.019
Neg logit contributions
 ost-0.019
ric-0.019
 ostr-0.018
 peac-0.018
work-0.017
Token.
Token ID13
Feature activation+5.53e-02

Pos logit contributions
iddled+0.001
 aback+0.001
uster+0.001
 tant+0.001
bench+0.001
Neg logit contributions
 ost-0.001
ric-0.001
 ostr-0.001
 peac-0.001
work-0.001
Token He
Token ID679
Feature activation-6.85e-02

Pos logit contributions
 ost+0.004
 peac+0.004
ric+0.004
work+0.004
 ostr+0.004
Neg logit contributions
iddled-0.003
 aback-0.003
uster-0.002
 tant-0.002
bench-0.002
TokenThe
Token ID464
Feature activation+2.62e+00

Pos logit contributions
iddled+0.021
 aback+0.018
uster+0.016
bench+0.015
ocated+0.015
Neg logit contributions
 ost-0.024
ric-0.023
 ostr-0.023
work-0.022
 peac-0.021
Token man
Token ID582
Feature activation-7.05e-01

Pos logit contributions
ric+0.209
 ost+0.179
fly+0.177
work+0.175
 highlight+0.167
Neg logit contributions
iddled-0.107
bench-0.100
uster-0.092
 aback-0.088
eal-0.077
Token was
Token ID373
Feature activation+1.28e-01

Pos logit contributions
iddled+0.034
 aback+0.030
 away+0.025
led+0.024
 shoved+0.024
Neg logit contributions
ric-0.053
 ost-0.048
 highlight-0.048
 North-0.046
ich-0.044
Token so
Token ID523
Feature activation+2.30e-02

Pos logit contributions
 ost+0.008
ric+0.008
 peac+0.008
 ostr+0.008
work+0.008
Neg logit contributions
iddled-0.007
 aback-0.007
bench-0.006
uster-0.006
wn-0.005
Token taken
Token ID2077
Feature activation-1.81e+00

Pos logit contributions
ric+0.001
 ost+0.001
 peac+0.001
 ostr+0.001
 zoo+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
uster-0.001
bench-0.001
 tant-0.001
Token aback
Token ID50147
Feature activation-8.24e+00

Pos logit contributions
iddled+0.102
uster+0.088
ocated+0.084
bench+0.081
irms+0.080
Neg logit contributions
 ost-0.103
work-0.103
 rob-0.096
 ostr-0.096
 moral-0.096
Token by
Token ID416
Feature activation+1.04e+00

Pos logit contributions
iddled+0.467
 aback+0.395
uster+0.384
bench+0.357
ocated+0.356
Neg logit contributions
 ost-0.537
ric-0.515
 ostr-0.498
 peac-0.493
work-0.485
Token Maria
Token ID14200
Feature activation-4.27e-02

Pos logit contributions
 ost+0.074
ric+0.071
 highlight+0.070
 ostr+0.070
 North+0.068
Neg logit contributions
iddled-0.051
 aback-0.045
uster-0.036
fully-0.035
 tant-0.034
Token's
Token ID338
Feature activation+1.96e+00

Pos logit contributions
 aback+0.003
iddled+0.002
uster+0.002
 away+0.002
bench+0.002
Neg logit contributions
 ost-0.003
ric-0.003
 peac-0.002
 flaming-0.002
 zoo-0.002
Token charming
Token ID23332
Feature activation-4.27e-01

Pos logit contributions
ric+0.131
 ost+0.126
str+0.117
 peac+0.114
 highlight+0.113
Neg logit contributions
iddled-0.098
 aback-0.095
uster-0.087
bench-0.082
 tant-0.082
Token request
Token ID2581
Feature activation-1.03e+00

Pos logit contributions
iddled+0.026
 aback+0.023
uster+0.023
 tant+0.022
bench+0.021
Neg logit contributions
ric-0.025
 ost-0.024
 highlight-0.022
work-0.022
 peac-0.021
Token the
Token ID262
Feature activation+2.80e-01

Pos logit contributions
iddled+0.003
 aback+0.002
uster+0.002
 tant+0.002
ocated+0.002
Neg logit contributions
 ost-0.003
ric-0.003
 ostr-0.003
 peac-0.003
work-0.003
Token entrance
Token ID10384
Feature activation-3.85e-01

Pos logit contributions
ric+0.017
work+0.016
 ost+0.016
 highlight+0.016
orse+0.016
Neg logit contributions
 aback-0.015
iddled-0.014
 tant-0.012
 away-0.012
ly-0.012
Token and
Token ID290
Feature activation-3.44e-01

Pos logit contributions
iddled+0.019
 aback+0.017
uster+0.015
ocated+0.014
bench+0.014
Neg logit contributions
 ost-0.027
ric-0.027
 peac-0.025
 ostr-0.025
 flaming-0.025
Token was
Token ID373
Feature activation+2.05e-02

Pos logit contributions
iddled+0.020
 aback+0.018
uster+0.016
ocated+0.015
 tant+0.015
Neg logit contributions
 ost-0.022
ric-0.022
 ostr-0.020
 peac-0.020
 moral-0.020
Token taken
Token ID2077
Feature activation-1.86e+00

Pos logit contributions
 ost+0.001
ric+0.001
 peac+0.001
 ostr+0.001
work+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
uster-0.001
ocated-0.001
bench-0.001
Token aback
Token ID50147
Feature activation-8.24e+00

Pos logit contributions
iddled+0.115
bench+0.106
uster+0.104
 tant+0.101
arl+0.098
Neg logit contributions
 ost-0.097
 rob-0.089
 guardian-0.087
 ostr-0.085
 peac-0.085
Token by
Token ID416
Feature activation+1.03e+00

Pos logit contributions
iddled+0.443
 aback+0.394
uster+0.364
 tant+0.345
ocated+0.334
Neg logit contributions
 ost-0.538
ric-0.532
 peac-0.509
 ostr-0.498
work-0.495
Token how
Token ID703
Feature activation-1.64e+00

Pos logit contributions
ric+0.077
 ost+0.076
 ostr+0.073
 highlight+0.073
work+0.073
Neg logit contributions
iddled-0.044
 aback-0.039
ocated-0.030
uster-0.030
 tant-0.028
Token beautiful
Token ID4950
Feature activation+8.59e-01

Pos logit contributions
iddled+0.087
 aback+0.076
uster+0.066
ocated+0.064
 tant+0.063
Neg logit contributions
ric-0.113
 ost-0.110
 ostr-0.104
work-0.104
 peac-0.104
Token the
Token ID262
Feature activation+2.81e-01

Pos logit contributions
ric+0.063
 ost+0.063
 peac+0.059
 ostr+0.059
work+0.059
Neg logit contributions
iddled-0.040
 aback-0.033
uster-0.029
 tant-0.027
ocated-0.027
Token enchanted
Token ID42282
Feature activation+1.19e+00

Pos logit contributions
ric+0.018
work+0.015
orse+0.014
 highlight+0.014
fly+0.014
Neg logit contributions
 aback-0.013
 breath-0.012
iddled-0.012
 piles-0.012
ly-0.012
Token
Token ID198
Feature activation-3.49e-01

Pos logit contributions
iddled+0.030
 aback+0.027
uster+0.026
ocated+0.025
 tant+0.024
Neg logit contributions
 ost-0.018
ric-0.018
 ostr-0.016
 peac-0.016
 moral-0.016
TokenHis
Token ID6653
Feature activation+7.16e-01

Pos logit contributions
iddled+0.017
 aback+0.014
uster+0.013
 tant+0.013
bench+0.012
Neg logit contributions
 ost-0.026
ric-0.025
 peac-0.024
 ostr-0.024
work-0.024
Token mom
Token ID1995
Feature activation+2.08e+00

Pos logit contributions
ric+0.050
 ost+0.048
 peac+0.044
work+0.043
 rob+0.042
Neg logit contributions
 tant-0.036
iddled-0.034
bench-0.030
 aback-0.029
uster-0.029
Token was
Token ID373
Feature activation+1.29e-01

Pos logit contributions
 ost+0.142
ric+0.140
 highlight+0.132
 peac+0.130
 North+0.129
Neg logit contributions
iddled-0.115
 aback-0.098
uster-0.087
ocated-0.085
 tant-0.084
Token taken
Token ID2077
Feature activation-1.81e+00

Pos logit contributions
 ost+0.006
ric+0.006
 ostr+0.006
 peac+0.006
work+0.006
Neg logit contributions
iddled-0.009
 aback-0.008
uster-0.008
 tant-0.008
bench-0.008
Token aback
Token ID50147
Feature activation-8.20e+00

Pos logit contributions
iddled+0.142
ows+0.125
uster+0.122
ocated+0.122
iddling+0.120
Neg logit contributions
 ost-0.060
 je-0.059
 moral-0.056
 ostr-0.055
 hipp-0.052
Token.
Token ID13
Feature activation+9.50e-02

Pos logit contributions
iddled+0.543
 aback+0.442
uster+0.432
ocated+0.429
wn+0.422
Neg logit contributions
 ost-0.482
ric-0.461
 ostr-0.449
 moral-0.414
 peac-0.411
Token She
Token ID1375
Feature activation-4.07e-02

Pos logit contributions
 ost+0.005
ric+0.005
 ostr+0.004
 zoo+0.004
 moral+0.004
Neg logit contributions
iddled-0.006
 aback-0.006
uster-0.006
 tant-0.005
wn-0.005
Token said
Token ID531
Feature activation-4.71e-02

Pos logit contributions
iddled+0.002
 aback+0.002
uster+0.002
 tant+0.002
ocated+0.002
Neg logit contributions
 ost-0.003
ric-0.003
 highlight-0.003
 peac-0.003
work-0.002
Token calmly
Token ID30180
Feature activation-7.07e-01

Pos logit contributions
iddled+0.002
 aback+0.002
uster+0.002
 tant+0.002
ocated+0.002
Neg logit contributions
 ost-0.003
ric-0.003
 peac-0.003
 highlight-0.003
 ostr-0.003
Token,
Token ID11
Feature activation-1.18e-04

Pos logit contributions
iddled+0.031
 aback+0.026
uster+0.024
bench+0.022
ocated+0.021
Neg logit contributions
 ost-0.055
ric-0.054
 highlight-0.053
 peac-0.051
 ostr-0.051
Token the
Token ID262
Feature activation+5.09e-01

Pos logit contributions
iddled+0.007
 aback+0.006
ocated+0.006
uster+0.006
 tant+0.005
Neg logit contributions
ric-0.009
 ost-0.009
 highlight-0.008
work-0.008
 ostr-0.008
Token little
Token ID1310
Feature activation+2.23e-01

Pos logit contributions
ric+0.034
 ost+0.031
orse+0.030
work+0.030
 peac+0.029
Neg logit contributions
iddled-0.026
 tant-0.024
 aback-0.023
uster-0.022
ocated-0.021
Token girl
Token ID2576
Feature activation-3.91e-01

Pos logit contributions
ric+0.013
 ost+0.013
 peac+0.012
 highlight+0.012
work+0.012
Neg logit contributions
iddled-0.013
 aback-0.012
uster-0.011
 tant-0.011
ocated-0.010
Token was
Token ID373
Feature activation+2.45e-01

Pos logit contributions
iddled+0.021
 aback+0.018
ocated+0.015
uster+0.015
 tant+0.015
Neg logit contributions
ric-0.026
 ost-0.026
 highlight-0.025
work-0.025
 moral-0.024
Token taken
Token ID2077
Feature activation-1.59e+00

Pos logit contributions
 ost+0.014
ric+0.014
 peac+0.013
 ostr+0.013
work+0.013
Neg logit contributions
iddled-0.016
 aback-0.014
uster-0.012
ocated-0.012
bench-0.012
Token aback
Token ID50147
Feature activation-8.19e+00

Pos logit contributions
iddled+0.091
uster+0.079
 tant+0.078
bench+0.076
irms+0.073
Neg logit contributions
 ost-0.086
�-0.080
 guardian-0.078
 ostr-0.077
 peac-0.076
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
iddled+0.517
 aback+0.436
uster+0.427
bench+0.406
ocated+0.401
Neg logit contributions
 ost-0.491
ric-0.463
 ostr-0.452
 peac-0.437
work-0.431
Token Inside
Token ID14384
Feature activation-2.78e+00

Pos logit contributions
 ost+0.007
ric+0.006
 ostr+0.006
 peac+0.006
work+0.006
Neg logit contributions
iddled-0.006
 aback-0.005
uster-0.005
ocated-0.004
bench-0.004
Token the
Token ID262
Feature activation+5.33e-01

Pos logit contributions
iddled+0.176
 aback+0.154
uster+0.147
 tant+0.139
bench+0.139
Neg logit contributions
 ost-0.161
ric-0.155
 ostr-0.147
 peac-0.147
work-0.143
Token room
Token ID2119
Feature activation-1.90e+00

Pos logit contributions
ric+0.042
 ost+0.038
orse+0.038
 peac+0.037
 flaming+0.036
Neg logit contributions
iddled-0.023
 aback-0.022
 tant-0.021
ocated-0.019
uster-0.019
Token,
Token ID11
Feature activation+3.49e-01

Pos logit contributions
iddled+0.110
 aback+0.095
ocated+0.084
bench+0.084
uster+0.084
Neg logit contributions
ric-0.122
 ost-0.121
 highlight-0.112
 ostr-0.111
 peac-0.111
TokenThe
Token ID464
Feature activation+2.64e+00

Pos logit contributions
iddled+0.022
 aback+0.019
uster+0.018
bench+0.017
ocated+0.017
Neg logit contributions
 ost-0.021
ric-0.021
 ostr-0.019
work-0.019
 peac-0.019
Token small
Token ID1402
Feature activation-1.45e+00

Pos logit contributions
ric+0.234
 ost+0.216
 North+0.198
 highlight+0.196
 peac+0.195
Neg logit contributions
iddled-0.074
 tant-0.069
 aback-0.066
 tug-0.059
 knot-0.058
Token boy
Token ID2933
Feature activation-8.09e-01

Pos logit contributions
iddled+0.076
 aback+0.071
 tant+0.067
bench+0.060
uster+0.059
Neg logit contributions
ric-0.101
 ost-0.097
 highlight-0.092
 peac-0.088
 North-0.087
Token was
Token ID373
Feature activation+2.69e-01

Pos logit contributions
iddled+0.040
 aback+0.038
 tant+0.030
 away+0.030
eal+0.030
Neg logit contributions
 ost-0.058
ric-0.057
 highlight-0.054
 peac-0.051
 North-0.051
Token taken
Token ID2077
Feature activation-1.68e+00

Pos logit contributions
 ost+0.018
 peac+0.017
ric+0.017
 ostr+0.017
work+0.017
Neg logit contributions
iddled-0.015
 aback-0.014
 away-0.011
bench-0.011
uster-0.010
Token aback
Token ID50147
Feature activation-8.13e+00

Pos logit contributions
iddled+0.066
uster+0.048
bench+0.045
ocated+0.045
iddling+0.040
Neg logit contributions
 ost-0.132
 rob-0.126
 ostr-0.125
 moral-0.123
work-0.123
Token.
Token ID13
Feature activation+1.09e-01

Pos logit contributions
iddled+0.436
 aback+0.376
uster+0.356
 tant+0.332
bench+0.328
Neg logit contributions
 ost-0.547
ric-0.530
 peac-0.509
 ostr-0.507
work-0.496
Token He
Token ID679
Feature activation-3.98e-02

Pos logit contributions
 ost+0.009
 peac+0.008
ric+0.008
 ostr+0.008
 flaming+0.008
Neg logit contributions
iddled-0.005
 aback-0.004
uster-0.004
bench-0.003
ocated-0.003
Token thanked
Token ID26280
Feature activation-7.15e-01

Pos logit contributions
iddled+0.002
 aback+0.002
 tant+0.002
uster+0.002
ocated+0.002
Neg logit contributions
 ost-0.003
ric-0.003
 highlight-0.002
work-0.002
 peac-0.002
Token the
Token ID262
Feature activation+3.98e-01

Pos logit contributions
iddled+0.027
 aback+0.025
uster+0.020
fully+0.018
 tant+0.018
Neg logit contributions
ric-0.056
 ost-0.056
 highlight-0.055
 ostr-0.052
str-0.052
Token saw
Token ID2497
Feature activation+7.68e-02

Pos logit contributions
ric+0.032
 ost+0.028
orse+0.026
 highlight+0.026
work+0.025
Neg logit contributions
 aback-0.016
 tant-0.014
iddled-0.013
bench-0.013
 away-0.011
TokenJane
Token ID41083
Feature activation-8.75e-04

Pos logit contributions
iddled+0.005
 aback+0.004
uster+0.004
bench+0.004
 tant+0.004
Neg logit contributions
 ost-0.007
ric-0.006
 ostr-0.006
 peac-0.006
work-0.006
Token,
Token ID11
Feature activation+4.87e-02

Pos logit contributions
iddled+0.000
 aback+0.000
 tant+0.000
led+0.000
ly+0.000
Neg logit contributions
 ost-0.000
 highlight-0.000
ric-0.000
 zoo-0.000
 North-0.000
Token a
Token ID257
Feature activation-3.29e-01

Pos logit contributions
 ost+0.003
ric+0.003
 ostr+0.003
 highlight+0.003
 peac+0.003
Neg logit contributions
iddled-0.003
 aback-0.003
uster-0.002
bench-0.002
 tant-0.002
Token little
Token ID1310
Feature activation+5.19e-02

Pos logit contributions
iddled+0.017
 aback+0.016
 tant+0.016
uster+0.015
bench+0.014
Neg logit contributions
ric-0.022
 ost-0.021
 highlight-0.019
work-0.019
riage-0.019
Token taken
Token ID2077
Feature activation-1.69e+00

Pos logit contributions
ric+0.003
 ost+0.003
 highlight+0.003
 moral+0.003
 North+0.003
Neg logit contributions
iddled-0.003
 aback-0.003
uster-0.003
 tant-0.003
bench-0.003
Token aback
Token ID50147
Feature activation-8.12e+00

Pos logit contributions
iddled+0.088
uster+0.075
ocated+0.072
bench+0.069
irms+0.068
Neg logit contributions
 ost-0.107
work-0.102
 rob-0.100
 peac-0.099
 ostr-0.099
Token,
Token ID11
Feature activation+2.74e-01

Pos logit contributions
iddled+0.452
 aback+0.392
uster+0.371
 tant+0.347
bench+0.345
Neg logit contributions
 ost-0.532
ric-0.516
 peac-0.493
 ostr-0.491
work-0.480
Token thought
Token ID1807
Feature activation+4.54e-01

Pos logit contributions
ric+0.020
 ost+0.020
work+0.019
 flaming+0.018
 ostr+0.018
Neg logit contributions
iddled-0.013
 aback-0.012
uster-0.010
bench-0.010
 tant-0.009
Token for
Token ID329
Feature activation-1.00e+00

Pos logit contributions
 ost+0.029
ric+0.028
 ostr+0.027
 peac+0.027
work+0.026
Neg logit contributions
iddled-0.026
 aback-0.022
uster-0.021
 tant-0.020
bench-0.020
Token a
Token ID257
Feature activation-3.61e-01

Pos logit contributions
iddled+0.059
 aback+0.051
uster+0.048
bench+0.045
ocated+0.045
Neg logit contributions
 ost-0.063
ric-0.061
 ostr-0.058
 peac-0.058
work-0.056
Token moment
Token ID2589
Feature activation+2.04e+00

Pos logit contributions
 aback+0.018
iddled+0.017
 tant+0.017
uster+0.016
bench+0.015
Neg logit contributions
ric-0.025
 ost-0.024
work-0.021
 North-0.021
 highlight-0.021
Token The
Token ID383
Feature activation+2.50e+00

Pos logit contributions
 ost+0.012
ric+0.011
 peac+0.011
 ostr+0.011
 highlight+0.011
Neg logit contributions
iddled-0.007
 aback-0.007
uster-0.006
bench-0.005
acks-0.005
Token bear
Token ID6842
Feature activation+4.33e-01

Pos logit contributions
ric+0.180
 ost+0.172
work+0.166
 highlight+0.162
str+0.156
Neg logit contributions
iddled-0.101
 aback-0.092
uster-0.089
 tant-0.083
 knot-0.080
Token was
Token ID373
Feature activation+1.54e-01

Pos logit contributions
ric+0.032
 highlight+0.030
 ost+0.030
riage+0.028
 North+0.028
Neg logit contributions
iddled-0.020
 aback-0.017
led-0.015
 away-0.014
 tant-0.014
Token so
Token ID523
Feature activation+9.55e-03

Pos logit contributions
 ost+0.009
ric+0.009
work+0.009
 peac+0.009
 ostr+0.009
Neg logit contributions
iddled-0.009
 aback-0.008
uster-0.007
bench-0.007
wn-0.007
Token taken
Token ID2077
Feature activation-1.67e+00

Pos logit contributions
ric+0.001
 ost+0.001
work+0.001
 peac+0.001
 highlight+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
 tant-0.000
uster-0.000
bench-0.000
Token aback
Token ID50147
Feature activation-8.07e+00

Pos logit contributions
iddled+0.083
uster+0.064
bench+0.062
ocated+0.060
iddling+0.059
Neg logit contributions
 ost-0.109
 ostr-0.105
 moral-0.104
 rob-0.104
work-0.102
Token by
Token ID416
Feature activation+1.09e+00

Pos logit contributions
iddled+0.456
 aback+0.380
uster+0.370
bench+0.345
ocated+0.345
Neg logit contributions
 ost-0.533
ric-0.510
 ostr-0.496
 peac-0.486
work-0.479
Token such
Token ID884
Feature activation-1.87e+00

Pos logit contributions
 ost+0.077
 highlight+0.072
ric+0.072
 peac+0.071
 ostr+0.071
Neg logit contributions
iddled-0.052
 aback-0.047
uster-0.041
 tant-0.038
ocated-0.036
Token kindness
Token ID23887
Feature activation+1.02e+00

Pos logit contributions
iddled+0.113
 aback+0.100
uster+0.094
 tant+0.089
bench+0.088
Neg logit contributions
 ost-0.115
ric-0.112
 peac-0.105
 ostr-0.105
work-0.104
Token it
Token ID340
Feature activation-1.21e+00

Pos logit contributions
 ost+0.069
ric+0.067
 peac+0.064
 ostr+0.064
 flaming+0.062
Neg logit contributions
iddled-0.054
 aback-0.048
uster-0.045
 tant-0.041
bench-0.041
Token gave
Token ID2921
Feature activation+2.64e-01

Pos logit contributions
iddled+0.066
 aback+0.062
uster+0.053
bench+0.052
ocated+0.051
Neg logit contributions
 ost-0.079
ric-0.079
 peac-0.074
 flaming-0.072
 ostr-0.072
Token touched
Token ID12615
Feature activation+3.43e-01

Pos logit contributions
 ost+0.056
ric+0.054
 ostr+0.051
 peac+0.051
work+0.050
Neg logit contributions
iddled-0.058
 aback-0.051
uster-0.049
 tant-0.046
bench-0.046
Token!"
Token ID2474
Feature activation-6.97e-01

Pos logit contributions
ric+0.025
 ost+0.024
 highlight+0.024
 peac+0.024
 ostr+0.023
Neg logit contributions
iddled-0.015
 aback-0.014
uster-0.012
 tant-0.012
ocated-0.011
Token Lily
Token ID20037
Feature activation-1.33e+00

Pos logit contributions
iddled+0.044
 aback+0.039
uster+0.036
 tant+0.035
bench+0.034
Neg logit contributions
 ost-0.042
ric-0.041
 ostr-0.038
 peac-0.038
 highlight-0.037
Token was
Token ID373
Feature activation+3.33e-01

Pos logit contributions
iddled+0.082
 aback+0.075
uster+0.063
 tant+0.062
ocated+0.060
Neg logit contributions
 ost-0.083
ric-0.079
 highlight-0.077
 zoo-0.075
 peac-0.075
Token taken
Token ID2077
Feature activation-1.57e+00

Pos logit contributions
 ost+0.020
ric+0.020
 peac+0.019
 ostr+0.019
work+0.019
Neg logit contributions
iddled-0.020
 aback-0.018
uster-0.016
ocated-0.015
bench-0.015
Token aback
Token ID50147
Feature activation-8.06e+00

Pos logit contributions
iddled+0.076
bench+0.065
oons+0.062
uster+0.061
resses+0.055
Neg logit contributions
 ost-0.097
 guardian-0.093
 rob-0.093
�-0.092
 moral-0.092
Token and
Token ID290
Feature activation-9.99e-02

Pos logit contributions
iddled+0.498
 aback+0.411
uster+0.402
bench+0.386
ocated+0.383
Neg logit contributions
 ost-0.499
ric-0.470
 ostr-0.463
 peac-0.445
 moral-0.437
Token stopped
Token ID5025
Feature activation+1.68e+00

Pos logit contributions
iddled+0.006
 aback+0.005
uster+0.005
ocated+0.005
 tant+0.005
Neg logit contributions
 ost-0.006
ric-0.006
 ostr-0.006
 peac-0.006
 highlight-0.005
Token in
Token ID287
Feature activation+5.74e-01

Pos logit contributions
 highlight+0.106
 ost+0.102
ric+0.099
 moral+0.099
work+0.099
Neg logit contributions
iddled-0.093
 aback-0.086
uster-0.070
 away-0.069
iddling-0.067
Token her
Token ID607
Feature activation-1.40e+00

Pos logit contributions
 ost+0.030
 peac+0.028
ric+0.027
 moral+0.027
 ostr+0.027
Neg logit contributions
iddled-0.040
uster-0.034
 aback-0.033
ocated-0.032
wn-0.032
Token tracks
Token ID8339
Feature activation-6.28e-01

Pos logit contributions
 aback+0.058
 tant+0.057
iddled+0.057
 breath+0.055
 away+0.051
Neg logit contributions
 ost-0.099
ric-0.096
 peac-0.090
 flaming-0.089
 highlight-0.088
Token."
Token ID526
Feature activation+1.12e-01

Pos logit contributions
iddled+0.091
 aback+0.078
 tant+0.068
bench+0.067
uster+0.065
Neg logit contributions
 ost-0.142
ric-0.134
 ostr-0.131
 peac-0.129
 North-0.125
Token
Token ID220
Feature activation+2.37e-01

Pos logit contributions
 ost+0.008
ric+0.008
 highlight+0.008
work+0.007
 peac+0.007
Neg logit contributions
iddled-0.005
 aback-0.005
 tant-0.004
uster-0.004
bench-0.004
Token
Token ID198
Feature activation-6.81e-01

Pos logit contributions
 ost+0.012
ric+0.012
 ostr+0.011
 peac+0.011
work+0.011
Neg logit contributions
iddled-0.017
 aback-0.015
uster-0.014
 tant-0.013
bench-0.013
Token
Token ID198
Feature activation-5.31e-01

Pos logit contributions
iddled+0.044
 aback+0.039
uster+0.037
bench+0.035
 tant+0.035
Neg logit contributions
 ost-0.039
ric-0.037
 ostr-0.036
 peac-0.036
work-0.036
TokenB
Token ID33
Feature activation-3.13e+00

Pos logit contributions
iddled+0.026
 aback+0.021
uster+0.020
bench+0.018
 tant+0.018
Neg logit contributions
 ost-0.040
ric-0.039
 ostr-0.037
work-0.037
 peac-0.036
Tokenuster
Token ID5819
Feature activation-8.03e+00

Pos logit contributions
iddled+0.153
 aback+0.131
uster+0.127
ocated+0.109
 tant+0.109
Neg logit contributions
 ost-0.236
ric-0.223
 ostr-0.215
 peac-0.214
 flaming-0.212
Token felt
Token ID2936
Feature activation-5.76e-01

Pos logit contributions
iddled+0.456
 aback+0.386
uster+0.335
 tant+0.328
bench+0.316
Neg logit contributions
 ost-0.528
ric-0.513
 highlight-0.505
 peac-0.489
 North-0.482
Token so
Token ID523
Feature activation-2.63e-01

Pos logit contributions
iddled+0.038
 aback+0.034
uster+0.031
 tant+0.031
bench+0.030
Neg logit contributions
 ost-0.033
ric-0.032
 peac-0.030
 ostr-0.030
work-0.029
Token proud
Token ID6613
Feature activation+1.71e-01

Pos logit contributions
iddled+0.017
 aback+0.016
uster+0.014
 tant+0.014
bench+0.014
Neg logit contributions
 ost-0.015
ric-0.015
 peac-0.014
work-0.014
 ostr-0.014
Token and
Token ID290
Feature activation-3.00e-01

Pos logit contributions
 ost+0.011
ric+0.011
 ostr+0.010
 peac+0.010
 highlight+0.010
Neg logit contributions
iddled-0.010
 aback-0.009
uster-0.008
 tant-0.008
bench-0.008
Token hum
Token ID1311
Feature activation-2.41e-01

Pos logit contributions
iddled+0.017
 aback+0.015
bench+0.013
 tant+0.012
ocated+0.012
Neg logit contributions
ric-0.021
 ost-0.019
work-0.018
 flaming-0.017
 zoo-0.017
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
iddled+0.024
 aback+0.021
uster+0.020
 tant+0.019
bench+0.019
Neg logit contributions
 ost-0.023
ric-0.022
 ostr-0.021
 peac-0.021
work-0.021
Token
Token ID220
Feature activation+9.90e-01

Pos logit contributions
 ost+0.001
ric+0.001
 peac+0.001
 ostr+0.001
work+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
uster-0.001
 tant-0.001
bench-0.001
Token
Token ID198
Feature activation-3.98e-01

Pos logit contributions
 ost+0.043
ric+0.041
 ostr+0.037
 moral+0.037
 peac+0.037
Neg logit contributions
iddled-0.076
 aback-0.067
uster-0.065
 tant-0.064
wn-0.063
Token
Token ID198
Feature activation-3.59e-01

Pos logit contributions
iddled+0.030
 aback+0.027
uster+0.026
 tant+0.025
bench+0.025
Neg logit contributions
 ost-0.018
ric-0.017
 peac-0.016
 ostr-0.016
 moral-0.016
TokenB
Token ID33
Feature activation-3.16e+00

Pos logit contributions
iddled+0.018
 aback+0.015
uster+0.014
 tant+0.014
bench+0.014
Neg logit contributions
 ost-0.025
ric-0.024
 peac-0.024
 ostr-0.023
 moral-0.023
Tokenuster
Token ID5819
Feature activation-7.81e+00

Pos logit contributions
iddled+0.154
bench+0.136
 tant+0.133
 aback+0.119
 apr+0.116
Neg logit contributions
ric-0.210
ich-0.186
work-0.186
 ost-0.186
 je-0.184
Token thought
Token ID1807
Feature activation+3.49e-01

Pos logit contributions
iddled+0.391
 aback+0.332
uster+0.290
eal+0.262
 tant+0.257
Neg logit contributions
 ost-0.554
 highlight-0.542
ric-0.541
 North-0.511
 peac-0.502
Token for
Token ID329
Feature activation-1.04e+00

Pos logit contributions
 ost+0.021
ric+0.020
 ostr+0.019
 peac+0.019
 moral+0.019
Neg logit contributions
iddled-0.021
 aback-0.019
uster-0.017
 tant-0.017
bench-0.017
Token a
Token ID257
Feature activation-3.96e-01

Pos logit contributions
iddled+0.069
 aback+0.060
uster+0.059
 tant+0.057
bench+0.055
Neg logit contributions
 ost-0.058
ric-0.055
 peac-0.052
 ostr-0.052
work-0.052
Token moment
Token ID2589
Feature activation+1.92e+00

Pos logit contributions
iddled+0.023
 aback+0.023
uster+0.021
 tant+0.021
bench+0.020
Neg logit contributions
ric-0.024
 ost-0.023
work-0.021
 ostr-0.019
 North-0.019
Token.
Token ID13
Feature activation+3.75e-02

Pos logit contributions
 ost+0.137
ric+0.135
 peac+0.127
 ostr+0.127
 rob+0.125
Neg logit contributions
iddled-0.095
 aback-0.083
uster-0.077
bench-0.073
 tant-0.070
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
iddled+0.027
 aback+0.023
 tant+0.023
uster+0.022
bench+0.022
Neg logit contributions
 ost-0.023
ric-0.022
 ostr-0.021
 peac-0.021
 moral-0.020
Token
Token ID220
Feature activation+9.67e-01

Pos logit contributions
 ost+0.006
ric+0.006
 peac+0.006
 ostr+0.006
work+0.006
Neg logit contributions
iddled-0.010
 aback-0.009
 tant-0.009
uster-0.009
bench-0.009
Token
Token ID198
Feature activation-3.48e-01

Pos logit contributions
 ost+0.043
ric+0.041
 ostr+0.037
 peac+0.037
 moral+0.036
Neg logit contributions
iddled-0.073
 aback-0.065
uster-0.063
 tant-0.062
bench-0.060
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
iddled+0.029
 tant+0.025
 aback+0.025
wn+0.024
uster+0.024
Neg logit contributions
 ost-0.013
ric-0.012
 moral-0.011
 peac-0.011
 ostr-0.011
TokenB
Token ID33
Feature activation-3.15e+00

Pos logit contributions
iddled+0.020
 tant+0.017
 aback+0.016
bench+0.016
wn+0.016
Neg logit contributions
 ost-0.018
 peac-0.017
 moral-0.016
str-0.016
 ostr-0.016
Tokenuster
Token ID5819
Feature activation-7.79e+00

Pos logit contributions
iddled+0.164
 tant+0.137
bench+0.137
 aback+0.126
ags+0.119
Neg logit contributions
ric-0.204
 ost-0.193
work-0.186
 peac-0.186
 ostr-0.183
Token looked
Token ID3114
Feature activation+1.03e+00

Pos logit contributions
iddled+0.384
 aback+0.319
uster+0.281
 away+0.252
ly+0.251
Neg logit contributions
 highlight-0.564
 ost-0.540
ric-0.528
 zoo-0.506
 North-0.501
Token and
Token ID290
Feature activation-1.76e-01

Pos logit contributions
 ost+0.075
ric+0.072
 ostr+0.070
 peac+0.070
work+0.068
Neg logit contributions
iddled-0.051
 aback-0.042
uster-0.040
bench-0.037
 tant-0.037
Token saw
Token ID2497
Feature activation-3.27e-02

Pos logit contributions
iddled+0.011
 aback+0.010
uster+0.009
 tant+0.009
bench+0.009
Neg logit contributions
 ost-0.010
ric-0.010
 ostr-0.009
 peac-0.009
work-0.009
Token a
Token ID257
Feature activation-3.65e-01

Pos logit contributions
iddled+0.002
 aback+0.002
uster+0.001
 tant+0.001
ocated+0.001
Neg logit contributions
ric-0.002
 ost-0.002
 highlight-0.002
 ostr-0.002
work-0.002
Token small
Token ID1402
Feature activation-1.47e+00

Pos logit contributions
iddled+0.017
 aback+0.016
uster+0.015
 tant+0.015
bench+0.013
Neg logit contributions
ric-0.025
 ost-0.024
 highlight-0.023
work-0.022
riage-0.021
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
 ost+0.035
ric+0.033
 peac+0.032
 ostr+0.032
work+0.031
Neg logit contributions
iddled-0.035
uster-0.031
 aback-0.030
 tant-0.028
ocated-0.028
Token forest
Token ID8222
Feature activation+7.11e-01

Pos logit contributions
 tant+0.010
 away+0.009
iddled+0.009
 aback+0.009
sc+0.009
Neg logit contributions
ric-0.011
orse-0.011
 ost-0.010
 flaming-0.010
riage-0.009
Token looking
Token ID2045
Feature activation+1.74e-01

Pos logit contributions
ric+0.056
 ost+0.055
 ostr+0.052
 flaming+0.052
 peac+0.052
Neg logit contributions
iddled-0.028
 aback-0.024
bench-0.020
ows-0.019
 away-0.018
Token for
Token ID329
Feature activation-1.53e+00

Pos logit contributions
 ost+0.012
ric+0.011
 ostr+0.011
 peac+0.011
work+0.011
Neg logit contributions
iddled-0.009
 aback-0.008
uster-0.008
 tant-0.007
bench-0.007
Token all
Token ID477
Feature activation-3.50e+00

Pos logit contributions
iddled+0.088
 aback+0.077
uster+0.072
 tant+0.068
bench+0.067
Neg logit contributions
 ost-0.096
ric-0.095
 ostr-0.089
 peac-0.089
work-0.088
Token sorts
Token ID10524
Feature activation-7.49e+00

Pos logit contributions
iddled+0.173
 aback+0.155
bench+0.130
uster+0.129
wn+0.125
Neg logit contributions
 ost-0.244
ric-0.242
 peac-0.237
work-0.231
 flaming-0.229
Token of
Token ID286
Feature activation+1.45e-01

Pos logit contributions
iddled+0.480
 aback+0.419
uster+0.405
 tant+0.383
bench+0.382
Neg logit contributions
 ost-0.429
ric-0.406
 ostr-0.392
 peac-0.390
work-0.381
Token exciting
Token ID7895
Feature activation-1.32e+00

Pos logit contributions
ric+0.009
 ost+0.009
work+0.008
 peac+0.008
 ostr+0.008
Neg logit contributions
iddled-0.009
 aback-0.008
uster-0.007
 tant-0.007
bench-0.006
Token things
Token ID1243
Feature activation-9.61e-01

Pos logit contributions
iddled+0.079
 aback+0.070
uster+0.065
 tant+0.062
bench+0.061
Neg logit contributions
 ost-0.079
ric-0.079
 peac-0.074
 ostr-0.073
work-0.073
Token.
Token ID13
Feature activation-5.54e-01

Pos logit contributions
iddled+0.052
 aback+0.046
uster+0.042
bench+0.040
ocated+0.039
Neg logit contributions
 ost-0.063
ric-0.062
 ostr-0.059
 peac-0.059
 moral-0.058
Token She
Token ID1375
Feature activation-3.71e-01

Pos logit contributions
iddled+0.027
 aback+0.025
uster+0.023
bench+0.020
ocated+0.019
Neg logit contributions
 ost-0.041
work-0.038
 peac-0.038
 ostr-0.037
 flaming-0.037
Token so
Token ID523
Feature activation-5.37e-02

Pos logit contributions
 ost+0.204
ric+0.198
 ostr+0.189
 peac+0.188
work+0.183
Neg logit contributions
iddled-0.182
 aback-0.158
uster-0.147
bench-0.139
 tant-0.138
Token much
Token ID881
Feature activation-2.71e-01

Pos logit contributions
iddled+0.002
 tant+0.002
 aback+0.002
ushes+0.002
wn+0.002
Neg logit contributions
ric-0.004
 ost-0.004
 peac-0.004
 ostr-0.004
ich-0.004
Token fun
Token ID1257
Feature activation-3.80e+00

Pos logit contributions
iddled+0.013
 aback+0.011
uster+0.010
bench+0.010
 tant+0.009
Neg logit contributions
 ost-0.020
ric-0.020
 ostr-0.019
 peac-0.019
work-0.018
Token.
Token ID13
Feature activation-2.19e-01

Pos logit contributions
iddled+0.173
 aback+0.139
bench+0.123
 tant+0.121
uster+0.121
Neg logit contributions
 ost-0.287
ric-0.281
 ostr-0.278
 peac-0.268
 rob-0.264
Token K
Token ID509
Feature activation+2.84e+00

Pos logit contributions
iddled+0.012
 aback+0.011
zip+0.009
uster+0.009
ocated+0.008
Neg logit contributions
work-0.013
 highlight-0.013
 peac-0.013
 whale-0.013
orse-0.013
Tokenait
Token ID4548
Feature activation-7.45e+00

Pos logit contributions
 ost+0.228
ric+0.223
 peac+0.218
 ostr+0.214
work+0.213
Neg logit contributions
iddled-0.115
 aback-0.093
uster-0.090
 tant-0.078
ocated-0.075
Tokenlyn
Token ID6213
Feature activation+2.41e+00

Pos logit contributions
iddled+0.482
 aback+0.426
uster+0.417
fully+0.390
 away+0.390
Neg logit contributions
 peac-0.385
 ost-0.359
 highlight-0.351
orse-0.344
ric-0.343
Token was
Token ID373
Feature activation+9.08e-02

Pos logit contributions
 ost+0.156
ric+0.150
 highlight+0.141
 flaming+0.135
 hipp+0.134
Neg logit contributions
iddled-0.138
 aback-0.121
 tant-0.101
bench-0.100
eal-0.100
Token so
Token ID523
Feature activation-7.24e-02

Pos logit contributions
 ost+0.007
ric+0.006
oral+0.006
 ostr+0.006
 peac+0.006
Neg logit contributions
 aback-0.004
iddled-0.004
 away-0.003
ocated-0.003
wn-0.003
Token happy
Token ID3772
Feature activation+5.11e-01

Pos logit contributions
iddled+0.004
 aback+0.004
 tant+0.003
uster+0.003
eal+0.003
Neg logit contributions
 ost-0.005
ric-0.005
 ostr-0.004
 zoo-0.004
 flaming-0.004
Token to
Token ID284
Feature activation-3.32e-01

Pos logit contributions
ric+0.034
 ost+0.034
 highlight+0.032
 ostr+0.032
 peac+0.031
Neg logit contributions
iddled-0.026
 aback-0.024
uster-0.020
ocated-0.020
bench-0.019
Token so
Token ID523
Feature activation-5.75e-02

Pos logit contributions
 ost+0.004
ric+0.004
 ostr+0.004
 peac+0.004
 moral+0.004
Neg logit contributions
iddled-0.003
 aback-0.003
bench-0.002
uster-0.002
ocated-0.002
Token happy
Token ID3772
Feature activation+5.36e-01

Pos logit contributions
iddled+0.004
 aback+0.004
uster+0.003
 tant+0.003
bench+0.003
Neg logit contributions
 ost-0.003
ric-0.003
 ostr-0.003
 peac-0.003
work-0.003
Token to
Token ID284
Feature activation-3.09e-01

Pos logit contributions
 ost+0.037
ric+0.037
 highlight+0.035
 ostr+0.035
 peac+0.035
Neg logit contributions
iddled-0.026
 aback-0.023
uster-0.020
ocated-0.020
bench-0.018
Token see
Token ID766
Feature activation-3.15e-01

Pos logit contributions
iddled+0.016
 aback+0.015
uster+0.013
ocated+0.012
zip+0.012
Neg logit contributions
 ost-0.020
ric-0.019
 highlight-0.018
 ostr-0.018
ich-0.017
Token K
Token ID509
Feature activation+2.87e+00

Pos logit contributions
iddled+0.021
 aback+0.019
uster+0.018
ocated+0.017
 tant+0.017
Neg logit contributions
ric-0.016
 ost-0.015
 peac-0.015
work-0.015
 highlight-0.015
Tokenait
Token ID4548
Feature activation-7.42e+00

Pos logit contributions
 ost+0.237
ric+0.234
 peac+0.231
 ostr+0.224
work+0.223
Neg logit contributions
iddled-0.105
uster-0.083
 aback-0.083
 tant-0.067
ocated-0.067
Tokenlyn
Token ID6213
Feature activation+2.37e+00

Pos logit contributions
iddled+0.437
 aback+0.404
 away+0.387
fully+0.386
uster+0.375
Neg logit contributions
 peac-0.422
 ost-0.389
 highlight-0.386
orse-0.378
ric-0.372
Token with
Token ID351
Feature activation-8.52e-01

Pos logit contributions
 ost+0.175
 ostr+0.162
 peac+0.158
 hipp+0.155
 flaming+0.155
Neg logit contributions
iddled-0.110
 aback-0.094
ows-0.086
 away-0.084
ets-0.084
Token a
Token ID257
Feature activation-3.92e-01

Pos logit contributions
iddled+0.050
 aback+0.043
uster+0.041
 tant+0.039
bench+0.038
Neg logit contributions
 ost-0.054
ric-0.052
 ostr-0.050
 peac-0.049
work-0.048
Token smile
Token ID8212
Feature activation-3.30e-01

Pos logit contributions
iddled+0.022
 aback+0.020
 tant+0.019
uster+0.019
bench+0.018
Neg logit contributions
 ost-0.025
ric-0.024
 ostr-0.023
work-0.022
 peac-0.021
Token on
Token ID319
Feature activation+7.07e-01

Pos logit contributions
iddled+0.014
 aback+0.011
uster+0.011
bench+0.011
 tant+0.010
Neg logit contributions
 ost-0.026
ric-0.025
 peac-0.023
 ostr-0.023
 highlight-0.023
Token,
Token ID11
Feature activation-4.82e-01

Pos logit contributions
iddled+0.140
 aback+0.119
bench+0.106
uster+0.105
ocated+0.098
Neg logit contributions
 ost-0.209
ric-0.207
 peac-0.197
 ostr-0.197
 flaming-0.193
Token thrilled
Token ID20536
Feature activation-3.28e-01

Pos logit contributions
iddled+0.030
 aback+0.027
uster+0.023
 tant+0.023
bench+0.023
Neg logit contributions
 ost-0.028
ric-0.027
 ostr-0.026
 peac-0.026
oral-0.025
Token to
Token ID284
Feature activation-7.28e-01

Pos logit contributions
iddled+0.017
 aback+0.015
uster+0.014
 tant+0.013
ocated+0.012
Neg logit contributions
 ost-0.022
ric-0.022
 ostr-0.021
 peac-0.021
 highlight-0.020
Token discover
Token ID7073
Feature activation+7.04e-01

Pos logit contributions
iddled+0.040
 aback+0.035
bench+0.030
uster+0.030
ocated+0.030
Neg logit contributions
 ost-0.047
ric-0.045
work-0.043
 ostr-0.043
 peac-0.042
Token all
Token ID477
Feature activation-3.37e+00

Pos logit contributions
 ost+0.043
ric+0.043
 peac+0.040
 ostr+0.040
work+0.040
Neg logit contributions
iddled-0.042
 aback-0.037
uster-0.034
 tant-0.032
bench-0.031
Token sorts
Token ID10524
Feature activation-7.41e+00

Pos logit contributions
iddled+0.187
 aback+0.164
uster+0.150
bench+0.143
 tant+0.142
Neg logit contributions
 ost-0.219
ric-0.214
 peac-0.207
 ostr-0.204
work-0.201
Token of
Token ID286
Feature activation+2.21e-01

Pos logit contributions
iddled+0.465
 aback+0.408
uster+0.391
 tant+0.369
bench+0.367
Neg logit contributions
 ost-0.434
ric-0.415
 ostr-0.397
 peac-0.396
work-0.385
Token new
Token ID649
Feature activation-5.89e-01

Pos logit contributions
ric+0.013
 ost+0.013
work+0.013
 peac+0.012
 ostr+0.012
Neg logit contributions
iddled-0.013
 aback-0.012
uster-0.011
 tant-0.010
bench-0.010
Token things
Token ID1243
Feature activation-7.71e-01

Pos logit contributions
iddled+0.034
 aback+0.030
uster+0.027
 tant+0.026
bench+0.025
Neg logit contributions
 ost-0.037
ric-0.037
 peac-0.034
 ostr-0.034
work-0.034
Token.
Token ID13
Feature activation-5.27e-01

Pos logit contributions
iddled+0.041
 aback+0.036
uster+0.032
bench+0.031
ocated+0.030
Neg logit contributions
 ost-0.052
ric-0.052
 ostr-0.049
 peac-0.049
 moral-0.048
Token
Token ID198
Feature activation-8.19e-01

Pos logit contributions
iddled+0.027
 aback+0.025
uster+0.023
bench+0.020
ocated+0.019
Neg logit contributions
 ost-0.038
 peac-0.035
 ostr-0.035
ric-0.034
 flaming-0.034
Token they
Token ID484
Feature activation+6.59e-01

Pos logit contributions
iddled+0.018
 away+0.016
 aback+0.015
 breath+0.014
 her+0.013
Neg logit contributions
ric-0.047
 ost-0.044
 rob-0.043
oral-0.043
 ostr-0.042
Token both
Token ID1111
Feature activation-3.24e-01

Pos logit contributions
 ost+0.039
ric+0.038
 ostr+0.035
 peac+0.034
work+0.033
Neg logit contributions
iddled-0.041
 aback-0.036
uster-0.033
 tant-0.033
ocated-0.032
Token were
Token ID547
Feature activation+3.38e-01

Pos logit contributions
iddled+0.017
 aback+0.015
 tant+0.014
 away+0.013
ets+0.013
Neg logit contributions
 ost-0.021
ric-0.021
ich-0.019
 moral-0.018
 ostr-0.018
Token out
Token ID503
Feature activation-1.70e+00

Pos logit contributions
 ost+0.020
ric+0.019
 ostr+0.019
 peac+0.018
work+0.018
Neg logit contributions
iddled-0.021
 aback-0.018
uster-0.017
bench-0.016
ocated-0.016
Token of
Token ID286
Feature activation+6.67e-01

Pos logit contributions
iddled+0.065
 aback+0.057
 tant+0.050
 away+0.049
 breath+0.045
Neg logit contributions
 ost-0.132
 ostr-0.131
ric-0.130
str-0.128
 peac-0.126
Token breath
Token ID8033
Feature activation-7.40e+00

Pos logit contributions
 ost+0.039
ric+0.037
 peac+0.036
 ostr+0.036
work+0.035
Neg logit contributions
iddled-0.042
 aback-0.037
uster-0.036
 tant-0.033
ocated-0.033
Token.
Token ID13
Feature activation-1.71e-01

Pos logit contributions
iddled+0.393
 aback+0.344
uster+0.321
 tant+0.301
bench+0.299
Neg logit contributions
 ost-0.503
ric-0.490
 peac-0.466
 ostr-0.465
 rob-0.451
Token
Token ID220
Feature activation+5.94e-01

Pos logit contributions
iddled+0.008
 aback+0.007
uster+0.007
acks+0.006
ocated+0.006
Neg logit contributions
 ost-0.012
 ostr-0.011
 highlight-0.011
 peac-0.011
ric-0.011
Token
Token ID198
Feature activation-6.80e-01

Pos logit contributions
 ost+0.032
ric+0.030
 ostr+0.029
 peac+0.029
work+0.028
Neg logit contributions
iddled-0.041
 aback-0.036
uster-0.035
bench-0.033
 tant-0.032
Token
Token ID198
Feature activation-5.69e-01

Pos logit contributions
iddled+0.044
 aback+0.038
uster+0.036
bench+0.034
ocated+0.034
Neg logit contributions
 ost-0.040
ric-0.037
 ostr-0.037
work-0.036
 peac-0.036
TokenB
Token ID33
Feature activation-3.11e+00

Pos logit contributions
iddled+0.028
 aback+0.022
uster+0.022
ocated+0.020
bench+0.019
Neg logit contributions
 ost-0.042
ric-0.041
 ostr-0.040
work-0.040
 peac-0.038
Token match
Token ID2872
Feature activation-6.63e-01

Pos logit contributions
iddled+0.013
 aback+0.011
 tant+0.010
wn+0.010
bench+0.010
Neg logit contributions
 ost-0.015
ric-0.015
 peac-0.014
work-0.014
 ostr-0.014
Token her
Token ID607
Feature activation-1.64e+00

Pos logit contributions
iddled+0.035
 aback+0.030
uster+0.029
bench+0.027
 tant+0.027
Neg logit contributions
 ost-0.045
ric-0.044
 ostr-0.042
 peac-0.041
work-0.041
Token moves
Token ID6100
Feature activation-2.45e+00

Pos logit contributions
iddled+0.082
 tant+0.071
 aback+0.070
uster+0.065
wn+0.062
Neg logit contributions
 ost-0.109
ric-0.105
 peac-0.103
 ostr-0.097
str-0.097
Token with
Token ID351
Feature activation-1.04e+00

Pos logit contributions
iddled+0.135
 aback+0.116
uster+0.110
 tant+0.103
bench+0.102
Neg logit contributions
 ost-0.163
ric-0.158
 ostr-0.151
 peac-0.151
 highlight-0.145
Token her
Token ID607
Feature activation-1.66e+00

Pos logit contributions
iddled+0.050
 aback+0.042
uster+0.040
bench+0.037
 tant+0.036
Neg logit contributions
 ost-0.076
ric-0.074
 ostr-0.071
 peac-0.071
work-0.069
Token breath
Token ID8033
Feature activation-7.40e+00

Pos logit contributions
iddled+0.085
 tant+0.074
 aback+0.073
uster+0.071
bench+0.064
Neg logit contributions
 ost-0.108
ric-0.105
 peac-0.102
 ostr-0.098
str-0.095
Token.
Token ID13
Feature activation-3.19e-02

Pos logit contributions
iddled+0.433
 aback+0.375
uster+0.358
 tant+0.336
bench+0.334
Neg logit contributions
 ost-0.461
ric-0.444
 ostr-0.425
 peac-0.424
work-0.415
Token One
Token ID1881
Feature activation+2.15e+00

Pos logit contributions
iddled+0.002
 aback+0.002
uster+0.001
 tant+0.001
bench+0.001
Neg logit contributions
 ost-0.002
 peac-0.002
 ostr-0.002
ric-0.002
work-0.002
Token day
Token ID1110
Feature activation+1.46e+00

Pos logit contributions
ric+0.115
 ost+0.102
 peac+0.100
work+0.093
 flaming+0.090
Neg logit contributions
iddled-0.141
 tant-0.126
 aback-0.126
uster-0.121
bench-0.118
Token,
Token ID11
Feature activation-8.12e-02

Pos logit contributions
 ost+0.094
ric+0.092
 peac+0.087
 ostr+0.087
work+0.085
Neg logit contributions
iddled-0.083
 aback-0.072
uster-0.068
 tant-0.064
ocated-0.063
Token while
Token ID981
Feature activation-4.08e+00

Pos logit contributions
iddled+0.004
 aback+0.004
uster+0.003
 tant+0.003
ocated+0.003
Neg logit contributions
ric-0.006
 ost-0.006
 peac-0.005
 ostr-0.005
 moral-0.005
Token things
Token ID1243
Feature activation-9.67e-01

Pos logit contributions
iddled+0.051
 tant+0.048
 aback+0.047
bench+0.042
uster+0.042
Neg logit contributions
ric-0.056
 ost-0.053
 highlight-0.052
str-0.048
riage-0.048
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
iddled+0.051
 aback+0.044
uster+0.039
bench+0.039
ocated+0.037
Neg logit contributions
 ost-0.065
ric-0.064
 peac-0.061
 ostr-0.061
 flaming-0.059
Token They
Token ID1119
Feature activation-8.93e-01

Pos logit contributions
iddled+0.024
 aback+0.021
uster+0.019
bench+0.017
zip+0.016
Neg logit contributions
 ost-0.043
ric-0.040
 highlight-0.039
 peac-0.039
 ostr-0.039
Token met
Token ID1138
Feature activation+1.46e+00

Pos logit contributions
iddled+0.054
 aback+0.046
 tant+0.042
bench+0.041
uster+0.041
Neg logit contributions
 ost-0.054
ric-0.052
 highlight-0.048
 flaming-0.048
ich-0.048
Token all
Token ID477
Feature activation-3.28e+00

Pos logit contributions
ric+0.106
 ost+0.101
 peac+0.096
 ostr+0.094
 highlight+0.094
Neg logit contributions
iddled-0.073
 aback-0.063
 tant-0.053
uster-0.052
ocated-0.048
Token kinds
Token ID6982
Feature activation-7.38e+00

Pos logit contributions
iddled+0.143
 aback+0.128
 tant+0.107
bench+0.105
 away+0.096
Neg logit contributions
ric-0.238
ich-0.233
 ost-0.233
 peac-0.230
 flaming-0.225
Token of
Token ID286
Feature activation+3.78e-01

Pos logit contributions
iddled+0.351
 aback+0.301
uster+0.269
 tant+0.251
bench+0.250
Neg logit contributions
ric-0.559
 ost-0.525
 North-0.498
 highlight-0.496
 ostr-0.494
Token animals
Token ID4695
Feature activation+2.14e+00

Pos logit contributions
ric+0.026
work+0.024
 peac+0.023
 ost+0.023
 highlight+0.023
Neg logit contributions
iddled-0.020
 aback-0.017
 tant-0.016
wn-0.014
uster-0.014
Token,
Token ID11
Feature activation-2.89e-01

Pos logit contributions
ric+0.171
 moral+0.163
 ost+0.161
 highlight+0.159
 North+0.158
Neg logit contributions
iddled-0.080
 aback-0.069
ows-0.055
ets-0.053
uster-0.051
Token from
Token ID422
Feature activation+1.18e+00

Pos logit contributions
iddled+0.016
 aback+0.014
 tant+0.013
uster+0.012
wn+0.012
Neg logit contributions
ric-0.018
work-0.016
oral-0.016
riage-0.016
 ost-0.016
Token tiny
Token ID7009
Feature activation-1.54e+00

Pos logit contributions
ric+0.087
str+0.084
 ost+0.083
 highlight+0.083
 peac+0.081
Neg logit contributions
iddled-0.047
 aback-0.041
 tant-0.039
 away-0.036
bench-0.031
Token moral
Token ID6573
Feature activation+6.83e+00

Pos logit contributions
ric+0.022
orse+0.021
work+0.020
riage+0.018
grand+0.018
Neg logit contributions
 aback-0.016
 knot-0.015
 away-0.015
iddled-0.014
 breath-0.014
Token of
Token ID286
Feature activation+6.41e-01

Pos logit contributions
ric+0.476
 ost+0.453
 peac+0.430
 highlight+0.427
 flaming+0.426
Neg logit contributions
iddled-0.355
 aback-0.325
uster-0.290
bench-0.281
wn-0.263
Token their
Token ID511
Feature activation-3.49e-01

Pos logit contributions
 ost+0.047
 ostr+0.044
 peac+0.044
 highlight+0.043
ric+0.043
Neg logit contributions
iddled-0.029
 aback-0.025
uster-0.022
bench-0.021
 tant-0.019
Token story
Token ID1621
Feature activation+5.47e+00

Pos logit contributions
 breath+0.017
 aback+0.016
 knot+0.016
iddled+0.015
 off+0.015
Neg logit contributions
ric-0.021
flower-0.019
 ost-0.017
ich-0.016
 highlight-0.016
Token:
Token ID25
Feature activation+3.98e+00

Pos logit contributions
 ost+0.332
ric+0.325
 peac+0.309
 ostr+0.307
 flaming+0.301
Neg logit contributions
iddled-0.330
 aback-0.294
bench-0.272
uster-0.269
ocated-0.253
Token Just
Token ID2329
Feature activation+4.19e+00

Pos logit contributions
 ost+0.267
 flaming+0.251
str+0.251
 ostr+0.250
 highlight+0.243
Neg logit contributions
iddled-0.195
 aback-0.182
uster-0.137
ocated-0.135
 If-0.130
Token because
Token ID780
Feature activation+5.21e-01

Pos logit contributions
 ost+0.273
 flaming+0.253
ich+0.244
ric+0.237
 peac+0.233
Neg logit contributions
 aback-0.201
iddled-0.192
 away-0.181
wn-0.169
uster-0.164
Token something
Token ID1223
Feature activation-5.14e-02

Pos logit contributions
ric+0.041
 flaming+0.039
 ost+0.038
 highlight+0.037
 ostr+0.037
Neg logit contributions
iddled-0.018
 aback-0.015
ocated-0.012
uster-0.012
bench-0.011
Token is
Token ID318
Feature activation-4.09e-01

Pos logit contributions
iddled+0.003
 aback+0.003
uster+0.002
 tant+0.002
ocated+0.002
Neg logit contributions
ric-0.003
 ost-0.003
 peac-0.003
 highlight-0.003
 flaming-0.003
Token difficult
Token ID2408
Feature activation-1.32e+00

Pos logit contributions
iddled+0.021
 aback+0.021
bench+0.017
 away+0.017
wn+0.017
Neg logit contributions
ric-0.026
 ost-0.025
 flaming-0.024
 peac-0.024
orse-0.024
Token,
Token ID11
Feature activation-1.96e-02

Pos logit contributions
iddled+0.076
 aback+0.066
uster+0.063
 tant+0.059
bench+0.059
Neg logit contributions
 ost-0.084
ric-0.081
 ostr-0.078
 peac-0.077
work-0.075
Token in
Token ID287
Feature activation+3.08e-01

Pos logit contributions
ric+0.397
 highlight+0.392
 ost+0.391
 moral+0.379
oral+0.374
Neg logit contributions
iddled-0.153
 away-0.114
 aback-0.105
bench-0.105
wn-0.093
Token his
Token ID465
Feature activation-1.57e+00

Pos logit contributions
 ost+0.020
ric+0.020
 ostr+0.019
 peac+0.019
 rob+0.018
Neg logit contributions
iddled-0.017
 aback-0.015
uster-0.015
 tant-0.013
ocated-0.013
Token garden
Token ID11376
Feature activation+5.68e-01

Pos logit contributions
iddled+0.090
 aback+0.082
 tant+0.075
uster+0.073
bench+0.072
Neg logit contributions
 ost-0.093
ric-0.090
work-0.085
 peac-0.085
 highlight-0.082
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
 ost+0.038
ric+0.037
 ostr+0.035
 peac+0.035
work+0.035
Neg logit contributions
iddled-0.030
 aback-0.026
uster-0.024
bench-0.023
 tant-0.023
Token The
Token ID383
Feature activation+2.27e+00

Pos logit contributions
 ost+0.007
ric+0.006
 ostr+0.006
 peac+0.006
 rob+0.006
Neg logit contributions
iddled-0.013
uster-0.012
 aback-0.012
 tant-0.011
ocated-0.011
Token angel
Token ID18304
Feature activation+4.66e+00

Pos logit contributions
ric+0.110
 ost+0.099
orse+0.087
 highlight+0.087
 peac+0.086
Neg logit contributions
iddled-0.161
 aback-0.149
 tant-0.143
bench-0.136
uster-0.132
Token was
Token ID373
Feature activation-6.62e-02

Pos logit contributions
ric+0.332
 highlight+0.317
 ost+0.301
 North+0.290
 Whale+0.282
Neg logit contributions
iddled-0.223
led-0.186
 aback-0.175
zip-0.172
 away-0.164
Token very
Token ID845
Feature activation+1.91e-01

Pos logit contributions
iddled+0.004
 aback+0.003
bench+0.003
uster+0.003
 tant+0.003
Neg logit contributions
ric-0.004
 ost-0.004
work-0.004
 highlight-0.004
 ostr-0.004
Token pretty
Token ID2495
Feature activation-1.17e+00

Pos logit contributions
ric+0.013
 ost+0.013
work+0.012
 highlight+0.012
 peac+0.012
Neg logit contributions
iddled-0.010
 aback-0.008
 tant-0.008
uster-0.007
bench-0.007
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
iddled+0.073
 aback+0.063
uster+0.061
 tant+0.056
bench+0.056
Neg logit contributions
 ost-0.071
ric-0.067
 ostr-0.065
 peac-0.064
work-0.064
Token had
Token ID550
Feature activation+2.84e+00

Pos logit contributions
iddled+0.025
 aback+0.022
bench+0.020
uster+0.020
ocated+0.020
Neg logit contributions
ric-0.023
 ost-0.022
 highlight-0.020
work-0.020
 peac-0.020
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
 ost+0.043
ric+0.040
 ostr+0.039
work+0.039
 peac+0.039
Neg logit contributions
iddled-0.042
 aback-0.036
uster-0.035
 tant-0.033
bench-0.032
Token buy
Token ID2822
Feature activation-3.59e-02

Pos logit contributions
iddled+0.023
 aback+0.020
uster+0.019
ocated+0.018
bench+0.018
Neg logit contributions
 ost-0.026
ric-0.025
 peac-0.024
 ostr-0.024
 moral-0.023
Token a
Token ID257
Feature activation-5.09e-01

Pos logit contributions
iddled+0.002
 aback+0.002
uster+0.002
ocated+0.002
 tant+0.002
Neg logit contributions
 ost-0.002
ric-0.002
 ostr-0.002
 peac-0.002
 moral-0.002
Token bright
Token ID6016
Feature activation+1.31e-01

Pos logit contributions
iddled+0.026
 aback+0.024
uster+0.023
 tant+0.022
bench+0.021
Neg logit contributions
ric-0.033
 ost-0.033
work-0.031
 peac-0.030
 highlight-0.029
Token purple
Token ID14032
Feature activation+1.92e+00

Pos logit contributions
 ost+0.008
ric+0.008
 highlight+0.007
 peac+0.007
work+0.007
Neg logit contributions
iddled-0.008
 aback-0.007
uster-0.007
 tant-0.006
bench-0.006
Token je
Token ID11223
Feature activation+4.91e+00

Pos logit contributions
ric+0.102
 ost+0.102
 highlight+0.097
work+0.089
 moral+0.088
Neg logit contributions
iddled-0.113
 aback-0.104
uster-0.102
 tant-0.102
bench-0.093
Tokenep
Token ID538
Feature activation-8.03e-01

Pos logit contributions
 ost+0.348
ric+0.337
 ostr+0.324
 peac+0.323
work+0.315
Neg logit contributions
iddled-0.247
 aback-0.210
uster-0.198
 tant-0.184
bench-0.182
Token.
Token ID13
Feature activation-2.75e-01

Pos logit contributions
iddled+0.042
 aback+0.035
uster+0.034
bench+0.031
ocated+0.029
Neg logit contributions
 ost-0.057
ric-0.054
 peac-0.053
 moral-0.052
 ostr-0.052
Token It
Token ID632
Feature activation-1.23e+00

Pos logit contributions
iddled+0.016
 aback+0.014
uster+0.013
 tant+0.012
bench+0.012
Neg logit contributions
 ost-0.018
ric-0.017
 ostr-0.016
 peac-0.016
work-0.016
Token was
Token ID373
Feature activation-6.65e-02

Pos logit contributions
iddled+0.091
 aback+0.081
uster+0.075
bench+0.074
ocated+0.073
Neg logit contributions
 ost-0.060
ric-0.058
 peac-0.053
 ostr-0.053
 highlight-0.051
Token so
Token ID523
Feature activation-1.38e-01

Pos logit contributions
iddled+0.004
 aback+0.004
uster+0.003
 tant+0.003
bench+0.003
Neg logit contributions
 ost-0.004
ric-0.004
 ostr-0.004
 peac-0.004
work-0.003
Token's
Token ID338
Feature activation+2.39e+00

Pos logit contributions
iddled+0.159
 aback+0.138
ocated+0.121
uster+0.120
bench+0.115
Neg logit contributions
 ost-0.227
ric-0.223
 peac-0.216
 highlight-0.214
 ostr-0.212
Token face
Token ID1986
Feature activation-8.39e-01

Pos logit contributions
ric+0.159
 ost+0.157
work+0.149
 highlight+0.144
str+0.144
Neg logit contributions
iddled-0.115
 aback-0.106
 tant-0.104
uster-0.096
ocated-0.093
Token.
Token ID13
Feature activation+8.51e-02

Pos logit contributions
iddled+0.040
 aback+0.032
uster+0.029
ocated+0.028
ows+0.027
Neg logit contributions
 ost-0.063
ric-0.062
 peac-0.060
 ostr-0.059
 rob-0.058
Token He
Token ID679
Feature activation-6.00e-02

Pos logit contributions
 ost+0.004
ric+0.004
 moral+0.004
 zoo+0.004
 flaming+0.004
Neg logit contributions
iddled-0.005
uster-0.005
 aback-0.005
wn-0.005
ocated-0.004
Token was
Token ID373
Feature activation+4.86e-01

Pos logit contributions
iddled+0.004
 aback+0.003
uster+0.003
 tant+0.003
ocated+0.003
Neg logit contributions
 ost-0.004
ric-0.004
 peac-0.003
 highlight-0.003
work-0.003
Token smiling
Token ID16755
Feature activation+4.63e+00

Pos logit contributions
 ost+0.026
ric+0.026
 peac+0.024
 ostr+0.024
work+0.024
Neg logit contributions
iddled-0.032
 aback-0.029
uster-0.027
bench-0.026
ocated-0.026
Token and
Token ID290
Feature activation-1.23e-01

Pos logit contributions
 ost+0.262
work+0.247
 ostr+0.247
 peac+0.244
ric+0.244
Neg logit contributions
iddled-0.288
 aback-0.248
uster-0.246
bench-0.239
 tant-0.229
Token holding
Token ID4769
Feature activation+5.72e-01

Pos logit contributions
iddled+0.008
 aback+0.007
bench+0.007
uster+0.007
ocated+0.007
Neg logit contributions
 ost-0.006
ric-0.006
 highlight-0.006
 ostr-0.006
work-0.006
Token something
Token ID1223
Feature activation+7.09e-03

Pos logit contributions
 ost+0.031
 flaming+0.029
ric+0.029
work+0.028
 ostr+0.028
Neg logit contributions
iddled-0.035
bench-0.031
uster-0.031
 aback-0.029
ocated-0.029
Token in
Token ID287
Feature activation+5.64e-01

Pos logit contributions
 ost+0.000
ric+0.000
 ostr+0.000
 peac+0.000
work+0.000
Neg logit contributions
iddled-0.000
 aback-0.000
uster-0.000
 tant-0.000
bench-0.000
Token his
Token ID465
Feature activation-1.25e+00

Pos logit contributions
 ost+0.029
 zoo+0.027
 rob+0.027
 North+0.027
 ostr+0.027
Neg logit contributions
iddled-0.039
uster-0.035
ocated-0.032
ows-0.031
iddling-0.031
Token of
Token ID286
Feature activation+8.94e-01

Pos logit contributions
iddled+0.080
 aback+0.069
uster+0.065
 tant+0.061
bench+0.060
Neg logit contributions
ric-0.091
 ost-0.091
 ostr-0.085
 peac-0.085
 highlight-0.084
Token the
Token ID262
Feature activation+4.97e-01

Pos logit contributions
 ost+0.043
 zoo+0.039
 ostr+0.039
 peac+0.037
 flaming+0.036
Neg logit contributions
iddled-0.070
uster-0.064
ocated-0.059
 aback-0.058
iddling-0.058
Token trees
Token ID7150
Feature activation+1.75e+00

Pos logit contributions
ric+0.031
 highlight+0.030
 ost+0.030
work+0.029
 known+0.029
Neg logit contributions
iddled-0.021
 aback-0.021
 tant-0.021
 away-0.021
bench-0.019
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
 ost+0.138
 peac+0.137
ric+0.136
 highlight+0.135
 moral+0.134
Neg logit contributions
iddled-0.063
 aback-0.053
bench-0.049
 away-0.043
ows-0.043
Token The
Token ID383
Feature activation+2.27e+00

Pos logit contributions
 ost+0.007
ric+0.007
 ostr+0.007
 peac+0.007
 highlight+0.006
Neg logit contributions
iddled-0.005
 aback-0.005
uster-0.004
bench-0.004
 tant-0.004
Token giant
Token ID6175
Feature activation+4.47e+00

Pos logit contributions
ric+0.140
 highlight+0.125
 ost+0.119
orse+0.118
str+0.114
Neg logit contributions
 tant-0.107
iddled-0.093
ly-0.093
 knot-0.092
 breath-0.091
Token had
Token ID550
Feature activation+3.28e+00

Pos logit contributions
ric+0.333
 highlight+0.324
riage+0.290
work+0.282
 ost+0.282
Neg logit contributions
iddled-0.187
ly-0.159
les-0.156
led-0.155
 shoved-0.145
Token long
Token ID890
Feature activation-1.73e+00

Pos logit contributions
ric+0.198
 ost+0.197
work+0.186
 highlight+0.182
 peac+0.181
Neg logit contributions
iddled-0.193
 aback-0.169
uster-0.154
ocated-0.149
bench-0.149
Token hair
Token ID4190
Feature activation+4.15e-01

Pos logit contributions
iddled+0.081
 aback+0.070
 tant+0.064
bench+0.061
uster+0.060
Neg logit contributions
 ost-0.121
ric-0.118
work-0.118
 highlight-0.117
 peac-0.114
Token and
Token ID290
Feature activation-7.49e-02

Pos logit contributions
 ost+0.031
 highlight+0.030
 moral+0.030
 peac+0.030
ric+0.030
Neg logit contributions
iddled-0.018
 aback-0.013
ows-0.012
uster-0.012
bench-0.012
Token long
Token ID890
Feature activation-1.72e+00

Pos logit contributions
iddled+0.004
 aback+0.003
 tant+0.003
bench+0.003
uster+0.002
Neg logit contributions
ric-0.005
 ost-0.005
 highlight-0.005
work-0.005
str-0.005
Token snow
Token ID6729
Feature activation+9.62e-01

Pos logit contributions
work+0.013
ric+0.013
 ost+0.012
 peac+0.012
 rob+0.012
Neg logit contributions
iddled-0.014
 aback-0.013
uster-0.012
 tant-0.012
bench-0.012
Token house
Token ID2156
Feature activation-8.87e-01

Pos logit contributions
 ost+0.061
ric+0.059
 ostr+0.057
 peac+0.056
work+0.055
Neg logit contributions
iddled-0.056
 aback-0.048
uster-0.046
 tant-0.043
bench-0.043
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
iddled+0.051
 aback+0.044
uster+0.042
 tant+0.039
bench+0.039
Neg logit contributions
 ost-0.057
ric-0.055
 ostr-0.053
 peac-0.052
work-0.051
Token Even
Token ID3412
Feature activation-3.26e-02

Pos logit contributions
 ost+0.009
 peac+0.008
ric+0.008
 ostr+0.008
 flaming+0.008
Neg logit contributions
iddled-0.006
 aback-0.005
uster-0.005
acks-0.004
 tant-0.004
Token when
Token ID618
Feature activation+5.63e-01

Pos logit contributions
iddled+0.001
 aback+0.001
uster+0.001
 tant+0.001
bench+0.001
Neg logit contributions
 ost-0.002
ric-0.002
 peac-0.002
 ostr-0.002
work-0.002
Token the
Token ID262
Feature activation+2.48e-01

Pos logit contributions
ric+0.044
work+0.042
 peac+0.042
 ostr+0.040
 highlight+0.040
Neg logit contributions
 breath-0.013
iddled-0.013
ts-0.013
 it-0.012
 his-0.011
Token weather
Token ID6193
Feature activation-5.29e-01

Pos logit contributions
ric+0.017
str+0.015
work+0.015
 rob+0.014
 peac+0.014
Neg logit contributions
 tant-0.011
iddled-0.010
uster-0.010
 breath-0.010
 socks-0.010
Token was
Token ID373
Feature activation+8.79e-02

Pos logit contributions
iddled+0.034
 aback+0.030
bench+0.027
uster+0.027
ocated+0.026
Neg logit contributions
ric-0.031
 ost-0.029
 peac-0.028
 ostr-0.027
 highlight-0.026
Token cold
Token ID4692
Feature activation-9.14e-01

Pos logit contributions
 ost+0.005
ric+0.005
 peac+0.005
 ostr+0.005
 flaming+0.005
Neg logit contributions
iddled-0.005
 aback-0.005
uster-0.004
bench-0.004
 tant-0.004
Token,
Token ID11
Feature activation-2.66e-01

Pos logit contributions
iddled+0.061
 aback+0.051
uster+0.050
 tant+0.048
bench+0.048
Neg logit contributions
 ost-0.052
ric-0.048
work-0.047
 ostr-0.047
 peac-0.046
Token they
Token ID484
Feature activation+5.87e-01

Pos logit contributions
iddled+0.010
 aback+0.009
 tant+0.008
uster+0.008
 away+0.007
Neg logit contributions
ric-0.019
 peac-0.018
str-0.018
oral-0.018
work-0.018
Token the
Token ID262
Feature activation+1.13e-01

Pos logit contributions
 ost+0.046
ric+0.044
 ostr+0.043
 peac+0.042
 moral+0.041
Neg logit contributions
iddled-0.042
 aback-0.035
uster-0.035
bench-0.032
ocated-0.032
Token bed
Token ID3996
Feature activation-3.06e+00

Pos logit contributions
ric+0.007
 ost+0.007
work+0.007
 peac+0.007
 rob+0.007
Neg logit contributions
iddled-0.006
uster-0.005
 aback-0.005
 tant-0.005
ocated-0.004
Token,
Token ID11
Feature activation-3.23e-01

Pos logit contributions
iddled+0.203
 aback+0.177
uster+0.169
 tant+0.159
ocated+0.157
Neg logit contributions
 ost-0.162
work-0.155
 ostr-0.153
ric-0.152
 zoo-0.151
Token she
Token ID673
Feature activation-1.57e-01

Pos logit contributions
iddled+0.021
 aback+0.019
uster+0.018
 tant+0.017
bench+0.017
Neg logit contributions
 ost-0.018
ric-0.017
 ostr-0.017
 peac-0.017
 highlight-0.016
Token hopped
Token ID45230
Feature activation-8.28e-01

Pos logit contributions
iddled+0.010
 aback+0.009
uster+0.008
 tant+0.008
ocated+0.008
Neg logit contributions
 ost-0.009
ric-0.009
 peac-0.008
work-0.008
 ostr-0.008
Token on
Token ID319
Feature activation+7.02e-01

Pos logit contributions
iddled+0.057
 tant+0.048
 aback+0.047
uster+0.047
bench+0.046
Neg logit contributions
 ost-0.039
 moral-0.038
 ostr-0.037
 zoo-0.036
 North-0.036
Token the
Token ID262
Feature activation+1.71e-01

Pos logit contributions
 ost+0.045
ric+0.042
 ostr+0.041
 peac+0.040
 moral+0.040
Neg logit contributions
iddled-0.042
 aback-0.035
uster-0.035
bench-0.033
ocated-0.032
Token sofa
Token ID34902
Feature activation-2.52e+00

Pos logit contributions
 ost+0.012
ric+0.011
work+0.011
 peac+0.011
 rob+0.011
Neg logit contributions
iddled-0.009
 aback-0.007
uster-0.007
 tant-0.007
ocated-0.007
Token,
Token ID11
Feature activation-3.64e-01

Pos logit contributions
iddled+0.162
 aback+0.140
uster+0.137
 tant+0.130
ocated+0.125
Neg logit contributions
 ost-0.141
ric-0.134
 ostr-0.131
work-0.129
 zoo-0.129
Token she
Token ID673
Feature activation-1.72e-01

Pos logit contributions
iddled+0.022
 aback+0.019
uster+0.018
 tant+0.017
bench+0.017
Neg logit contributions
 ost-0.023
ric-0.022
 ostr-0.021
 peac-0.021
 highlight-0.020
Token hopped
Token ID45230
Feature activation-8.54e-01

Pos logit contributions
iddled+0.011
 aback+0.010
uster+0.009
 tant+0.009
ocated+0.009
Neg logit contributions
 ost-0.010
ric-0.010
 peac-0.009
 ostr-0.009
work-0.009
Token was
Token ID373
Feature activation+2.34e-01

Pos logit contributions
iddled+0.163
 aback+0.146
uster+0.135
 tant+0.124
ocated+0.123
Neg logit contributions
 ost-0.204
ric-0.195
 peac-0.192
 ostr-0.190
 flaming-0.188
Token important
Token ID1593
Feature activation+8.39e-01

Pos logit contributions
ric+0.015
 ost+0.014
 ostr+0.014
 peac+0.014
 flaming+0.014
Neg logit contributions
iddled-0.013
 aback-0.013
wn-0.010
uster-0.010
 away-0.010
Token.
Token ID13
Feature activation-6.87e-02

Pos logit contributions
 ost+0.053
ric+0.051
 ostr+0.049
 peac+0.049
work+0.048
Neg logit contributions
iddled-0.049
 aback-0.042
uster-0.040
 tant-0.038
bench-0.037
Token He
Token ID679
Feature activation-6.20e-02

Pos logit contributions
 aback+0.003
iddled+0.003
uster+0.002
bench+0.002
acks+0.002
Neg logit contributions
 ost-0.005
 peac-0.005
work-0.005
 highlight-0.005
ric-0.005
Token learned
Token ID4499
Feature activation+1.48e+00

Pos logit contributions
iddled+0.003
 aback+0.003
uster+0.002
 away+0.002
eal+0.002
Neg logit contributions
ric-0.004
 ost-0.004
 highlight-0.004
 flaming-0.004
work-0.004
Token that
Token ID326
Feature activation-2.93e-01

Pos logit contributions
 ost+0.094
ric+0.094
 flaming+0.090
 peac+0.088
 ostr+0.088
Neg logit contributions
iddled-0.082
 aback-0.077
uster-0.067
 tant-0.063
bench-0.062
Token day
Token ID1110
Feature activation+1.55e+00

Pos logit contributions
 aback+0.012
iddled+0.011
bench+0.009
ocated+0.009
 tant+0.009
Neg logit contributions
ric-0.022
 ost-0.020
 flaming-0.020
 ostr-0.019
work-0.019
Token that
Token ID326
Feature activation-3.05e-01

Pos logit contributions
 ost+0.094
ric+0.092
 ostr+0.087
 peac+0.087
 flaming+0.086
Neg logit contributions
iddled-0.095
 aback-0.085
uster-0.080
bench-0.075
ocated-0.075
Token if
Token ID611
Feature activation-1.62e+00

Pos logit contributions
 aback+0.015
iddled+0.015
ocated+0.013
bench+0.013
 tant+0.012
Neg logit contributions
ric-0.020
 ost-0.017
 flaming-0.017
 ostr-0.017
work-0.017
Token you
Token ID345
Feature activation+2.28e+00

Pos logit contributions
 aback+0.061
iddled+0.050
ocated+0.044
 away+0.041
ly+0.038
Neg logit contributions
ric-0.132
work-0.114
 flaming-0.114
flower-0.112
 peac-0.112
Token make
Token ID787
Feature activation-1.18e+00

Pos logit contributions
 ost+0.147
ric+0.136
 flaming+0.133
 ostr+0.133
 peac+0.132
Neg logit contributions
iddled-0.131
 aback-0.122
uster-0.112
 tant-0.104
bench-0.102
Token and
Token ID290
Feature activation-2.53e-01

Pos logit contributions
 ost+0.027
ric+0.027
 peac+0.025
 ostr+0.025
 highlight+0.025
Neg logit contributions
iddled-0.021
 aback-0.018
uster-0.017
 tant-0.016
bench-0.016
Token whispers
Token ID37806
Feature activation-1.62e+00

Pos logit contributions
iddled+0.013
 aback+0.011
uster+0.010
 tant+0.010
ocated+0.009
Neg logit contributions
 ost-0.017
ric-0.017
 peac-0.017
 highlight-0.016
 ostr-0.016
Token in
Token ID287
Feature activation+5.38e-01

Pos logit contributions
iddled+0.092
 aback+0.080
uster+0.076
 tant+0.071
bench+0.070
Neg logit contributions
 ost-0.104
ric-0.102
 ostr-0.097
 peac-0.097
work-0.094
Token their
Token ID511
Feature activation-3.05e-01

Pos logit contributions
 ost+0.033
ric+0.033
 ostr+0.031
 peac+0.031
work+0.031
Neg logit contributions
iddled-0.031
 aback-0.028
uster-0.026
 tant-0.025
bench-0.024
Token ears
Token ID11368
Feature activation-6.78e-01

Pos logit contributions
iddled+0.014
 tant+0.013
 aback+0.012
uster+0.012
ags+0.012
Neg logit contributions
ric-0.020
 ost-0.020
 peac-0.020
work-0.020
 highlight-0.020
Token.
Token ID13
Feature activation-3.00e-01

Pos logit contributions
iddled+0.034
 aback+0.029
uster+0.028
bench+0.026
 tant+0.026
Neg logit contributions
 ost-0.047
ric-0.046
 peac-0.044
 ostr-0.044
 highlight-0.043
Token He
Token ID679
Feature activation-1.99e-01

Pos logit contributions
iddled+0.018
 aback+0.015
uster+0.014
bench+0.014
ocated+0.014
Neg logit contributions
 ost-0.019
ric-0.018
 ostr-0.017
 peac-0.017
 moral-0.017
Token says
Token ID1139
Feature activation-6.32e-02

Pos logit contributions
iddled+0.010
 aback+0.008
 tant+0.007
uster+0.007
irms+0.007
Neg logit contributions
 ost-0.014
ric-0.014
 highlight-0.013
 peac-0.013
work-0.013
Token the
Token ID262
Feature activation+3.94e-01

Pos logit contributions
iddled+0.002
 aback+0.002
 tant+0.002
uster+0.002
ocated+0.002
Neg logit contributions
ric-0.005
 highlight-0.005
work-0.005
 colony-0.004
ich-0.004
Token secret
Token ID3200
Feature activation+2.22e-01

Pos logit contributions
ric+0.022
 ost+0.020
work+0.020
 highlight+0.020
orse+0.020
Neg logit contributions
iddled-0.022
uster-0.020
bench-0.020
 tant-0.020
 aback-0.020
Token is
Token ID318
Feature activation-2.75e-01

Pos logit contributions
 highlight+0.014
ric+0.014
 ost+0.013
 rob+0.013
str+0.013
Neg logit contributions
iddled-0.012
 aback-0.010
ows-0.009
bench-0.009
uster-0.009
Token,
Token ID11
Feature activation-1.36e-01

Pos logit contributions
iddled+0.023
 aback+0.020
bench+0.016
uster+0.015
ocated+0.015
Neg logit contributions
 ost-0.044
ric-0.043
 ostr-0.042
 peac-0.041
 highlight-0.041
Token using
Token ID1262
Feature activation+2.28e-01

Pos logit contributions
iddled+0.007
 aback+0.007
uster+0.006
bench+0.006
 tant+0.006
Neg logit contributions
ric-0.008
 ost-0.008
 ostr-0.008
work-0.008
oral-0.007
Token his
Token ID465
Feature activation-1.48e+00

Pos logit contributions
 ost+0.015
ric+0.014
 peac+0.014
 ostr+0.013
work+0.013
Neg logit contributions
iddled-0.013
uster-0.011
 aback-0.011
ocated-0.010
bench-0.010
Token reversing
Token ID37556
Feature activation+1.97e+00

Pos logit contributions
iddled+0.073
 aback+0.069
 tant+0.063
uster+0.061
wn+0.060
Neg logit contributions
ric-0.097
 ost-0.096
 ostr-0.089
work-0.088
 North-0.086
Token powers
Token ID5635
Feature activation-3.98e+00

Pos logit contributions
 ost+0.140
ric+0.135
 ostr+0.130
 peac+0.129
work+0.126
Neg logit contributions
iddled-0.099
 aback-0.084
uster-0.079
 tant-0.074
bench-0.074
Token to
Token ID284
Feature activation-3.17e-01

Pos logit contributions
iddled+0.222
 aback+0.194
uster+0.182
bench+0.170
 tant+0.170
Neg logit contributions
 ost-0.260
ric-0.250
 ostr-0.241
 peac-0.240
 flaming-0.232
Token help
Token ID1037
Feature activation-1.80e+00

Pos logit contributions
iddled+0.019
 aback+0.017
uster+0.016
bench+0.015
ocated+0.015
Neg logit contributions
 ost-0.019
ric-0.018
 ostr-0.018
 peac-0.017
work-0.017
Token out
Token ID503
Feature activation-1.61e+00

Pos logit contributions
iddled+0.096
 aback+0.080
uster+0.077
 tant+0.071
bench+0.071
Neg logit contributions
 ost-0.124
ric-0.119
 peac-0.115
 ostr-0.115
work-0.113
Token.
Token ID13
Feature activation+4.16e-02

Pos logit contributions
iddled+0.074
 aback+0.068
uster+0.057
 tant+0.057
 away+0.053
Neg logit contributions
 ost-0.116
ric-0.114
 ostr-0.112
str-0.110
 flaming-0.108
Token He
Token ID679
Feature activation-1.70e-01

Pos logit contributions
 ost+0.003
 peac+0.003
 ostr+0.003
 flaming+0.003
ric+0.003
Neg logit contributions
iddled-0.002
 aback-0.002
uster-0.002
bench-0.002
acks-0.002
Token was
Token ID373
Feature activation-1.78e-02

Pos logit contributions
iddled+0.011
 aback+0.010
uster+0.008
bench+0.008
ocated+0.008
Neg logit contributions
 ost-0.010
ric-0.009
 highlight-0.008
 flaming-0.008
 peac-0.008
Token a
Token ID257
Feature activation-5.54e-01

Pos logit contributions
iddled+0.057
 aback+0.049
uster+0.047
 tant+0.044
bench+0.044
Neg logit contributions
 ost-0.059
ric-0.056
 peac-0.054
 ostr-0.054
work-0.052
Token time
Token ID640
Feature activation-9.00e-01

Pos logit contributions
iddled+0.043
 aback+0.037
uster+0.036
ocated+0.035
bench+0.033
Neg logit contributions
 ost-0.025
 moral-0.024
ric-0.024
 ostr-0.023
 highlight-0.022
Token,
Token ID11
Feature activation+5.78e-02

Pos logit contributions
iddled+0.053
 aback+0.046
uster+0.044
 tant+0.041
bench+0.041
Neg logit contributions
 ost-0.057
ric-0.054
 ostr-0.052
 peac-0.052
work-0.051
Token there
Token ID612
Feature activation-1.11e+00

Pos logit contributions
 ost+0.004
ric+0.004
 peac+0.004
 ostr+0.004
work+0.004
Neg logit contributions
iddled-0.003
 aback-0.003
uster-0.002
 tant-0.002
ocated-0.002
Token was
Token ID373
Feature activation-4.28e-02

Pos logit contributions
iddled+0.090
 aback+0.081
uster+0.079
 tant+0.075
bench+0.075
Neg logit contributions
 ost-0.046
ric-0.043
 ostr-0.040
 peac-0.040
work-0.038
Token a
Token ID257
Feature activation-5.39e-01

Pos logit contributions
iddled+0.003
 aback+0.002
uster+0.002
 tant+0.002
bench+0.002
Neg logit contributions
 ost-0.003
ric-0.003
 peac-0.002
 ostr-0.002
work-0.002
Token little
Token ID1310
Feature activation-2.63e-01

Pos logit contributions
iddled+0.025
uster+0.022
 tant+0.022
 aback+0.020
ocated+0.020
Neg logit contributions
ric-0.038
 ost-0.036
work-0.034
 highlight-0.033
 peac-0.031
Token girl
Token ID2576
Feature activation-8.17e-01

Pos logit contributions
iddled+0.017
 aback+0.015
uster+0.015
 tant+0.014
bench+0.014
Neg logit contributions
ric-0.014
 ost-0.014
 highlight-0.013
 peac-0.013
work-0.012
Token named
Token ID3706
Feature activation+2.51e+00

Pos logit contributions
iddled+0.057
 aback+0.051
uster+0.049
bench+0.049
 tant+0.047
Neg logit contributions
ric-0.038
 highlight-0.036
 ost-0.036
work-0.032
 moral-0.032
Token Lily
Token ID20037
Feature activation-1.67e+00

Pos logit contributions
 ost+0.180
ric+0.173
 ostr+0.169
 peac+0.168
work+0.164
Neg logit contributions
iddled-0.127
 aback-0.106
uster-0.101
 tant-0.093
bench-0.093
Token.
Token ID13
Feature activation+9.00e-02

Pos logit contributions
iddled+0.093
 aback+0.080
uster+0.076
bench+0.072
 tant+0.071
Neg logit contributions
 ost-0.109
ric-0.105
 peac-0.100
 ostr-0.099
 highlight-0.098
Token and
Token ID290
Feature activation-2.79e-01

Pos logit contributions
 ost+0.062
ric+0.061
 moral+0.058
work+0.058
 ostr+0.057
Neg logit contributions
iddled-0.076
 aback-0.066
uster-0.064
bench-0.061
ocated-0.061
Token started
Token ID2067
Feature activation-1.27e+00

Pos logit contributions
iddled+0.018
 aback+0.016
uster+0.015
 tant+0.014
ocated+0.014
Neg logit contributions
 ost-0.016
ric-0.015
 ostr-0.015
 peac-0.015
 moral-0.014
Token to
Token ID284
Feature activation-2.87e-01

Pos logit contributions
iddled+0.064
 aback+0.055
 tant+0.050
bench+0.048
uster+0.047
Neg logit contributions
 ost-0.092
ric-0.087
 ostr-0.086
 peac-0.085
 highlight-0.084
Token cry
Token ID3960
Feature activation-6.72e-01

Pos logit contributions
iddled+0.019
 aback+0.017
uster+0.016
 tant+0.015
bench+0.015
Neg logit contributions
 ost-0.016
ric-0.015
 ostr-0.015
 peac-0.015
work-0.014
Token.
Token ID13
Feature activation+9.01e-02

Pos logit contributions
iddled+0.041
 aback+0.036
uster+0.034
bench+0.032
 tant+0.032
Neg logit contributions
 ost-0.040
ric-0.039
 ostr-0.037
 peac-0.037
work-0.036
Token Lily
Token ID20037
Feature activation-1.50e+00

Pos logit contributions
 ost+0.005
ric+0.005
 moral+0.005
 ostr+0.005
 peac+0.005
Neg logit contributions
iddled-0.005
 aback-0.005
uster-0.004
ocated-0.004
 tant-0.004
Token felt
Token ID2936
Feature activation-4.12e-01

Pos logit contributions
iddled+0.087
 aback+0.076
 tant+0.066
ocated+0.066
uster+0.064
Neg logit contributions
 ost-0.097
ric-0.096
 highlight-0.089
 peac-0.087
work-0.086
Token bad
Token ID2089
Feature activation+1.23e-01

Pos logit contributions
iddled+0.031
uster+0.027
 aback+0.027
bench+0.026
ocated+0.026
Neg logit contributions
 ost-0.019
ric-0.018
 ostr-0.017
 peac-0.017
 moral-0.017
Token but
Token ID475
Feature activation-1.62e+00

Pos logit contributions
 ost+0.007
ric+0.007
work+0.007
 moral+0.006
 ostr+0.006
Neg logit contributions
iddled-0.008
 aback-0.007
uster-0.007
bench-0.006
 tant-0.006
Token she
Token ID673
Feature activation-1.17e-03

Pos logit contributions
iddled+0.094
 aback+0.081
ocated+0.072
uster+0.070
bench+0.069
Neg logit contributions
ric-0.109
 ost-0.108
 ostr-0.098
 peac-0.097
 flaming-0.096
Token still
Token ID991
Feature activation-7.37e-01

Pos logit contributions
iddled+0.000
 aback+0.000
uster+0.000
 tant+0.000
ocated+0.000
Neg logit contributions
 ost-0.000
ric-0.000
 peac-0.000
 ostr-0.000
work-0.000
Token Lily
Token ID20037
Feature activation-1.11e+00

Pos logit contributions
ric+0.075
 ost+0.071
 highlight+0.068
work+0.067
 North+0.066
Neg logit contributions
iddled-0.031
 aback-0.027
 tant-0.024
bench-0.022
 shoved-0.019
Token said
Token ID531
Feature activation+4.08e-01

Pos logit contributions
iddled+0.075
uster+0.067
 aback+0.064
ocated+0.062
wn+0.060
Neg logit contributions
 ost-0.058
 ostr-0.055
 peac-0.054
 moral-0.054
ric-0.053
Token,
Token ID11
Feature activation+4.25e-01

Pos logit contributions
 ost+0.021
ric+0.020
work+0.020
 ostr+0.019
 peac+0.019
Neg logit contributions
iddled-0.028
 aback-0.024
uster-0.023
 tant-0.022
ocated-0.022
Token rubbing
Token ID27714
Feature activation+7.35e-01

Pos logit contributions
 ost+0.021
ric+0.020
 peac+0.019
 ostr+0.019
work+0.018
Neg logit contributions
iddled-0.030
 aback-0.027
uster-0.026
bench-0.025
ocated-0.025
Token her
Token ID607
Feature activation-1.08e+00

Pos logit contributions
 ost+0.048
ric+0.048
 ostr+0.044
 flaming+0.044
 moral+0.044
Neg logit contributions
iddled-0.039
 aback-0.034
uster-0.033
ocated-0.031
bench-0.030
Token belly
Token ID19921
Feature activation-7.55e-01

Pos logit contributions
iddled+0.065
 aback+0.058
uster+0.054
 tant+0.053
bench+0.051
Neg logit contributions
 ost-0.067
ric-0.064
 peac-0.062
 ostr-0.061
work-0.060
Token.
Token ID13
Feature activation+2.27e-01

Pos logit contributions
iddled+0.048
 aback+0.041
uster+0.040
ocated+0.038
 tant+0.037
Neg logit contributions
 ost-0.043
ric-0.041
 ostr-0.040
 peac-0.039
work-0.039
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
 ost+0.011
ric+0.011
 peac+0.010
 ostr+0.010
work+0.010
Neg logit contributions
iddled-0.016
 aback-0.014
uster-0.014
 tant-0.013
bench-0.013
Token
Token ID198
Feature activation-1.69e-01

Pos logit contributions
iddled+0.016
 aback+0.015
uster+0.014
 tant+0.014
ocated+0.013
Neg logit contributions
 ost-0.009
ric-0.009
 ostr-0.008
 peac-0.008
 moral-0.008
TokenSam
Token ID16305
Feature activation-6.08e-01

Pos logit contributions
iddled+0.010
 aback+0.008
uster+0.008
 tant+0.008
bench+0.007
Neg logit contributions
 ost-0.011
ric-0.011
 peac-0.010
 ostr-0.010
 moral-0.010
Token felt
Token ID2936
Feature activation+3.97e-02

Pos logit contributions
iddled+0.040
 aback+0.035
uster+0.034
 tant+0.032
bench+0.032
Neg logit contributions
 ost-0.033
ric-0.032
 ostr-0.031
 peac-0.031
work-0.030
Token yellow
Token ID7872
Feature activation+6.21e-01

Pos logit contributions
 ost+0.046
ric+0.046
work+0.044
 peac+0.043
 highlight+0.042
Neg logit contributions
iddled-0.047
uster-0.041
 aback-0.040
 tant-0.040
bench-0.038
Token scarf
Token ID36953
Feature activation-1.59e+00

Pos logit contributions
 ost+0.045
ric+0.043
 peac+0.042
work+0.041
 ostr+0.041
Neg logit contributions
iddled-0.029
 aback-0.024
uster-0.024
 tant-0.022
bench-0.022
Token was
Token ID373
Feature activation+2.28e-01

Pos logit contributions
iddled+0.130
 aback+0.118
uster+0.117
 tant+0.109
ocated+0.107
Neg logit contributions
 ost-0.061
ric-0.057
 ostr-0.056
 peac-0.054
work-0.053
Token soft
Token ID2705
Feature activation-2.47e+00

Pos logit contributions
 ost+0.012
ric+0.011
 ostr+0.011
 peac+0.011
 moral+0.011
Neg logit contributions
iddled-0.016
 aback-0.014
uster-0.013
ocated-0.013
 tant-0.013
Token and
Token ID290
Feature activation-2.12e-01

Pos logit contributions
iddled+0.192
uster+0.163
 aback+0.160
 tant+0.155
wn+0.152
Neg logit contributions
work-0.105
 ost-0.103
 ostr-0.100
 North-0.098
 zoo-0.096
Token warm
Token ID5814
Feature activation-2.01e+00

Pos logit contributions
iddled+0.014
 aback+0.013
uster+0.012
 tant+0.012
ocated+0.011
Neg logit contributions
 ost-0.011
ric-0.011
 ostr-0.011
 peac-0.010
 moral-0.010
Token.
Token ID13
Feature activation+3.53e-02

Pos logit contributions
iddled+0.150
uster+0.128
 aback+0.126
 tant+0.122
ocated+0.118
Neg logit contributions
 ost-0.094
work-0.093
 ostr-0.088
ric-0.087
 hipp-0.082
Token His
Token ID2399
Feature activation+7.66e-01

Pos logit contributions
 ost+0.002
ric+0.002
 ostr+0.002
 moral+0.002
 peac+0.002
Neg logit contributions
iddled-0.002
 aback-0.002
uster-0.002
ocated-0.002
 tant-0.002
Token mom
Token ID1995
Feature activation+2.35e+00

Pos logit contributions
 ost+0.054
ric+0.053
work+0.051
 peac+0.051
 highlight+0.050
Neg logit contributions
iddled-0.037
 aback-0.030
uster-0.030
 tant-0.029
bench-0.028
Token gave
Token ID2921
Feature activation+3.20e-01

Pos logit contributions
 ost+0.132
ric+0.126
 ostr+0.122
 peac+0.121
work+0.118
Neg logit contributions
iddled-0.151
 aback-0.133
uster-0.129
 tant-0.122
bench-0.120
Token it
Token ID340
Feature activation-9.83e-01

Pos logit contributions
 ost+0.021
 ostr+0.020
ric+0.019
 hipp+0.018
 flaming+0.018
Neg logit contributions
iddled-0.019
uster-0.016
 aback-0.015
ocated-0.015
bench-0.015
Token is
Token ID318
Feature activation-1.71e-01

Pos logit contributions
iddled+0.020
uster+0.019
bench+0.017
 aback+0.017
wn+0.017
Neg logit contributions
 ost-0.013
 ostr-0.012
 moral-0.012
ric-0.012
 zoo-0.011
Token not
Token ID407
Feature activation+7.85e-01

Pos logit contributions
iddled+0.013
 aback+0.011
uster+0.011
 tant+0.011
bench+0.011
Neg logit contributions
 ost-0.008
ric-0.008
 ostr-0.007
 peac-0.007
 moral-0.007
Token scared
Token ID12008
Feature activation+3.06e-01

Pos logit contributions
 ost+0.032
 ostr+0.029
 flaming+0.027
 rob+0.027
 peac+0.027
Neg logit contributions
iddled-0.066
uster-0.058
 tant-0.057
 aback-0.054
ocated-0.053
Token of
Token ID286
Feature activation+9.73e-01

Pos logit contributions
 ost+0.016
ric+0.014
 ostr+0.014
 moral+0.014
 peac+0.014
Neg logit contributions
iddled-0.023
 aback-0.019
uster-0.018
bench-0.018
ocated-0.018
Token the
Token ID262
Feature activation+7.45e-01

Pos logit contributions
 ost+0.059
ric+0.058
 peac+0.055
 ostr+0.054
work+0.054
Neg logit contributions
iddled-0.058
 aback-0.051
uster-0.048
 tant-0.045
ocated-0.045
Token dog
Token ID3290
Feature activation-5.09e-01

Pos logit contributions
 ost+0.035
ric+0.032
 ostr+0.031
 peac+0.031
 moral+0.030
Neg logit contributions
iddled-0.057
 aback-0.051
uster-0.049
bench-0.047
ocated-0.046
Token.
Token ID13
Feature activation+8.38e-02

Pos logit contributions
iddled+0.023
 aback+0.021
uster+0.019
ocated+0.019
 tant+0.019
Neg logit contributions
ric-0.036
 ost-0.036
 peac-0.034
 highlight-0.033
 ostr-0.033
Token He
Token ID679
Feature activation-1.72e-01

Pos logit contributions
 ost+0.005
ric+0.005
 ostr+0.005
 peac+0.004
 rob+0.004
Neg logit contributions
iddled-0.005
uster-0.004
 aback-0.004
bench-0.004
ocated-0.004
Token walks
Token ID11114
Feature activation-4.91e-01

Pos logit contributions
iddled+0.010
 aback+0.009
uster+0.008
 tant+0.008
ocated+0.007
Neg logit contributions
 ost-0.011
ric-0.011
 peac-0.010
 ostr-0.010
work-0.010
Token to
Token ID284
Feature activation+1.75e-02

Pos logit contributions
iddled+0.030
uster+0.026
 aback+0.023
bench+0.022
ocated+0.022
Neg logit contributions
 ost-0.031
 ostr-0.028
 moral-0.028
 zoo-0.028
work-0.027
Token the
Token ID262
Feature activation+6.91e-01

Pos logit contributions
 ost+0.001
ric+0.001
 ostr+0.001
 peac+0.001
work+0.001
Neg logit contributions
iddled-0.001
 aback-0.001
uster-0.001
 tant-0.001
bench-0.001
Token with
Token ID351
Feature activation-9.65e-01

Pos logit contributions
 moral+0.045
 ost+0.043
 zoo+0.042
 hipp+0.041
work+0.041
Neg logit contributions
iddled-0.062
uster-0.056
 aback-0.053
wn-0.048
bench-0.048
Token him
Token ID683
Feature activation-1.86e+00

Pos logit contributions
iddled+0.049
 aback+0.042
uster+0.040
 tant+0.037
bench+0.037
Neg logit contributions
 ost-0.068
ric-0.065
 ostr-0.063
 peac-0.063
work-0.061
Token.
Token ID13
Feature activation-7.48e-02

Pos logit contributions
iddled+0.092
 aback+0.079
uster+0.072
 tant+0.072
ocated+0.069
Neg logit contributions
 ost-0.133
ric-0.127
 peac-0.126
 ostr-0.123
 rob-0.121
Token Then
Token ID3244
Feature activation+1.18e+00

Pos logit contributions
iddled+0.004
 aback+0.004
uster+0.004
 tant+0.004
bench+0.003
Neg logit contributions
 ost-0.005
ric-0.004
 peac-0.004
 ostr-0.004
 highlight-0.004
Token an
Token ID281
Feature activation-6.88e-01

Pos logit contributions
ric+0.102
 ost+0.095
 highlight+0.092
work+0.091
 ostr+0.089
Neg logit contributions
iddled-0.040
 aback-0.038
 away-0.029
 tant-0.026
ocated-0.026
Token idea
Token ID2126
Feature activation-5.34e+00

Pos logit contributions
iddled+0.041
 aback+0.035
uster+0.034
 tant+0.032
bench+0.031
Neg logit contributions
 ost-0.043
ric-0.042
 peac-0.039
 ostr-0.039
work-0.039
Token came
Token ID1625
Feature activation+3.78e-01

Pos logit contributions
iddled+0.356
uster+0.324
 aback+0.319
 tant+0.309
bench+0.291
Neg logit contributions
 ost-0.280
 ostr-0.260
 peac-0.257
work-0.255
 hipp-0.241
Token to
Token ID284
Feature activation-4.17e-01

Pos logit contributions
 ost+0.029
ric+0.028
 ostr+0.027
 peac+0.027
 highlight+0.027
Neg logit contributions
iddled-0.018
 aback-0.016
uster-0.014
ocated-0.012
bench-0.012
Token him
Token ID683
Feature activation-1.84e+00

Pos logit contributions
iddled+0.023
 aback+0.020
uster+0.018
 tant+0.017
bench+0.017
Neg logit contributions
 ost-0.028
ric-0.027
 ostr-0.026
 peac-0.026
 highlight-0.025
Token.
Token ID13
Feature activation-1.62e-01

Pos logit contributions
iddled+0.087
 aback+0.076
uster+0.069
bench+0.064
ocated+0.063
Neg logit contributions
 ost-0.139
ric-0.131
 peac-0.129
 ostr-0.128
 flaming-0.126
Token He
Token ID679
Feature activation-3.44e-01

Pos logit contributions
iddled+0.011
uster+0.009
 aback+0.009
 tant+0.009
wn+0.009
Neg logit contributions
 ost-0.009
ric-0.008
 ostr-0.008
work-0.008
 peac-0.008
Token desk
Token ID6915
Feature activation+3.88e-01

Pos logit contributions
ric+0.030
 ost+0.030
 peac+0.027
str+0.026
orse+0.026
Neg logit contributions
iddled-0.019
 aback-0.017
 tant-0.017
uster-0.017
ocated-0.017
Token,
Token ID11
Feature activation-4.78e-02

Pos logit contributions
 ost+0.026
ric+0.025
 peac+0.024
 ostr+0.024
 highlight+0.023
Neg logit contributions
iddled-0.021
 aback-0.018
uster-0.017
bench-0.016
ocated-0.016
Token and
Token ID290
Feature activation-2.08e-01

Pos logit contributions
iddled+0.002
 aback+0.002
uster+0.001
ocated+0.001
 tant+0.001
Neg logit contributions
 ost-0.004
ric-0.004
 highlight-0.003
str-0.003
 peac-0.003
Token a
Token ID257
Feature activation-4.04e-01

Pos logit contributions
iddled+0.010
 aback+0.009
ocated+0.008
 tant+0.008
uster+0.008
Neg logit contributions
ric-0.014
 ost-0.014
str-0.013
 ostr-0.013
 peac-0.013
Token wet
Token ID9583
Feature activation-9.66e-01

Pos logit contributions
 tant+0.018
iddled+0.017
 aback+0.016
 knot+0.015
uster+0.015
Neg logit contributions
ric-0.028
 ost-0.028
work-0.026
 highlight-0.025
riage-0.024
Token spot
Token ID4136
Feature activation-5.24e+00

Pos logit contributions
iddled+0.054
 aback+0.048
uster+0.046
 tant+0.044
bench+0.043
Neg logit contributions
 ost-0.062
ric-0.059
 highlight-0.055
 peac-0.055
 ostr-0.055
Token on
Token ID319
Feature activation+8.76e-01

Pos logit contributions
iddled+0.280
 aback+0.241
uster+0.226
bench+0.215
 tant+0.211
Neg logit contributions
 ost-0.352
ric-0.342
 peac-0.327
 ostr-0.326
 highlight-0.317
Token the
Token ID262
Feature activation+4.54e-01

Pos logit contributions
 ost+0.054
ric+0.052
 ostr+0.050
 peac+0.049
work+0.048
Neg logit contributions
iddled-0.052
 aback-0.046
uster-0.044
 tant-0.041
bench-0.041
Token rug
Token ID14477
Feature activation-6.71e-02

Pos logit contributions
ric+0.031
 ost+0.031
 peac+0.028
 rob+0.027
str+0.027
Neg logit contributions
iddled-0.021
 aback-0.019
 tant-0.019
uster-0.019
ocated-0.018
Token.
Token ID13
Feature activation+3.50e-02

Pos logit contributions
iddled+0.004
 aback+0.003
uster+0.003
bench+0.003
ocated+0.003
Neg logit contributions
 ost-0.005
ric-0.004
 peac-0.004
 ostr-0.004
 rob-0.004
Token Who
Token ID5338
Feature activation+4.60e+00

Pos logit contributions
 ost+0.002
ric+0.002
 peac+0.002
 ostr+0.002
 highlight+0.002
Neg logit contributions
iddled-0.002
 aback-0.002
uster-0.002
ocated-0.002
zip-0.002
Token,
Token ID11
Feature activation-1.92e-01

Pos logit contributions
 ost+0.129
ric+0.124
 ostr+0.119
 peac+0.118
work+0.117
Neg logit contributions
iddled-0.113
 aback-0.097
uster-0.093
bench-0.086
 tant-0.086
Token but
Token ID475
Feature activation-1.62e+00

Pos logit contributions
iddled+0.008
 aback+0.007
 tant+0.006
uster+0.006
bench+0.006
Neg logit contributions
ric-0.015
 ost-0.015
 peac-0.014
work-0.013
 ostr-0.013
Token Jamie
Token ID17826
Feature activation-8.04e-01

Pos logit contributions
iddled+0.088
 aback+0.074
ocated+0.060
bench+0.059
uster+0.058
Neg logit contributions
ric-0.115
 ost-0.109
 peac-0.106
 flaming-0.103
 ostr-0.101
Token had
Token ID550
Feature activation+3.08e+00

Pos logit contributions
iddled+0.043
 aback+0.038
bench+0.034
uster+0.033
 tant+0.033
Neg logit contributions
ric-0.054
 ost-0.054
 peac-0.049
 highlight-0.049
 North-0.048
Token an
Token ID281
Feature activation-5.53e-01

Pos logit contributions
 ost+0.175
ric+0.170
 ostr+0.160
 peac+0.156
work+0.156
Neg logit contributions
iddled-0.200
 aback-0.181
uster-0.164
 tant-0.163
bench-0.161
Token idea
Token ID2126
Feature activation-5.38e+00

Pos logit contributions
iddled+0.030
 aback+0.025
uster+0.024
ocated+0.023
 tant+0.022
Neg logit contributions
 ost-0.036
 ostr-0.035
 moral-0.035
ric-0.034
 peac-0.033
Token.
Token ID13
Feature activation+4.34e-02

Pos logit contributions
iddled+0.333
 aback+0.290
uster+0.282
 tant+0.266
bench+0.260
Neg logit contributions
 ost-0.320
ric-0.303
 ostr-0.293
 peac-0.291
work-0.285
Token
Token ID198
Feature activation-3.38e-01

Pos logit contributions
 ost+0.003
ric+0.002
 ostr+0.002
 peac+0.002
work+0.002
Neg logit contributions
iddled-0.003
 aback-0.002
uster-0.002
 tant-0.002
ocated-0.002
Token
Token ID198
Feature activation-3.04e-01

Pos logit contributions
iddled+0.028
uster+0.025
 aback+0.025
 tant+0.025
wn+0.024
Neg logit contributions
 ost-0.012
ric-0.011
 moral-0.011
 ostr-0.010
 peac-0.010
TokenHe
Token ID1544
Feature activation+4.19e-01

Pos logit contributions
iddled+0.018
 aback+0.016
uster+0.016
 tant+0.016
ocated+0.015
Neg logit contributions
 ost-0.017
 moral-0.016
ric-0.016
 ostr-0.016
 peac-0.016
Token said
Token ID531
Feature activation-9.95e-02

Pos logit contributions
 ost+0.024
ric+0.023
 ostr+0.023
 peac+0.023
 moral+0.022
Neg logit contributions
iddled-0.026
 aback-0.023
uster-0.022
 tant-0.021
bench-0.021
Token to
Token ID284
Feature activation-3.55e-01

Pos logit contributions
iddled+0.043
 aback+0.037
uster+0.035
bench+0.033
 tant+0.032
Neg logit contributions
 ost-0.058
ric-0.057
 peac-0.055
 ostr-0.055
 rob-0.054
Token put
Token ID1234
Feature activation-2.55e+00

Pos logit contributions
iddled+0.025
 aback+0.022
uster+0.021
 tant+0.020
ocated+0.020
Neg logit contributions
 ost-0.018
ric-0.017
 ostr-0.017
 peac-0.016
 moral-0.016
Token it
Token ID340
Feature activation-1.13e+00

Pos logit contributions
iddled+0.165
 aback+0.145
uster+0.143
ocated+0.139
 tant+0.139
Neg logit contributions
 ost-0.137
ric-0.127
 peac-0.123
work-0.121
 ostr-0.121
Token on
Token ID319
Feature activation+6.92e-01

Pos logit contributions
iddled+0.069
 aback+0.061
uster+0.058
 tant+0.055
bench+0.054
Neg logit contributions
 ost-0.067
ric-0.064
 peac-0.061
 ostr-0.061
work-0.061
Token.
Token ID13
Feature activation+7.96e-02

Pos logit contributions
 ost+0.046
ric+0.045
 ostr+0.043
 peac+0.043
work+0.042
Neg logit contributions
iddled-0.038
 aback-0.033
uster-0.031
 tant-0.029
bench-0.029
Token First
Token ID3274
Feature activation-5.94e+00

Pos logit contributions
 ost+0.005
 peac+0.005
ric+0.005
work+0.005
 highlight+0.005
Neg logit contributions
iddled-0.004
 aback-0.004
uster-0.003
ocated-0.003
bench-0.003
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
iddled+0.314
 aback+0.270
uster+0.254
bench+0.237
ocated+0.235
Neg logit contributions
 ost-0.400
ric-0.399
 peac-0.375
work-0.370
 highlight-0.369
Token her
Token ID607
Feature activation-1.61e+00

Pos logit contributions
iddled+0.006
 aback+0.005
uster+0.005
ocated+0.005
 tant+0.005
Neg logit contributions
ric-0.007
 ost-0.006
 peac-0.006
work-0.006
 moral-0.006
Token mom
Token ID1995
Feature activation+2.39e+00

Pos logit contributions
iddled+0.103
uster+0.088
 aback+0.087
 tant+0.085
ocated+0.078
Neg logit contributions
 ost-0.092
ric-0.090
 peac-0.080
work-0.079
 ostr-0.078
Token helped
Token ID4193
Feature activation-2.64e+00

Pos logit contributions
 ost+0.145
ric+0.140
 ostr+0.133
 peac+0.133
work+0.129
Neg logit contributions
iddled-0.144
 aback-0.126
uster-0.120
 tant-0.113
bench-0.113
Token her
Token ID607
Feature activation-1.61e+00

Pos logit contributions
iddled+0.133
 aback+0.109
uster+0.109
bench+0.103
 tant+0.102
Neg logit contributions
 ost-0.193
 ostr-0.179
ric-0.174
 rob-0.169
work-0.163
Token Suddenly
Token ID24975
Feature activation+1.59e+00

Pos logit contributions
 ost+0.002
ric+0.002
 ostr+0.002
 peac+0.002
work+0.002
Neg logit contributions
iddled-0.002
 aback-0.002
uster-0.002
 tant-0.002
bench-0.002
Token,
Token ID11
Feature activation-2.48e-02

Pos logit contributions
 ost+0.090
 peac+0.083
ric+0.083
 ostr+0.083
 moral+0.080
Neg logit contributions
iddled-0.103
 aback-0.088
uster-0.088
bench-0.083
 tant-0.082
Token Molly
Token ID30236
Feature activation-2.19e+00

Pos logit contributions
iddled+0.001
 aback+0.001
uster+0.001
 tant+0.001
bench+0.001
Neg logit contributions
 ost-0.002
ric-0.001
 ostr-0.001
 peac-0.001
work-0.001
Token had
Token ID550
Feature activation+3.19e+00

Pos logit contributions
iddled+0.117
 aback+0.100
ocated+0.091
uster+0.090
 tant+0.087
Neg logit contributions
ric-0.146
 ost-0.143
 highlight-0.137
work-0.135
riage-0.133
Token an
Token ID281
Feature activation-4.52e-01

Pos logit contributions
 ost+0.182
ric+0.175
 ostr+0.167
 peac+0.166
work+0.162
Neg logit contributions
iddled-0.205
 aback-0.181
uster-0.173
 tant-0.163
bench-0.162
Token idea
Token ID2126
Feature activation-5.30e+00

Pos logit contributions
iddled+0.025
 aback+0.021
uster+0.020
 tant+0.019
ocated+0.019
Neg logit contributions
 ost-0.030
 ostr-0.029
 moral-0.029
 peac-0.027
ric-0.027
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
iddled+0.331
 aback+0.287
uster+0.282
 tant+0.270
bench+0.259
Neg logit contributions
 ost-0.314
ric-0.293
 ostr-0.287
 peac-0.284
work-0.277
Token She
Token ID1375
Feature activation+5.73e-02

Pos logit contributions
 ost+0.001
ric+0.001
 moral+0.001
 peac+0.001
 ostr+0.001
Neg logit contributions
iddled-0.001
uster-0.001
 tant-0.001
 aback-0.001
wn-0.001
Token went
Token ID1816
Feature activation+3.84e-01

Pos logit contributions
 ost+0.004
ric+0.004
 ostr+0.003
 peac+0.003
work+0.003
Neg logit contributions
iddled-0.003
 aback-0.003
uster-0.003
 tant-0.003
bench-0.003
Token inside
Token ID2641
Feature activation+7.78e-01

Pos logit contributions
 ost+0.023
ric+0.021
 ostr+0.021
 peac+0.021
work+0.020
Neg logit contributions
iddled-0.024
 aback-0.020
uster-0.020
 tant-0.019
bench-0.019
Token her
Token ID607
Feature activation-1.43e+00

Pos logit contributions
 ost+0.043
ric+0.042
 moral+0.041
 ostr+0.040
work+0.039
Neg logit contributions
iddled-0.049
uster-0.043
 aback-0.041
ocated-0.040
wn-0.039