TOP ACTIVATIONS
MAX = 15.410

placed it onto the wheel bar row . John
harder to push the wheel bar row . But her backyard
He jumped onto the wheel bar row and started rolling around
back with a big wheel bar row . He asked the
. She saw a wheel bar row , a large sp
a big , spinning wheel bar row and put the pumpkin
him a big red wheel bar row and filled it with
the cat off the wheel bar row and put him back
dolls around in a wheel bar row she had found in
. He found a wheel bar row , a tr amp
The wheel bar row wheel ed the cup
uffy had made the wheel bar row much lighter . The
much lighter . The wheel bar row was now much easier
of soil into the wheel bar row . It was heavy
filled up lots of wheel bar rows with the waste and
it away in a wheel bar row . Once
was wheel ing the wheel bar row around she made sure
fun . Soon the wheel bar row was empty and all
light en up the wheel bar row . <|endoftext|> Once there
whistle . The train was arriving ! Exc ited ly ,

MIN ACTIVATIONS
MIN = -13.378

he passed it to another child , who also looked at
was a mom and a child who liked to go for
<|endoftext|> L ily was a child who loved to whistle .
You 're a very smart child !" The j
? â The child said ,
offered to help the other child organize his things into the
So the child and Mom my sn ugg
is a picture of a child with a sad face and
One day , a little child was playing in the town
and a 3 year old child . The mom my was
seen . The child was so happy . From
He went over to the child who was yelling and asked
down to see a small child standing with its arms folded
" Let the child decide ," said Mum stern
sand box . The other child shouted : " Help !
to everyone . So the child started to sing a special
compassionate , and the small child was always dressed nicely .
sky . Suddenly , the child heard a noise . He
the honey and thanked the child again . From
closed . The child smiled and asked the witch

INTERVAL 8.213 - 15.410
CONTAINS 3.924%

<|endoftext|> Once upon a time , a little girl named Lily
demanded . Finally , the door opened and an
. " Ring , ring , ring , we
and his dad lost everything , including their golf clubs .
played with his cars again , but he kept them clean

INTERVAL 1.016 - 8.213
CONTAINS 29.123%

Then , Lily got lost and started to cry
J enny thought for a moment and said , " I
Lily , I found your car !" Max says . He
?" N ana smiled and pointed to an old
We have to pray for them and the people in the

INTERVAL -6.181 - 1.016
CONTAINS 62.054%

it off , but it just got worse and worse .
fire engine . It 's red and shiny and has a
They make a loud noise . They hit the floor and
, the birds and the squirrel s . He ran ahead
a y ummy sandwich available for her . Lily was very

INTERVAL -13.378 - -6.181
CONTAINS 4.899%

. Even though she was only small , she had done
moment and said , " We need an intelligent plan to
take it home . Her mom said yes , but they
time , there was a little girl named Lily . She
time , there was a little bear . The little bear
Token placed
Token ID4624
Feature activation+4.89e+00

Pos logit contributions
 virtue+0.136
vous+0.134
rig+0.132
 importance+0.128
Yes+0.126
Neg logit contributions
 down-0.113
ged-0.111
iked-0.107
 onward-0.100
am-0.097
Token it
Token ID340
Feature activation+3.06e+00

Pos logit contributions
ged+0.115
 down+0.114
iked+0.109
 onward+0.102
ls+0.097
Neg logit contributions
vous-0.180
 virtue-0.180
rig-0.177
 importance-0.173
Yes-0.172
Token onto
Token ID4291
Feature activation+1.46e+00

Pos logit contributions
iked+0.089
ged+0.087
 inspection+0.082
 onward+0.081
leys+0.080
Neg logit contributions
 importance-0.074
vous-0.073
 bit-0.073
Yes-0.072
rig-0.072
Token the
Token ID262
Feature activation+4.64e-01

Pos logit contributions
 down+0.034
ged+0.031
 onward+0.028
,+0.028
iked+0.028
Neg logit contributions
vous-0.057
rig-0.056
 virtue-0.055
leaf-0.053
 importance-0.053
Token wheel
Token ID7825
Feature activation+4.43e-01

Pos logit contributions
 down+0.012
ged+0.011
,+0.010
 onward+0.010
iked+0.010
Neg logit contributions
vous-0.017
rig-0.016
 virtue-0.016
leaf-0.016
Yes-0.015
Tokenbar
Token ID5657
Feature activation+1.54e+01

Pos logit contributions
ged+0.010
iked+0.010
 down+0.010
 onward+0.009
ls+0.009
Neg logit contributions
vous-0.016
 virtue-0.016
rig-0.016
Yes-0.016
 importance-0.015
Tokenrow
Token ID808
Feature activation+5.07e+00

Pos logit contributions
ged+0.375
iked+0.363
 down+0.360
 onward+0.348
ls+0.338
Neg logit contributions
vous-0.521
 virtue-0.520
rig-0.511
 importance-0.491
Yes-0.485
Token.
Token ID13
Feature activation+4.30e-01

Pos logit contributions
ged+0.128
iked+0.126
 down+0.118
ls+0.117
 onward+0.116
Neg logit contributions
 virtue-0.163
vous-0.159
rig-0.157
 importance-0.156
Yes-0.153
Token
Token ID198
Feature activation-9.60e-01

Pos logit contributions
ged+0.009
 down+0.009
iked+0.009
 onward+0.008
ls+0.008
Neg logit contributions
 virtue-0.016
vous-0.016
rig-0.016
Yes-0.016
 importance-0.016
Token
Token ID198
Feature activation-9.56e-01

Pos logit contributions
 virtue+0.037
vous+0.037
 matter+0.037
 importance+0.036
 least+0.035
Neg logit contributions
ged-0.019
iked-0.019
 down-0.019
 onward-0.019
leys-0.017
TokenJohn
Token ID7554
Feature activation+1.79e+00

Pos logit contributions
vous+0.029
 virtue+0.029
rig+0.029
 importance+0.028
 matter+0.028
Neg logit contributions
iked-0.027
ged-0.026
 onward-0.025
 down-0.025
leys-0.024
Token harder
Token ID7069
Feature activation+2.97e+00

Pos logit contributions
 virtue+0.158
vous+0.155
rig+0.153
 importance+0.147
leaf+0.142
Neg logit contributions
 down-0.123
ged-0.114
iked-0.104
 onward-0.102
,-0.099
Token to
Token ID284
Feature activation-2.37e+00

Pos logit contributions
iked+0.070
ged+0.069
 down+0.065
 onward+0.064
leys+0.063
Neg logit contributions
 virtue-0.104
rig-0.101
 importance-0.101
vous-0.100
Yes-0.099
Token push
Token ID4574
Feature activation+2.86e+00

Pos logit contributions
vous+0.078
 virtue+0.077
rig+0.076
 importance+0.074
leaf+0.072
Neg logit contributions
 down-0.071
ged-0.064
,-0.059
 onward-0.058
 his-0.057
Token the
Token ID262
Feature activation+1.81e-01

Pos logit contributions
 down+0.066
ged+0.065
iked+0.059
 onward+0.058
ls+0.054
Neg logit contributions
vous-0.109
 virtue-0.108
rig-0.107
 importance-0.105
Yes-0.103
Token wheel
Token ID7825
Feature activation+4.10e-02

Pos logit contributions
 down+0.005
ged+0.004
,+0.004
ls+0.004
 onward+0.004
Neg logit contributions
vous-0.007
rig-0.007
 virtue-0.006
Yes-0.006
leaf-0.006
Tokenbar
Token ID5657
Feature activation+1.54e+01

Pos logit contributions
ged+0.001
iked+0.001
 down+0.001
 onward+0.001
leys+0.001
Neg logit contributions
 virtue-0.002
vous-0.002
rig-0.002
Yes-0.002
 importance-0.001
Tokenrow
Token ID808
Feature activation+4.99e+00

Pos logit contributions
ged+0.285
iked+0.276
 down+0.274
 onward+0.251
ls+0.237
Neg logit contributions
 virtue-0.621
vous-0.620
rig-0.612
Yes-0.598
 importance-0.597
Token.
Token ID13
Feature activation+3.95e-01

Pos logit contributions
iked+0.117
ged+0.117
 down+0.104
 onward+0.102
leys+0.102
Neg logit contributions
 virtue-0.177
vous-0.171
rig-0.170
Yes-0.167
 importance-0.166
Token But
Token ID887
Feature activation-3.31e+00

Pos logit contributions
 down+0.008
ged+0.008
iked+0.008
 onward+0.007
am+0.006
Neg logit contributions
vous-0.016
 virtue-0.016
rig-0.015
 importance-0.015
leaf-0.015
Token her
Token ID607
Feature activation+4.85e+00

Pos logit contributions
vous+0.123
rig+0.121
 virtue+0.118
leaf+0.116
 importance+0.114
Neg logit contributions
 down-0.088
ged-0.084
iked-0.077
 onward-0.076
,-0.076
Token backyard
Token ID24296
Feature activation+5.48e+00

Pos logit contributions
 down+0.113
,+0.110
am+0.109
ged+0.101
iked+0.097
Neg logit contributions
vous-0.190
leaf-0.186
rig-0.180
Yes-0.173
 virtue-0.173
Token He
Token ID679
Feature activation+5.95e+00

Pos logit contributions
 down+0.011
ged+0.011
iked+0.011
 onward+0.010
am+0.010
Neg logit contributions
vous-0.022
 virtue-0.022
rig-0.022
 importance-0.021
Yes-0.021
Token jumped
Token ID11687
Feature activation+7.80e+00

Pos logit contributions
ged+0.123
 down+0.118
am+0.114
,+0.112
 his+0.107
Neg logit contributions
 virtue-0.245
vous-0.233
leaf-0.224
rig-0.224
 importance-0.217
Token onto
Token ID4291
Feature activation+1.30e+00

Pos logit contributions
iked+0.201
leys+0.192
ged+0.189
am+0.181
 onward+0.164
Neg logit contributions
Yes-0.252
rig-0.248
 virtue-0.241
 importance-0.230
 bit-0.230
Token the
Token ID262
Feature activation+5.15e-01

Pos logit contributions
 down+0.029
ged+0.027
 his+0.025
,+0.024
 onward+0.024
Neg logit contributions
vous-0.054
rig-0.054
 virtue-0.053
 importance-0.050
leaf-0.049
Token wheel
Token ID7825
Feature activation+2.02e-01

Pos logit contributions
 down+0.014
ged+0.014
iked+0.013
 onward+0.013
ls+0.012
Neg logit contributions
vous-0.017
 virtue-0.017
rig-0.017
Yes-0.016
 importance-0.016
Tokenbar
Token ID5657
Feature activation+1.52e+01

Pos logit contributions
ged+0.005
 down+0.005
iked+0.005
 onward+0.005
leys+0.005
Neg logit contributions
 virtue-0.007
vous-0.007
rig-0.006
Yes-0.006
 importance-0.006
Tokenrow
Token ID808
Feature activation+4.91e+00

Pos logit contributions
ged+0.359
iked+0.351
 down+0.346
 onward+0.329
ls+0.321
Neg logit contributions
vous-0.533
 virtue-0.526
rig-0.521
Yes-0.503
 importance-0.498
Token and
Token ID290
Feature activation-3.93e+00

Pos logit contributions
ged+0.125
iked+0.123
 down+0.120
 onward+0.113
leys+0.112
Neg logit contributions
 virtue-0.163
vous-0.162
rig-0.159
Yes-0.157
 importance-0.156
Token started
Token ID2067
Feature activation+5.53e+00

Pos logit contributions
 virtue+0.137
vous+0.136
rig+0.134
 importance+0.131
Yes+0.130
Neg logit contributions
ged-0.100
 down-0.100
iked-0.096
 onward-0.090
ls-0.086
Token rolling
Token ID10708
Feature activation+6.59e+00

Pos logit contributions
ged+0.168
iked+0.168
leys+0.166
 onward+0.163
ls+0.163
Neg logit contributions
Yes-0.143
vous-0.140
rig-0.140
 importance-0.139
 virtue-0.138
Token around
Token ID1088
Feature activation+1.76e+00

Pos logit contributions
iked+0.174
leys+0.160
ged+0.151
am+0.146
 onward+0.142
Neg logit contributions
Yes-0.224
 virtue-0.203
rig-0.201
vous-0.200
 importance-0.198
Token back
Token ID736
Feature activation+6.09e+00

Pos logit contributions
ged+0.167
iked+0.164
ls+0.156
leys+0.151
 onward+0.149
Neg logit contributions
vous-0.252
Yes-0.248
rig-0.246
 virtue-0.243
 importance-0.239
Token with
Token ID351
Feature activation-1.45e+00

Pos logit contributions
 down+0.160
ged+0.155
iked+0.151
 onward+0.142
am+0.133
Neg logit contributions
 virtue-0.212
vous-0.211
rig-0.206
 importance-0.203
Yes-0.200
Token a
Token ID257
Feature activation-3.88e+00

Pos logit contributions
rig+0.050
 virtue+0.049
vous+0.048
leaf+0.046
Yes+0.046
Neg logit contributions
 down-0.040
ged-0.039
 onward-0.036
iked-0.036
,-0.034
Token big
Token ID1263
Feature activation-1.35e+00

Pos logit contributions
vous+0.128
 virtue+0.125
rig+0.125
Yes+0.122
leaf+0.121
Neg logit contributions
 down-0.104
ged-0.101
 onward-0.094
iked-0.094
,-0.092
Token wheel
Token ID7825
Feature activation+2.44e-01

Pos logit contributions
vous+0.050
 virtue+0.050
rig+0.050
Yes+0.048
 importance+0.048
Neg logit contributions
 down-0.031
ged-0.031
iked-0.029
 onward-0.027
ls-0.026
Tokenbar
Token ID5657
Feature activation+1.51e+01

Pos logit contributions
ged+0.006
 down+0.006
iked+0.006
 onward+0.006
leys+0.006
Neg logit contributions
vous-0.008
 virtue-0.008
rig-0.008
Yes-0.008
 importance-0.008
Tokenrow
Token ID808
Feature activation+4.78e+00

Pos logit contributions
ged+0.336
 down+0.332
iked+0.329
 onward+0.310
ls+0.294
Neg logit contributions
vous-0.553
 virtue-0.547
rig-0.537
 importance-0.527
Yes-0.524
Token.
Token ID13
Feature activation+4.61e-01

Pos logit contributions
ged+0.122
iked+0.120
 down+0.119
 onward+0.112
leys+0.109
Neg logit contributions
 virtue-0.159
vous-0.159
rig-0.155
 importance-0.153
Yes-0.152
Token He
Token ID679
Feature activation+5.96e+00

Pos logit contributions
 down+0.006
iked+0.006
ged+0.005
 onward+0.005
am+0.005
Neg logit contributions
vous-0.022
 virtue-0.021
 matter-0.021
rig-0.021
 importance-0.021
Token asked
Token ID1965
Feature activation+4.24e+00

Pos logit contributions
ged+0.144
 down+0.137
am+0.137
,+0.134
iked+0.132
Neg logit contributions
 virtue-0.223
vous-0.218
rig-0.209
 matter-0.207
leaf-0.207
Token the
Token ID262
Feature activation+7.09e-01

Pos logit contributions
ged+0.093
 down+0.091
iked+0.090
 onward+0.083
leys+0.079
Neg logit contributions
 virtue-0.160
vous-0.160
rig-0.157
Yes-0.155
 importance-0.155
Token.
Token ID13
Feature activation+4.31e-01

Pos logit contributions
ged+0.147
iked+0.146
 down+0.139
 onward+0.131
leys+0.129
Neg logit contributions
 virtue-0.207
vous-0.206
rig-0.204
Yes-0.203
 importance-0.203
Token She
Token ID1375
Feature activation+4.28e+00

Pos logit contributions
ged+0.007
 down+0.006
iked+0.006
 onward+0.005
ls+0.005
Neg logit contributions
vous-0.019
 virtue-0.019
rig-0.019
Yes-0.019
 importance-0.019
Token saw
Token ID2497
Feature activation+3.55e+00

Pos logit contributions
ged+0.115
 down+0.112
iked+0.112
am+0.107
,+0.102
Neg logit contributions
 virtue-0.147
vous-0.142
rig-0.141
leaf-0.135
Yes-0.135
Token a
Token ID257
Feature activation-4.00e+00

Pos logit contributions
 down+0.097
ged+0.095
iked+0.091
 onward+0.085
,+0.084
Neg logit contributions
 virtue-0.121
rig-0.118
vous-0.118
Yes-0.110
 importance-0.110
Token wheel
Token ID7825
Feature activation+2.17e-01

Pos logit contributions
vous+0.134
rig+0.128
 virtue+0.124
leaf+0.123
Yes+0.120
Neg logit contributions
 down-0.109
ged-0.101
,-0.099
 onward-0.095
 ashore-0.092
Tokenbar
Token ID5657
Feature activation+1.50e+01

Pos logit contributions
ged+0.006
iked+0.006
 down+0.006
 onward+0.006
leys+0.005
Neg logit contributions
vous-0.007
 virtue-0.007
rig-0.007
Yes-0.007
 importance-0.006
Tokenrow
Token ID808
Feature activation+4.82e+00

Pos logit contributions
ged+0.359
iked+0.355
 down+0.351
 onward+0.340
ls+0.324
Neg logit contributions
vous-0.526
 virtue-0.513
rig-0.504
 importance-0.494
Yes-0.489
Token,
Token ID11
Feature activation+9.58e+00

Pos logit contributions
ged+0.133
iked+0.131
 down+0.125
leys+0.122
 onward+0.121
Neg logit contributions
vous-0.148
 virtue-0.145
rig-0.143
 importance-0.142
Yes-0.140
Token a
Token ID257
Feature activation-4.04e+00

Pos logit contributions
 down+0.246
ged+0.228
 his+0.226
,+0.222
 he+0.208
Neg logit contributions
 virtue-0.384
vous-0.353
rig-0.342
Yes-0.316
 importance-0.316
Token large
Token ID1588
Feature activation-1.94e+00

Pos logit contributions
vous+0.136
rig+0.132
 virtue+0.131
Yes+0.126
leaf+0.125
Neg logit contributions
 down-0.108
ged-0.105
 onward-0.096
iked-0.096
,-0.093
Token sp
Token ID599
Feature activation+1.33e+00

Pos logit contributions
vous+0.066
 virtue+0.066
rig+0.065
Yes+0.064
 importance+0.063
Neg logit contributions
ged-0.049
 down-0.049
iked-0.047
 onward-0.045
ls-0.042
Token a
Token ID257
Feature activation-3.92e+00

Pos logit contributions
 down+0.207
ged+0.198
iked+0.195
 onward+0.181
am+0.178
Neg logit contributions
 virtue-0.275
rig-0.268
vous-0.265
 importance-0.255
Yes-0.251
Token big
Token ID1263
Feature activation-1.37e+00

Pos logit contributions
vous+0.122
 virtue+0.121
rig+0.119
Yes+0.116
 importance+0.116
Neg logit contributions
 down-0.112
ged-0.110
iked-0.106
 onward-0.101
ls-0.098
Token,
Token ID11
Feature activation+9.68e+00

Pos logit contributions
 virtue+0.044
vous+0.043
Yes+0.042
 importance+0.042
rig+0.042
Neg logit contributions
iked-0.037
ged-0.037
 down-0.035
 onward-0.035
leys-0.035
Token spinning
Token ID19493
Feature activation+4.83e+00

Pos logit contributions
 down+0.251
ged+0.225
 onward+0.208
iked+0.203
,+0.200
Neg logit contributions
 virtue-0.350
vous-0.339
rig-0.336
Yes-0.323
 importance-0.321
Token wheel
Token ID7825
Feature activation+1.63e-01

Pos logit contributions
 down+0.132
ged+0.127
iked+0.114
,+0.112
 onward+0.109
Neg logit contributions
vous-0.172
 virtue-0.170
rig-0.168
 importance-0.162
leaf-0.159
Tokenbar
Token ID5657
Feature activation+1.50e+01

Pos logit contributions
ged+0.004
iked+0.004
 down+0.004
 onward+0.004
leys+0.004
Neg logit contributions
vous-0.005
 virtue-0.005
rig-0.005
Yes-0.005
 importance-0.005
Tokenrow
Token ID808
Feature activation+4.80e+00

Pos logit contributions
ged+0.351
iked+0.347
 down+0.341
 onward+0.332
ls+0.315
Neg logit contributions
vous-0.526
 virtue-0.516
rig-0.505
 importance-0.497
Yes-0.490
Token and
Token ID290
Feature activation-4.02e+00

Pos logit contributions
ged+0.137
iked+0.136
leys+0.129
 onward+0.128
 down+0.128
Neg logit contributions
 virtue-0.138
vous-0.137
rig-0.134
 importance-0.133
Yes-0.132
Token put
Token ID1234
Feature activation+1.63e+00

Pos logit contributions
 virtue+0.122
vous+0.122
rig+0.120
Yes+0.117
 importance+0.116
Neg logit contributions
ged-0.119
 down-0.117
iked-0.115
 onward-0.109
leys-0.104
Token the
Token ID262
Feature activation+7.00e-01

Pos logit contributions
ged+0.039
iked+0.038
 down+0.038
 onward+0.035
leys+0.034
Neg logit contributions
 virtue-0.057
vous-0.057
rig-0.056
Yes-0.056
 importance-0.055
Token pumpkin
Token ID30089
Feature activation+4.43e-01

Pos logit contributions
 down+0.015
ged+0.013
,+0.012
iked+0.012
am+0.012
Neg logit contributions
rig-0.029
vous-0.028
 virtue-0.028
Yes-0.027
leaf-0.026
Token him
Token ID683
Feature activation+6.26e+00

Pos logit contributions
 down+0.076
ged+0.074
iked+0.068
 onward+0.064
am+0.059
Neg logit contributions
 virtue-0.168
vous-0.168
rig-0.165
 importance-0.162
Yes-0.157
Token a
Token ID257
Feature activation-3.98e+00

Pos logit contributions
 down+0.142
ged+0.135
iked+0.132
 onward+0.122
am+0.120
Neg logit contributions
 virtue-0.239
vous-0.238
rig-0.233
 importance-0.229
Yes-0.228
Token big
Token ID1263
Feature activation-1.50e+00

Pos logit contributions
vous+0.135
 virtue+0.128
rig+0.126
 importance+0.126
Yes+0.124
Neg logit contributions
 down-0.108
ged-0.098
iked-0.093
,-0.093
 onward-0.093
Token red
Token ID2266
Feature activation+8.35e-02

Pos logit contributions
vous+0.051
rig+0.050
 virtue+0.050
 importance+0.048
Yes+0.047
Neg logit contributions
 down-0.041
ged-0.039
,-0.036
iked-0.036
 onward-0.035
Token wheel
Token ID7825
Feature activation+1.79e-01

Pos logit contributions
ged+0.002
 down+0.002
iked+0.002
 onward+0.002
leys+0.002
Neg logit contributions
 virtue-0.003
vous-0.003
rig-0.003
Yes-0.003
 importance-0.003
Tokenbar
Token ID5657
Feature activation+1.49e+01

Pos logit contributions
ged+0.004
 down+0.004
iked+0.004
 onward+0.004
am+0.003
Neg logit contributions
 virtue-0.007
vous-0.007
rig-0.006
 importance-0.006
Yes-0.006
Tokenrow
Token ID808
Feature activation+4.62e+00

Pos logit contributions
ged+0.344
iked+0.334
 down+0.334
 onward+0.315
ls+0.300
Neg logit contributions
vous-0.537
 virtue-0.534
rig-0.526
Yes-0.513
 importance-0.513
Token and
Token ID290
Feature activation-3.96e+00

Pos logit contributions
ged+0.110
 down+0.107
iked+0.107
 onward+0.099
leys+0.095
Neg logit contributions
 virtue-0.164
vous-0.163
rig-0.161
Yes-0.158
 importance-0.157
Token filled
Token ID5901
Feature activation+5.44e+00

Pos logit contributions
 virtue+0.135
vous+0.133
rig+0.132
 importance+0.128
Yes+0.125
Neg logit contributions
 down-0.105
ged-0.105
iked-0.101
 onward-0.095
am-0.091
Token it
Token ID340
Feature activation+3.16e+00

Pos logit contributions
 down+0.109
ged+0.104
iked+0.089
 his+0.087
ls+0.082
Neg logit contributions
vous-0.235
 virtue-0.233
rig-0.224
 importance-0.224
 matter-0.218
Token with
Token ID351
Feature activation-1.53e+00

Pos logit contributions
ged+0.097
iked+0.095
 down+0.091
 onward+0.089
leys+0.088
Neg logit contributions
 virtue-0.091
rig-0.090
vous-0.089
Yes-0.088
 importance-0.086
Token the
Token ID262
Feature activation+5.04e-01

Pos logit contributions
iked+0.148
ged+0.146
 down+0.136
leys+0.135
 onward+0.132
Neg logit contributions
 virtue-0.231
Yes-0.230
vous-0.229
rig-0.228
 importance-0.223
Token cat
Token ID3797
Feature activation-9.74e+00

Pos logit contributions
 down+0.013
ged+0.013
iked+0.013
 onward+0.012
ls+0.011
Neg logit contributions
vous-0.017
 virtue-0.017
rig-0.017
Yes-0.017
 importance-0.016
Token off
Token ID572
Feature activation+5.50e+00

Pos logit contributions
rig+0.318
vous+0.315
 virtue+0.314
Yes+0.309
 importance+0.302
Neg logit contributions
ged-0.251
iked-0.250
 onward-0.229
 down-0.228
leys-0.225
Token the
Token ID262
Feature activation+5.16e-01

Pos logit contributions
ged+0.135
 down+0.135
iked+0.130
 onward+0.123
ls+0.115
Neg logit contributions
 virtue-0.196
vous-0.196
rig-0.192
 importance-0.188
Yes-0.186
Token wheel
Token ID7825
Feature activation+1.46e-01

Pos logit contributions
ged+0.016
iked+0.016
 down+0.015
 onward+0.015
leys+0.014
Neg logit contributions
 virtue-0.015
vous-0.015
rig-0.015
 importance-0.014
Yes-0.014
Tokenbar
Token ID5657
Feature activation+1.49e+01

Pos logit contributions
ged+0.004
 down+0.004
iked+0.004
 onward+0.004
leys+0.004
Neg logit contributions
 virtue-0.005
vous-0.005
rig-0.005
 importance-0.004
Yes-0.004
Tokenrow
Token ID808
Feature activation+4.68e+00

Pos logit contributions
ged+0.353
iked+0.344
 down+0.341
 onward+0.327
ls+0.316
Neg logit contributions
vous-0.526
 virtue-0.519
rig-0.514
Yes-0.497
 importance-0.494
Token and
Token ID290
Feature activation-3.87e+00

Pos logit contributions
ged+0.136
iked+0.134
 down+0.129
leys+0.125
 onward+0.125
Neg logit contributions
 virtue-0.136
vous-0.134
rig-0.133
Yes-0.131
 importance-0.130
Token put
Token ID1234
Feature activation+1.60e+00

Pos logit contributions
 virtue+0.135
vous+0.135
rig+0.132
 importance+0.128
Yes+0.124
Neg logit contributions
 down-0.103
ged-0.103
iked-0.096
 onward-0.090
ls-0.088
Token him
Token ID683
Feature activation+6.18e+00

Pos logit contributions
iked+0.040
ged+0.039
 down+0.038
leys+0.036
 onward+0.036
Neg logit contributions
 virtue-0.054
vous-0.053
Yes-0.053
rig-0.052
 importance-0.051
Token back
Token ID736
Feature activation+6.08e+00

Pos logit contributions
iked+0.130
ged+0.130
 down+0.118
 onward+0.117
ls+0.113
Neg logit contributions
vous-0.229
 virtue-0.225
rig-0.222
Yes-0.222
 importance-0.219
Token dolls
Token ID36062
Feature activation-5.00e+00

Pos logit contributions
 down+0.117
,+0.092
ls+0.089
ged+0.089
 onward+0.081
Neg logit contributions
 virtue-0.215
vous-0.211
leaf-0.204
rig-0.201
 importance-0.197
Token around
Token ID1088
Feature activation+1.54e+00

Pos logit contributions
 virtue+0.173
vous+0.173
rig+0.170
Yes+0.166
 importance+0.166
Neg logit contributions
ged-0.125
 down-0.123
iked-0.121
 onward-0.113
leys-0.108
Token in
Token ID287
Feature activation+1.13e+00

Pos logit contributions
 down+0.035
,+0.033
ged+0.031
 his+0.026
 onward+0.025
Neg logit contributions
 virtue-0.068
vous-0.068
rig-0.068
leaf-0.065
 deserve-0.063
Token a
Token ID257
Feature activation-4.06e+00

Pos logit contributions
 down+0.027
ged+0.024
,+0.024
 onward+0.023
 his+0.022
Neg logit contributions
 virtue-0.045
rig-0.045
vous-0.043
leaf-0.043
 importance-0.041
Token wheel
Token ID7825
Feature activation+1.61e-01

Pos logit contributions
 virtue+0.130
vous+0.128
rig+0.127
 importance+0.125
Yes+0.124
Neg logit contributions
 down-0.112
ged-0.110
iked-0.104
 onward-0.102
ls-0.098
Tokenbar
Token ID5657
Feature activation+1.49e+01

Pos logit contributions
 down+0.003
ged+0.003
,+0.003
iked+0.003
 onward+0.003
Neg logit contributions
 virtue-0.007
 importance-0.007
rig-0.007
vous-0.007
leaf-0.007
Tokenrow
Token ID808
Feature activation+4.66e+00

Pos logit contributions
ged+0.365
 down+0.359
iked+0.357
 onward+0.336
ls+0.321
Neg logit contributions
vous-0.517
 virtue-0.511
rig-0.504
Yes-0.492
 importance-0.491
Token she
Token ID673
Feature activation+5.30e+00

Pos logit contributions
 down+0.108
ged+0.104
iked+0.100
 onward+0.093
,+0.090
Neg logit contributions
 virtue-0.175
vous-0.174
rig-0.173
Yes-0.170
leaf-0.169
Token had
Token ID550
Feature activation-2.14e+00

Pos logit contributions
ged+0.126
 down+0.123
am+0.114
,+0.103
ed+0.099
Neg logit contributions
 virtue-0.205
rig-0.198
 importance-0.190
leaf-0.189
resa-0.184
Token found
Token ID1043
Feature activation+5.43e+00

Pos logit contributions
rig+0.069
 virtue+0.068
vous+0.065
Yes+0.065
 importance+0.062
Neg logit contributions
ged-0.063
 down-0.062
iked-0.060
,-0.057
 onward-0.056
Token in
Token ID287
Feature activation+1.09e+00

Pos logit contributions
 down+0.100
ged+0.093
iked+0.081
 onward+0.079
,+0.077
Neg logit contributions
rig-0.244
 virtue-0.241
vous-0.239
Yes-0.233
 importance-0.233
Token.
Token ID13
Feature activation+3.38e-01

Pos logit contributions
Yes+0.125
rig+0.121
leaf+0.120
vous+0.117
 importance+0.116
Neg logit contributions
iked-0.136
leys-0.133
ged-0.132
 onward-0.126
am-0.125
Token He
Token ID679
Feature activation+5.89e+00

Pos logit contributions
ged+0.008
ls+0.007
leys+0.007
iked+0.007
 down+0.006
Neg logit contributions
 importance-0.013
 virtue-0.013
vous-0.012
Yes-0.012
rig-0.012
Token found
Token ID1043
Feature activation+5.36e+00

Pos logit contributions
ged+0.152
 down+0.148
iked+0.146
am+0.135
 onward+0.134
Neg logit contributions
 virtue-0.207
vous-0.200
rig-0.198
Yes-0.194
 importance-0.191
Token a
Token ID257
Feature activation-4.02e+00

Pos logit contributions
ged+0.163
 down+0.161
iked+0.160
 onward+0.151
leys+0.146
Neg logit contributions
 virtue-0.155
vous-0.155
rig-0.151
Yes-0.148
 importance-0.148
Token wheel
Token ID7825
Feature activation+1.04e-01

Pos logit contributions
vous+0.148
 virtue+0.142
rig+0.140
leaf+0.138
Yes+0.137
Neg logit contributions
 down-0.096
ged-0.086
,-0.085
 onward-0.082
iked-0.082
Tokenbar
Token ID5657
Feature activation+1.49e+01

Pos logit contributions
ged+0.003
iked+0.003
 down+0.003
 onward+0.003
leys+0.002
Neg logit contributions
vous-0.003
 virtue-0.003
rig-0.003
Yes-0.003
 importance-0.003
Tokenrow
Token ID808
Feature activation+4.61e+00

Pos logit contributions
ged+0.350
iked+0.347
 down+0.346
 onward+0.332
ls+0.314
Neg logit contributions
vous-0.523
 virtue-0.510
rig-0.503
 importance-0.492
Yes-0.489
Token,
Token ID11
Feature activation+9.59e+00

Pos logit contributions
ged+0.128
iked+0.126
 down+0.121
 onward+0.118
leys+0.117
Neg logit contributions
vous-0.141
 virtue-0.140
rig-0.136
 importance-0.135
Yes-0.135
Token a
Token ID257
Feature activation-4.05e+00

Pos logit contributions
 down+0.247
ged+0.244
 his+0.222
,+0.221
iked+0.220
Neg logit contributions
 virtue-0.383
vous-0.351
rig-0.340
 importance-0.320
Yes-0.317
Token tr
Token ID491
Feature activation+3.94e+00

Pos logit contributions
vous+0.140
 virtue+0.138
rig+0.136
Yes+0.131
 importance+0.131
Neg logit contributions
 down-0.103
ged-0.101
iked-0.096
 onward-0.093
ls-0.087
Tokenamp
Token ID696
Feature activation-2.61e+00

Pos logit contributions
 down+0.140
ged+0.140
iked+0.138
 onward+0.132
leys+0.128
Neg logit contributions
 virtue-0.093
vous-0.092
rig-0.091
Yes-0.087
 importance-0.085
Token
Token ID220
Feature activation+4.94e+00

Pos logit contributions
 down+0.006
 onward+0.005
ged+0.005
iked+0.005
am+0.005
Neg logit contributions
vous-0.013
 virtue-0.013
 matter-0.013
 importance-0.013
rig-0.012
Token
Token ID198
Feature activation-1.01e+00

Pos logit contributions
ged+0.136
 down+0.133
iked+0.133
 onward+0.124
leys+0.119
Neg logit contributions
 virtue-0.158
vous-0.157
rig-0.155
Yes-0.152
 importance-0.151
Token
Token ID198
Feature activation-1.01e+00

Pos logit contributions
 virtue+0.038
vous+0.038
 matter+0.037
 importance+0.037
rig+0.036
Neg logit contributions
ged-0.022
 down-0.022
iked-0.021
 onward-0.021
am-0.019
TokenThe
Token ID464
Feature activation-3.61e+00

Pos logit contributions
 matter+0.030
 virtue+0.030
vous+0.030
rig+0.030
 least+0.029
Neg logit contributions
ged-0.029
 onward-0.029
His-0.028
iked-0.027
 down-0.025
Token wheel
Token ID7825
Feature activation+1.33e-01

Pos logit contributions
 virtue+0.132
leaf+0.132
rig+0.130
 rather+0.122
 deserve+0.121
Neg logit contributions
,-0.089
ged-0.077
 sand-0.075
iked-0.072
 cart-0.067
Tokenbar
Token ID5657
Feature activation+1.48e+01

Pos logit contributions
 down+0.004
ged+0.003
iked+0.003
am+0.003
,+0.003
Neg logit contributions
 virtue-0.005
rig-0.005
vous-0.004
leaf-0.004
Yes-0.004
Tokenrow
Token ID808
Feature activation+4.56e+00

Pos logit contributions
ged+0.302
 down+0.292
iked+0.286
am+0.276
leys+0.250
Neg logit contributions
 virtue-0.603
rig-0.597
Yes-0.587
leaf-0.586
 importance-0.577
Token wheel
Token ID7825
Feature activation+1.25e-01

Pos logit contributions
ged+0.099
 down+0.097
iked+0.096
 onward+0.089
leys+0.084
Neg logit contributions
vous-0.171
 virtue-0.171
rig-0.167
 importance-0.165
Yes-0.165
Tokened
Token ID276
Feature activation+4.86e+00

Pos logit contributions
ged+0.003
 down+0.003
iked+0.003
 onward+0.003
leys+0.003
Neg logit contributions
 virtue-0.004
vous-0.004
rig-0.004
Yes-0.004
 importance-0.004
Token the
Token ID262
Feature activation+6.32e-01

Pos logit contributions
iked+0.108
ged+0.106
leys+0.097
 onward+0.093
ls+0.091
Neg logit contributions
 virtue-0.178
vous-0.173
Yes-0.173
 importance-0.173
rig-0.171
Token cup
Token ID6508
Feature activation-1.24e+00

Pos logit contributions
 down+0.015
 sand+0.014
,+0.014
iked+0.013
 castles+0.013
Neg logit contributions
rig-0.024
vous-0.022
leaf-0.022
 virtue-0.022
 deserve-0.021
Tokenuffy
Token ID15352
Feature activation-2.07e+00

Pos logit contributions
iked+0.043
ged+0.043
 down+0.041
am+0.040
ls+0.039
Neg logit contributions
vous-0.081
Yes-0.080
 virtue-0.080
leaf-0.080
 importance-0.079
Token had
Token ID550
Feature activation-2.07e+00

Pos logit contributions
 virtue+0.071
Yes+0.070
rig+0.070
leaf+0.070
vous+0.066
Neg logit contributions
 down-0.056
ged-0.055
,-0.054
am-0.052
ls-0.052
Token made
Token ID925
Feature activation+3.08e-01

Pos logit contributions
rig+0.070
 virtue+0.063
Yes+0.063
vous+0.062
leaf+0.061
Neg logit contributions
 down-0.060
ged-0.057
 his-0.057
,-0.056
iked-0.056
Token the
Token ID262
Feature activation+4.66e-01

Pos logit contributions
 down+0.008
 his+0.007
,+0.007
ged+0.006
 out+0.006
Neg logit contributions
rig-0.011
vous-0.011
 virtue-0.011
Yes-0.011
leaf-0.011
Token wheel
Token ID7825
Feature activation+5.71e-02

Pos logit contributions
 down+0.012
 sand+0.009
,+0.009
 castles+0.009
 back+0.009
Neg logit contributions
leaf-0.018
rig-0.018
vous-0.017
Yes-0.016
 virtue-0.016
Tokenbar
Token ID5657
Feature activation+1.47e+01

Pos logit contributions
 down+0.002
ged+0.001
iked+0.001
 onward+0.001
,+0.001
Neg logit contributions
 virtue-0.002
vous-0.002
leaf-0.002
 importance-0.002
rig-0.002
Tokenrow
Token ID808
Feature activation+4.51e+00

Pos logit contributions
 down+0.323
ged+0.321
iked+0.310
am+0.283
 onward+0.282
Neg logit contributions
 virtue-0.559
vous-0.551
rig-0.548
Yes-0.542
 importance-0.540
Token much
Token ID881
Feature activation-1.45e+00

Pos logit contributions
 down+0.125
ged+0.119
iked+0.115
 onward+0.111
am+0.106
Neg logit contributions
 virtue-0.146
vous-0.146
rig-0.143
Yes-0.142
leaf-0.141
Token lighter
Token ID14871
Feature activation+3.05e+00

Pos logit contributions
 virtue+0.042
vous+0.042
rig+0.042
Yes+0.041
 importance+0.041
Neg logit contributions
ged-0.045
iked-0.044
 down-0.043
 onward-0.042
leys-0.040
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
 down+0.081
ged+0.074
iked+0.069
,+0.069
 onward+0.066
Neg logit contributions
vous-0.111
 virtue-0.107
leaf-0.105
Yes-0.105
rig-0.105
Token The
Token ID383
Feature activation-3.00e+00

Pos logit contributions
 down+0.006
iked+0.006
ged+0.006
 onward+0.006
am+0.005
Neg logit contributions
vous-0.017
 virtue-0.017
rig-0.016
 importance-0.016
Yes-0.016
Token much
Token ID881
Feature activation-1.45e+00

Pos logit contributions
 down+0.125
ged+0.119
iked+0.115
 onward+0.111
am+0.106
Neg logit contributions
 virtue-0.146
vous-0.146
rig-0.143
Yes-0.142
leaf-0.141
Token lighter
Token ID14871
Feature activation+3.05e+00

Pos logit contributions
 virtue+0.042
vous+0.042
rig+0.042
Yes+0.041
 importance+0.041
Neg logit contributions
ged-0.045
iked-0.044
 down-0.043
 onward-0.042
leys-0.040
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
 down+0.081
ged+0.074
iked+0.069
,+0.069
 onward+0.066
Neg logit contributions
vous-0.111
 virtue-0.107
leaf-0.105
Yes-0.105
rig-0.105
Token The
Token ID383
Feature activation-3.00e+00

Pos logit contributions
 down+0.006
iked+0.006
ged+0.006
 onward+0.006
am+0.005
Neg logit contributions
vous-0.017
 virtue-0.017
rig-0.016
 importance-0.016
Yes-0.016
Token wheel
Token ID7825
Feature activation+2.67e-02

Pos logit contributions
rig+0.118
leaf+0.111
vous+0.107
 virtue+0.107
illa+0.101
Neg logit contributions
 down-0.069
ged-0.066
,-0.063
 castles-0.060
iked-0.059
Tokenbar
Token ID5657
Feature activation+1.47e+01

Pos logit contributions
 down+0.001
ged+0.001
iked+0.001
am+0.001
,+0.001
Neg logit contributions
 virtue-0.001
rig-0.001
vous-0.001
leaf-0.001
Yes-0.001
Tokenrow
Token ID808
Feature activation+4.45e+00

Pos logit contributions
ged+0.311
 down+0.306
iked+0.301
 onward+0.276
leys+0.262
Neg logit contributions
 virtue-0.563
vous-0.561
rig-0.554
Yes-0.544
 importance-0.543
Token was
Token ID373
Feature activation-2.99e+00

Pos logit contributions
ged+0.123
 down+0.122
iked+0.120
 onward+0.113
leys+0.108
Neg logit contributions
 virtue-0.141
vous-0.141
rig-0.138
Yes-0.135
 importance-0.135
Token now
Token ID783
Feature activation-3.58e+00

Pos logit contributions
vous+0.084
rig+0.083
 virtue+0.082
Yes+0.081
leaf+0.079
Neg logit contributions
 down-0.097
ged-0.094
iked-0.090
 onward-0.088
leys-0.083
Token much
Token ID881
Feature activation-1.54e+00

Pos logit contributions
vous+0.106
 virtue+0.104
rig+0.103
Yes+0.101
 importance+0.099
Neg logit contributions
 down-0.109
ged-0.108
iked-0.105
 onward-0.100
leys-0.096
Token easier
Token ID4577
Feature activation+1.80e+00

Pos logit contributions
 virtue+0.048
vous+0.048
rig+0.047
Yes+0.046
 importance+0.046
Neg logit contributions
ged-0.044
 down-0.044
iked-0.043
 onward-0.041
leys-0.039
Token of
Token ID286
Feature activation-5.38e+00

Pos logit contributions
ged+0.008
iked+0.008
leys+0.007
ls+0.007
 onward+0.007
Neg logit contributions
Yes-0.006
rig-0.006
vous-0.006
 virtue-0.006
 importance-0.006
Token soil
Token ID9260
Feature activation+3.87e+00

Pos logit contributions
 virtue+0.179
vous+0.178
rig+0.175
Yes+0.173
 importance+0.173
Neg logit contributions
ged-0.141
iked-0.139
 down-0.137
 onward-0.130
leys-0.124
Token into
Token ID656
Feature activation+3.22e+00

Pos logit contributions
ged+0.106
iked+0.104
leys+0.100
 onward+0.097
am+0.088
Neg logit contributions
rig-0.115
 virtue-0.112
Yes-0.111
 importance-0.108
 bit-0.105
Token the
Token ID262
Feature activation+3.11e-01

Pos logit contributions
 down+0.076
ged+0.075
iked+0.068
 onward+0.065
,+0.063
Neg logit contributions
vous-0.122
 virtue-0.120
rig-0.119
leaf-0.113
Yes-0.112
Token wheel
Token ID7825
Feature activation+5.68e-02

Pos logit contributions
ged+0.008
iked+0.008
 down+0.008
 onward+0.007
leys+0.007
Neg logit contributions
 virtue-0.011
vous-0.010
 importance-0.010
rig-0.010
Yes-0.010
Tokenbar
Token ID5657
Feature activation+1.46e+01

Pos logit contributions
ged+0.001
iked+0.001
 down+0.001
 onward+0.001
ls+0.001
Neg logit contributions
vous-0.002
rig-0.002
 virtue-0.002
Yes-0.002
 importance-0.002
Tokenrow
Token ID808
Feature activation+4.40e+00

Pos logit contributions
ged+0.391
 onward+0.376
iked+0.375
 down+0.369
ls+0.355
Neg logit contributions
vous-0.446
rig-0.444
 virtue-0.442
 importance-0.420
 least-0.412
Token.
Token ID13
Feature activation+2.67e-01

Pos logit contributions
ged+0.115
iked+0.111
 onward+0.105
 down+0.105
leys+0.105
Neg logit contributions
 virtue-0.139
rig-0.136
vous-0.133
 importance-0.133
Yes-0.132
Token It
Token ID632
Feature activation-9.51e-01

Pos logit contributions
ged+0.006
 down+0.006
iked+0.006
 onward+0.006
ls+0.005
Neg logit contributions
 virtue-0.010
vous-0.010
rig-0.010
Yes-0.009
 importance-0.009
Token was
Token ID373
Feature activation-3.10e+00

Pos logit contributions
 virtue+0.029
vous+0.028
rig+0.027
leaf+0.027
Yes+0.027
Neg logit contributions
 down-0.029
ged-0.028
iked-0.027
am-0.026
ls-0.026
Token heavy
Token ID4334
Feature activation-2.06e+00

Pos logit contributions
vous+0.081
 virtue+0.080
rig+0.078
Yes+0.077
 importance+0.075
Neg logit contributions
 down-0.105
ged-0.104
iked-0.101
 onward-0.098
am-0.093
Token filled
Token ID5901
Feature activation+5.09e+00

Pos logit contributions
 down+0.139
ged+0.137
iked+0.129
am+0.128
ls+0.121
Neg logit contributions
 virtue-0.204
vous-0.196
rig-0.193
 importance-0.188
Yes-0.188
Token up
Token ID510
Feature activation+7.58e+00

Pos logit contributions
 down+0.106
ged+0.094
 his+0.089
iked+0.087
am+0.080
Neg logit contributions
 virtue-0.222
vous-0.217
rig-0.209
 importance-0.205
 matter-0.201
Token lots
Token ID6041
Feature activation-7.26e+00

Pos logit contributions
 down+0.144
 his+0.123
ged+0.120
iked+0.114
,+0.111
Neg logit contributions
 virtue-0.352
rig-0.346
vous-0.342
 importance-0.323
 matter-0.320
Token of
Token ID286
Feature activation-5.39e+00

Pos logit contributions
 virtue+0.181
vous+0.179
rig+0.174
 importance+0.171
Yes+0.168
Neg logit contributions
 down-0.253
ged-0.253
iked-0.248
 onward-0.237
ls-0.232
Token wheel
Token ID7825
Feature activation-7.27e-02

Pos logit contributions
 virtue+0.206
rig+0.200
vous+0.187
illa+0.186
resa+0.184
Neg logit contributions
 down-0.140
 his-0.121
ged-0.120
,-0.117
 castles-0.117
Tokenbar
Token ID5657
Feature activation+1.46e+01

Pos logit contributions
rig+0.002
vous+0.002
 virtue+0.002
Yes+0.002
 importance+0.002
Neg logit contributions
ged-0.002
iked-0.002
 down-0.002
 onward-0.002
leys-0.002
Tokenrows
Token ID8516
Feature activation-2.91e+00

Pos logit contributions
ged+0.351
iked+0.346
 onward+0.340
 down+0.330
ls+0.310
Neg logit contributions
vous-0.492
 virtue-0.471
rig-0.468
 importance-0.456
Yes-0.448
Token with
Token ID351
Feature activation-1.71e+00

Pos logit contributions
 virtue+0.087
vous+0.087
rig+0.085
Yes+0.084
 importance+0.083
Neg logit contributions
ged-0.085
iked-0.083
 down-0.083
 onward-0.078
leys-0.076
Token the
Token ID262
Feature activation+2.73e-01

Pos logit contributions
 virtue+0.061
vous+0.060
rig+0.060
 importance+0.057
Yes+0.057
Neg logit contributions
 down-0.043
ged-0.043
iked-0.041
 onward-0.038
am-0.037
Token waste
Token ID7030
Feature activation+4.12e-01

Pos logit contributions
 down+0.007
,+0.006
ged+0.006
 castles+0.006
 sand+0.006
Neg logit contributions
rig-0.011
 virtue-0.010
leaf-0.010
vous-0.009
Yes-0.009
Token and
Token ID290
Feature activation-4.20e+00

Pos logit contributions
ged+0.011
 down+0.011
iked+0.010
 onward+0.010
ls+0.009
Neg logit contributions
 virtue-0.014
vous-0.014
rig-0.014
Yes-0.013
 importance-0.013
Token it
Token ID340
Feature activation+3.01e+00

Pos logit contributions
iked+0.114
ged+0.113
 down+0.106
leys+0.102
 onward+0.102
Neg logit contributions
 virtue-0.166
vous-0.165
Yes-0.164
rig-0.160
 importance-0.160
Token away
Token ID1497
Feature activation+5.91e+00

Pos logit contributions
ged+0.075
iked+0.072
 onward+0.065
ls+0.063
leys+0.063
Neg logit contributions
 virtue-0.103
rig-0.099
vous-0.098
Yes-0.098
 importance-0.096
Token in
Token ID287
Feature activation+9.09e-01

Pos logit contributions
ged+0.135
iked+0.131
 down+0.131
 onward+0.120
leys+0.115
Neg logit contributions
 virtue-0.218
vous-0.217
rig-0.213
Yes-0.210
 importance-0.210
Token a
Token ID257
Feature activation-4.20e+00

Pos logit contributions
 down+0.019
ged+0.017
 his+0.016
,+0.016
 onward+0.016
Neg logit contributions
rig-0.038
vous-0.037
leaf-0.036
 virtue-0.036
Yes-0.035
Token wheel
Token ID7825
Feature activation-1.04e-01

Pos logit contributions
vous+0.131
 virtue+0.131
rig+0.129
Yes+0.126
 importance+0.126
Neg logit contributions
 down-0.117
ged-0.117
iked-0.113
 onward-0.109
leys-0.104
Tokenbar
Token ID5657
Feature activation+1.45e+01

Pos logit contributions
 virtue+0.004
vous+0.004
rig+0.004
 importance+0.004
Yes+0.004
Neg logit contributions
 down-0.002
ged-0.002
iked-0.002
 onward-0.002
am-0.002
Tokenrow
Token ID808
Feature activation+4.32e+00

Pos logit contributions
ged+0.349
iked+0.340
 down+0.338
 onward+0.326
ls+0.311
Neg logit contributions
vous-0.508
 virtue-0.503
rig-0.491
 importance-0.479
Yes-0.472
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
 down+0.089
ged+0.089
iked+0.086
 onward+0.079
leys+0.075
Neg logit contributions
vous-0.168
 virtue-0.167
rig-0.166
Yes-0.163
 importance-0.162
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
ged+0.003
iked+0.003
 down+0.003
ls+0.003
 onward+0.003
Neg logit contributions
Yes-0.006
vous-0.005
 virtue-0.005
 importance-0.005
rig-0.005
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
 virtue+0.039
vous+0.038
rig+0.037
 importance+0.037
Yes+0.037
Neg logit contributions
ged-0.028
 down-0.027
iked-0.027
 onward-0.025
leys-0.024
TokenOnce
Token ID7454
Feature activation+3.24e+00

Pos logit contributions
rig+0.033
 virtue+0.033
 least+0.032
leaf+0.032
vous+0.032
Neg logit contributions
iked-0.031
ged-0.030
 onward-0.030
 down-0.029
leys-0.029
Token was
Token ID373
Feature activation-3.12e+00

Pos logit contributions
 virtue+0.103
vous+0.098
rig+0.098
Yes+0.098
 importance+0.096
Neg logit contributions
ged-0.062
 down-0.061
iked-0.058
am-0.058
,-0.055
Token wheel
Token ID7825
Feature activation-9.25e-02

Pos logit contributions
vous+0.088
 virtue+0.088
rig+0.084
 importance+0.082
Yes+0.081
Neg logit contributions
iked-0.097
ged-0.096
 down-0.091
ls-0.089
leys-0.088
Tokening
Token ID278
Feature activation+5.50e+00

Pos logit contributions
vous+0.004
 virtue+0.004
rig+0.004
Yes+0.003
 importance+0.003
Neg logit contributions
ged-0.002
iked-0.002
 down-0.002
 onward-0.002
leys-0.002
Token the
Token ID262
Feature activation+4.04e-01

Pos logit contributions
iked+0.130
ged+0.129
 down+0.123
 onward+0.117
leys+0.117
Neg logit contributions
 virtue-0.192
vous-0.191
rig-0.189
Yes-0.186
 importance-0.186
Token wheel
Token ID7825
Feature activation-1.20e-01

Pos logit contributions
 down+0.011
ged+0.009
iked+0.009
 ashore+0.009
 onward+0.009
Neg logit contributions
rig-0.015
vous-0.014
leaf-0.014
 virtue-0.013
Yes-0.013
Tokenbar
Token ID5657
Feature activation+1.44e+01

Pos logit contributions
 virtue+0.004
vous+0.004
rig+0.004
Yes+0.004
 importance+0.004
Neg logit contributions
ged-0.003
 down-0.003
iked-0.003
 onward-0.003
leys-0.002
Tokenrow
Token ID808
Feature activation+4.19e+00

Pos logit contributions
ged+0.322
iked+0.317
 down+0.314
 onward+0.297
ls+0.286
Neg logit contributions
vous-0.525
 virtue-0.518
rig-0.509
 importance-0.498
Yes-0.496
Token around
Token ID1088
Feature activation+1.24e+00

Pos logit contributions
ged+0.095
iked+0.093
 down+0.091
 onward+0.085
leys+0.083
Neg logit contributions
 virtue-0.152
vous-0.151
rig-0.148
 importance-0.146
Yes-0.146
Token she
Token ID673
Feature activation+5.02e+00

Pos logit contributions
 down+0.025
ged+0.024
iked+0.022
 onward+0.021
,+0.020
Neg logit contributions
vous-0.052
rig-0.052
 virtue-0.052
leaf-0.050
 importance-0.049
Token made
Token ID925
Feature activation+1.52e-01

Pos logit contributions
ged+0.121
 down+0.115
am+0.113
iked+0.103
 onward+0.100
Neg logit contributions
 virtue-0.197
rig-0.187
leaf-0.184
 importance-0.178
Yes-0.177
Token sure
Token ID1654
Feature activation-3.38e+00

Pos logit contributions
 down+0.004
ged+0.003
iked+0.003
 onward+0.003
,+0.003
Neg logit contributions
 virtue-0.006
vous-0.006
rig-0.006
Yes-0.006
 importance-0.006
Token fun
Token ID1257
Feature activation-1.25e-01

Pos logit contributions
 virtue+0.152
vous+0.150
rig+0.147
Yes+0.138
 importance+0.134
Neg logit contributions
 down-0.184
ged-0.181
iked-0.178
 onward-0.171
,-0.166
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
vous+0.004
 virtue+0.004
rig+0.004
 importance+0.004
Yes+0.004
Neg logit contributions
ged-0.003
iked-0.003
 down-0.003
 onward-0.003
leys-0.003
Token Soon
Token ID15894
Feature activation+1.97e+00

Pos logit contributions
 down+0.004
ged+0.004
iked+0.004
 onward+0.004
leys+0.004
Neg logit contributions
 virtue-0.007
vous-0.007
rig-0.007
 importance-0.007
Yes-0.006
Token the
Token ID262
Feature activation+2.27e-01

Pos logit contributions
ged+0.043
 down+0.041
iked+0.041
leys+0.040
 ashore+0.037
Neg logit contributions
Yes-0.071
 virtue-0.070
 importance-0.069
 matter-0.069
vous-0.068
Token wheel
Token ID7825
Feature activation-2.05e-01

Pos logit contributions
 down+0.005
ged+0.005
iked+0.005
 onward+0.005
,+0.004
Neg logit contributions
 virtue-0.009
rig-0.009
vous-0.008
leaf-0.008
Yes-0.008
Tokenbar
Token ID5657
Feature activation+1.42e+01

Pos logit contributions
 virtue+0.006
vous+0.006
rig+0.006
Yes+0.006
 importance+0.006
Neg logit contributions
 down-0.006
ged-0.006
iked-0.006
 onward-0.006
am-0.005
Tokenrow
Token ID808
Feature activation+3.92e+00

Pos logit contributions
ged+0.342
 down+0.338
iked+0.334
 onward+0.313
ls+0.298
Neg logit contributions
vous-0.499
 virtue-0.496
rig-0.487
Yes-0.479
 importance-0.479
Token was
Token ID373
Feature activation-3.35e+00

Pos logit contributions
ged+0.110
iked+0.108
 down+0.107
leys+0.101
 onward+0.101
Neg logit contributions
vous-0.118
 virtue-0.118
rig-0.114
 importance-0.114
Yes-0.114
Token empty
Token ID6565
Feature activation+2.57e+00

Pos logit contributions
 virtue+0.089
vous+0.087
 importance+0.086
rig+0.084
 matter+0.084
Neg logit contributions
ged-0.109
iked-0.108
ls-0.102
 down-0.101
leys-0.099
Token and
Token ID290
Feature activation-4.28e+00

Pos logit contributions
ged+0.069
iked+0.068
leys+0.063
 down+0.062
 onward+0.062
Neg logit contributions
 virtue-0.083
 importance-0.081
vous-0.080
Yes-0.080
rig-0.079
Token all
Token ID477
Feature activation-3.76e+00

Pos logit contributions
vous+0.148
 virtue+0.148
rig+0.145
 importance+0.141
Yes+0.139
Neg logit contributions
 down-0.112
ged-0.108
iked-0.105
 onward-0.101
ls-0.094
Token light
Token ID1657
Feature activation-3.58e-01

Pos logit contributions
 virtue+0.074
vous+0.073
rig+0.070
 importance+0.069
leaf+0.067
Neg logit contributions
 down-0.070
ged-0.067
iked-0.063
 onward-0.061
,-0.060
Tokenen
Token ID268
Feature activation+4.75e+00

Pos logit contributions
 virtue+0.013
vous+0.013
rig+0.013
Yes+0.013
 importance+0.013
Neg logit contributions
ged-0.008
iked-0.008
 down-0.008
 onward-0.007
leys-0.007
Token up
Token ID510
Feature activation+7.35e+00

Pos logit contributions
ged+0.111
iked+0.111
 down+0.107
 onward+0.101
leys+0.099
Neg logit contributions
 virtue-0.167
vous-0.166
rig-0.166
Yes-0.162
 importance-0.162
Token the
Token ID262
Feature activation+1.57e-01

Pos logit contributions
 down+0.171
ged+0.164
iked+0.156
 onward+0.151
ls+0.140
Neg logit contributions
vous-0.279
 virtue-0.276
rig-0.271
Yes-0.265
 importance-0.264
Token wheel
Token ID7825
Feature activation-3.12e-01

Pos logit contributions
 down+0.004
ged+0.004
iked+0.004
 onward+0.004
am+0.003
Neg logit contributions
vous-0.006
rig-0.005
 virtue-0.005
Yes-0.005
leaf-0.005
Tokenbar
Token ID5657
Feature activation+1.41e+01

Pos logit contributions
 virtue+0.012
vous+0.012
rig+0.012
 importance+0.011
Yes+0.011
Neg logit contributions
ged-0.007
 down-0.007
iked-0.007
 onward-0.006
leys-0.006
Tokenrow
Token ID808
Feature activation+3.91e+00

Pos logit contributions
ged+0.363
iked+0.352
 down+0.344
 onward+0.340
ls+0.336
Neg logit contributions
vous-0.459
 virtue-0.454
rig-0.449
 importance-0.431
 least-0.423
Token.
Token ID13
Feature activation-2.50e-02

Pos logit contributions
ged+0.094
iked+0.092
 down+0.091
 onward+0.085
leys+0.082
Neg logit contributions
 virtue-0.138
vous-0.137
rig-0.135
Yes-0.132
 importance-0.132
Token<|endoftext|>
Token ID50256
Feature activation-1.57e+00

Pos logit contributions
vous+0.001
 virtue+0.001
rig+0.001
 importance+0.001
 matter+0.001
Neg logit contributions
 down-0.001
ged-0.001
iked-0.001
 onward-0.001
am-0.000
TokenOnce
Token ID7454
Feature activation+3.02e+00

Pos logit contributions
vous+0.054
Yes+0.053
 importance+0.052
rig+0.052
 virtue+0.052
Neg logit contributions
iked-0.038
ged-0.038
 down-0.035
leys-0.034
am-0.033
Token there
Token ID612
Feature activation+4.14e+00

Pos logit contributions
ged+0.097
iked+0.094
 down+0.088
 onward+0.087
 ashore+0.086
Neg logit contributions
rig-0.078
Yes-0.074
 importance-0.073
vous-0.073
 virtue-0.071
Token whistle
Token ID16121
Feature activation+1.55e+00

Pos logit contributions
vous+0.078
 virtue+0.076
rig+0.076
Yes+0.074
 importance+0.073
Neg logit contributions
ged-0.131
iked-0.131
 down-0.128
 onward-0.124
leys-0.122
Token.
Token ID13
Feature activation+7.27e-01

Pos logit contributions
 down+0.036
ged+0.034
iked+0.032
 onward+0.031
,+0.029
Neg logit contributions
 virtue-0.060
vous-0.058
rig-0.057
 importance-0.057
Yes-0.056
Token The
Token ID383
Feature activation-2.66e+00

Pos logit contributions
 down+0.016
ged+0.016
iked+0.016
 onward+0.015
am+0.014
Neg logit contributions
vous-0.027
 virtue-0.027
rig-0.026
 importance-0.026
Yes-0.026
Token train
Token ID4512
Feature activation+8.12e-01

Pos logit contributions
 virtue+0.099
rig+0.094
illa+0.089
vous+0.085
grand+0.082
Neg logit contributions
 down-0.071
,-0.067
ged-0.062
 he-0.061
 his-0.061
Token was
Token ID373
Feature activation-2.84e+00

Pos logit contributions
ged+0.020
 down+0.020
iked+0.019
 onward+0.018
am+0.017
Neg logit contributions
 virtue-0.030
vous-0.029
rig-0.029
Yes-0.028
leaf-0.027
Token arriving
Token ID14820
Feature activation+1.39e+01

Pos logit contributions
 virtue+0.089
vous+0.086
rig+0.084
Yes+0.083
 importance+0.082
Neg logit contributions
 down-0.087
ged-0.084
iked-0.078
 onward-0.078
 ashore-0.075
Token!
Token ID0
Feature activation-9.43e-01

Pos logit contributions
ged+0.379
 down+0.372
iked+0.370
 onward+0.347
leys+0.333
Neg logit contributions
 virtue-0.450
vous-0.448
rig-0.441
Yes-0.433
 importance-0.431
Token Exc
Token ID25268
Feature activation-1.14e+00

Pos logit contributions
vous+0.034
 virtue+0.034
rig+0.033
 matter+0.033
 importance+0.033
Neg logit contributions
 down-0.023
ged-0.022
iked-0.022
 onward-0.021
ls-0.019
Tokenited
Token ID863
Feature activation+5.31e-01

Pos logit contributions
 importance+0.029
 virtue+0.028
vous+0.028
 song+0.026
 meaning+0.026
Neg logit contributions
ged-0.041
ls-0.039
iked-0.038
 down-0.038
 onward-0.037
Tokenly
Token ID306
Feature activation+5.76e+00

Pos logit contributions
ged+0.010
iked+0.010
 onward+0.009
leys+0.009
 down+0.009
Neg logit contributions
 matter-0.020
Yes-0.020
vous-0.020
 years-0.020
 importance-0.020
Token,
Token ID11
Feature activation+9.73e+00

Pos logit contributions
leys+0.087
iked+0.086
 down+0.080
ged+0.079
 onward+0.074
Neg logit contributions
Yes-0.238
 virtue-0.236
vous-0.234
rig-0.232
 child-0.231
Token he
Token ID339
Feature activation+6.77e+00

Pos logit contributions
Yes+0.012
 matter+0.011
 least+0.010
 bit+0.010
 child+0.010
Neg logit contributions
leys-0.010
ged-0.010
iked-0.010
 ashore-0.009
rolling-0.008
Token passed
Token ID3804
Feature activation+4.94e+00

Pos logit contributions
ged+0.183
 down+0.180
iked+0.172
am+0.167
ls+0.166
Neg logit contributions
 virtue-0.243
vous-0.235
rig-0.221
 importance-0.218
 matter-0.211
Token it
Token ID340
Feature activation+2.87e+00

Pos logit contributions
 down+0.111
ged+0.104
iked+0.094
 onward+0.092
ls+0.087
Neg logit contributions
 virtue-0.202
rig-0.201
vous-0.199
 importance-0.193
Yes-0.184
Token to
Token ID284
Feature activation-2.35e+00

Pos logit contributions
ged+0.077
 down+0.076
iked+0.075
 onward+0.071
leys+0.068
Neg logit contributions
 virtue-0.093
vous-0.093
rig-0.091
Yes-0.090
 importance-0.089
Token another
Token ID1194
Feature activation-2.48e+00

Pos logit contributions
rig+0.106
 virtue+0.106
vous+0.104
 importance+0.098
leaf+0.096
Neg logit contributions
 down-0.043
ged-0.039
 his-0.036
,-0.033
 them-0.032
Token child
Token ID1200
Feature activation-1.32e+01

Pos logit contributions
 virtue+0.092
leaf+0.088
vous+0.087
rig+0.086
 Tooth+0.081
Neg logit contributions
,-0.068
 down-0.065
 his-0.051
ged-0.050
 onward-0.050
Token,
Token ID11
Feature activation+9.14e+00

Pos logit contributions
 virtue+0.541
vous+0.531
rig+0.522
 importance+0.520
Yes+0.508
Neg logit contributions
 down-0.267
ged-0.259
iked-0.247
 onward-0.228
,-0.222
Token who
Token ID508
Feature activation-7.09e+00

Pos logit contributions
 down+0.298
ged+0.270
,+0.258
 his+0.242
 onward+0.237
Neg logit contributions
vous-0.312
 virtue-0.309
 importance-0.286
rig-0.283
 matter-0.271
Token also
Token ID635
Feature activation-3.90e+00

Pos logit contributions
 virtue+0.278
rig+0.265
vous+0.254
 importance+0.248
resa+0.227
Neg logit contributions
ged-0.178
 down-0.174
,-0.170
ls-0.168
 his-0.164
Token looked
Token ID3114
Feature activation+6.93e+00

Pos logit contributions
 virtue+0.127
rig+0.122
vous+0.120
 importance+0.115
Yes+0.114
Neg logit contributions
ged-0.117
 down-0.111
iked-0.104
,-0.103
am-0.101
Token at
Token ID379
Feature activation+2.83e+00

Pos logit contributions
 down+0.120
ged+0.112
iked+0.102
 onward+0.096
ls+0.091
Neg logit contributions
 virtue-0.305
vous-0.304
rig-0.296
 importance-0.294
Yes-0.291
Token was
Token ID373
Feature activation-3.38e+00

Pos logit contributions
ged+0.149
 down+0.147
iked+0.146
 onward+0.139
leys+0.135
Neg logit contributions
vous-0.100
 virtue-0.099
rig-0.096
Yes-0.095
 importance-0.094
Token a
Token ID257
Feature activation-4.55e+00

Pos logit contributions
 virtue+0.107
rig+0.102
vous+0.100
 importance+0.098
Yes+0.095
Neg logit contributions
 down-0.100
ged-0.099
iked-0.094
 onward-0.090
,-0.087
Token mom
Token ID1995
Feature activation-8.07e+00

Pos logit contributions
 virtue+0.126
vous+0.124
rig+0.121
 importance+0.118
leaf+0.117
Neg logit contributions
 down-0.146
ged-0.141
iked-0.133
,-0.132
ls-0.131
Token and
Token ID290
Feature activation-4.39e+00

Pos logit contributions
 virtue+0.260
rig+0.246
 importance+0.238
vous+0.236
leaf+0.227
Neg logit contributions
 down-0.252
ged-0.238
,-0.228
iked-0.225
am-0.213
Token a
Token ID257
Feature activation-4.58e+00

Pos logit contributions
vous+0.124
Yes+0.123
 virtue+0.120
 importance+0.117
leaf+0.115
Neg logit contributions
iked-0.136
ged-0.135
 down-0.132
 onward-0.129
leys-0.126
Token child
Token ID1200
Feature activation-1.31e+01

Pos logit contributions
 virtue+0.144
rig+0.143
vous+0.142
 importance+0.132
leaf+0.130
Neg logit contributions
 down-0.138
,-0.127
ged-0.125
iked-0.112
 onward-0.112
Token who
Token ID508
Feature activation-7.13e+00

Pos logit contributions
 virtue+0.468
rig+0.458
 importance+0.448
vous+0.446
 matter+0.424
Neg logit contributions
 down-0.345
ged-0.345
iked-0.325
,-0.310
am-0.293
Token liked
Token ID8288
Feature activation-4.10e+00

Pos logit contributions
rig+0.237
 virtue+0.235
vous+0.218
leaf+0.214
 importance+0.210
Neg logit contributions
 down-0.194
ged-0.190
,-0.176
iked-0.174
 his-0.167
Token to
Token ID284
Feature activation-2.37e+00

Pos logit contributions
 virtue+0.195
rig+0.195
vous+0.192
ight+0.175
 deserve+0.174
Neg logit contributions
 down-0.073
iked-0.059
 his-0.058
,-0.054
ged-0.053
Token go
Token ID467
Feature activation+4.44e+00

Pos logit contributions
 virtue+0.079
rig+0.076
vous+0.074
 importance+0.072
leaf+0.070
Neg logit contributions
 down-0.065
iked-0.061
,-0.060
ged-0.060
am-0.057
Token for
Token ID329
Feature activation-3.99e+00

Pos logit contributions
ged+0.162
bled+0.149
leys+0.149
iked+0.147
iece+0.147
Neg logit contributions
leaf-0.099
 elderly-0.099
Yes-0.098
 lecture-0.093
rig-0.092
Token<|endoftext|>
Token ID50256
Feature activation-1.56e+00

Pos logit contributions
 virtue+0.001
vous+0.001
rig+0.001
 importance+0.001
Yes+0.001
Neg logit contributions
ged-0.001
 down-0.001
iked-0.001
 onward-0.001
leys-0.000
TokenL
Token ID43
Feature activation-4.95e+00

Pos logit contributions
Yes+0.054
vous+0.053
 importance+0.052
rig+0.051
leaf+0.050
Neg logit contributions
ged-0.039
iked-0.038
leys-0.034
 down-0.034
 onward-0.032
Tokenily
Token ID813
Feature activation-2.30e+00

Pos logit contributions
vous+0.124
rig+0.115
Yes+0.113
 virtue+0.111
leaf+0.111
Neg logit contributions
ged-0.170
 down-0.170
iked-0.162
 onward-0.161
 ashore-0.149
Token was
Token ID373
Feature activation-3.47e+00

Pos logit contributions
 virtue+0.067
vous+0.067
rig+0.065
Yes+0.064
 importance+0.063
Neg logit contributions
ged-0.070
 down-0.069
iked-0.068
 onward-0.064
am-0.062
Token a
Token ID257
Feature activation-4.67e+00

Pos logit contributions
 virtue+0.126
vous+0.123
 importance+0.120
rig+0.120
Yes+0.118
Neg logit contributions
 down-0.091
ged-0.085
iked-0.081
 onward-0.079
am-0.075
Token child
Token ID1200
Feature activation-1.31e+01

Pos logit contributions
 virtue+0.139
rig+0.134
vous+0.134
 importance+0.130
leaf+0.128
Neg logit contributions
 down-0.148
,-0.135
ged-0.134
 onward-0.127
iked-0.127
Token who
Token ID508
Feature activation-7.21e+00

Pos logit contributions
 virtue+0.603
vous+0.597
 importance+0.595
rig+0.591
leaf+0.557
Neg logit contributions
,-0.239
 down-0.225
ged-0.197
iked-0.170
 onward-0.170
Token loved
Token ID6151
Feature activation-3.83e+00

Pos logit contributions
 virtue+0.203
rig+0.196
vous+0.189
 importance+0.184
Yes+0.181
Neg logit contributions
 down-0.230
ged-0.225
iked-0.217
 onward-0.210
,-0.208
Token to
Token ID284
Feature activation-2.54e+00

Pos logit contributions
 virtue+0.163
vous+0.162
rig+0.160
 importance+0.146
 deserve+0.144
Neg logit contributions
 down-0.084
iked-0.075
ged-0.070
 his-0.069
,-0.063
Token whistle
Token ID16121
Feature activation+1.01e+00

Pos logit contributions
 virtue+0.086
vous+0.083
rig+0.082
 importance+0.080
Yes+0.076
Neg logit contributions
 down-0.069
ged-0.066
iked-0.065
 onward-0.061
,-0.061
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
 down+0.021
ged+0.020
iked+0.019
 onward+0.018
ls+0.017
Neg logit contributions
vous-0.040
 virtue-0.040
rig-0.039
Yes-0.038
 importance-0.038
Token You
Token ID921
Feature activation-6.21e+00

Pos logit contributions
 down+0.000
 onward+0.000
iked+0.000
,+0.000
 He+0.000
Neg logit contributions
vous-0.000
rig-0.000
 virtue-0.000
 matter-0.000
 importance-0.000
Token're
Token ID821
Feature activation-1.83e+00

Pos logit contributions
rig+0.239
 virtue+0.231
vous+0.224
leaf+0.213
resa+0.213
Neg logit contributions
,-0.150
 down-0.141
 out-0.119
 onward-0.114
 ashore-0.113
Token a
Token ID257
Feature activation-4.49e+00

Pos logit contributions
rig+0.063
vous+0.059
 virtue+0.058
Yes+0.057
leaf+0.054
Neg logit contributions
 down-0.054
,-0.048
 his-0.047
 onward-0.045
 out-0.044
Token very
Token ID845
Feature activation-5.30e+00

Pos logit contributions
rig+0.168
ampoo+0.160
leaf+0.160
vous+0.156
 outage+0.150
Neg logit contributions
,-0.106
 down-0.092
 back-0.085
,-0.078
 his-0.076
Token smart
Token ID4451
Feature activation-5.36e+00

Pos logit contributions
rig+0.152
 virtue+0.151
 importance+0.147
vous+0.146
Yes+0.145
Neg logit contributions
 down-0.156
 onward-0.143
iked-0.143
,-0.142
ged-0.142
Token child
Token ID1200
Feature activation-1.31e+01

Pos logit contributions
rig+0.172
leaf+0.161
vous+0.158
Yes+0.156
 virtue+0.155
Neg logit contributions
,-0.174
 down-0.149
ged-0.140
 his-0.130
 out-0.128
Token!"
Token ID2474
Feature activation-4.34e+00

Pos logit contributions
rig+0.519
 virtue+0.487
 importance+0.480
vous+0.477
leaf+0.465
Neg logit contributions
,-0.330
 down-0.326
 onward-0.257
ged-0.253
 his-0.234
Token
Token ID220
Feature activation+4.31e+00

Pos logit contributions
vous+0.181
 virtue+0.181
 matter+0.174
 importance+0.173
rig+0.170
Neg logit contributions
 down-0.093
ged-0.087
 onward-0.082
iked-0.081
,-0.077
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
ged+0.127
iked+0.123
 down+0.122
 onward+0.115
leys+0.111
Neg logit contributions
rig-0.130
 virtue-0.130
vous-0.128
Yes-0.125
 importance-0.124
TokenThe
Token ID464
Feature activation-4.44e+00

Pos logit contributions
 matter+0.058
vous+0.058
 virtue+0.058
 importance+0.055
rig+0.054
Neg logit contributions
ged-0.028
 down-0.028
 onward-0.026
iked-0.026
am-0.024
Token j
Token ID474
Feature activation+1.46e+00

Pos logit contributions
 virtue+0.120
rig+0.119
 deserve+0.113
leaf+0.111
vous+0.105
Neg logit contributions
,-0.145
ged-0.139
 down-0.131
ls-0.129
 sand-0.121
Token?
Token ID30
Feature activation-1.88e+00

Pos logit contributions
rig+0.176
vous+0.168
 virtue+0.167
 importance+0.161
leaf+0.153
Neg logit contributions
,-0.107
 down-0.101
 his-0.092
 he-0.084
ged-0.083
Tokenâ
Token ID22940
Feature activation+7.22e-01

Pos logit contributions
 virtue+0.069
vous+0.068
rig+0.067
 importance+0.067
 matter+0.065
Neg logit contributions
 down-0.044
ged-0.042
iked-0.041
 onward-0.040
am-0.036
Token
Token ID26391
Feature activation+3.33e+00

Pos logit contributions
ged+0.024
 down+0.024
iked+0.024
 onward+0.023
leys+0.022
Neg logit contributions
 virtue-0.018
vous-0.018
rig-0.018
 importance-0.018
Yes-0.017
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
ged+0.094
 down+0.093
iked+0.092
 onward+0.086
leys+0.083
Neg logit contributions
 virtue-0.104
vous-0.104
rig-0.102
Yes-0.100
 importance-0.100
TokenThe
Token ID464
Feature activation-4.18e+00

Pos logit contributions
 virtue+0.048
vous+0.047
rig+0.046
 importance+0.046
Yes+0.045
Neg logit contributions
ged-0.034
 down-0.033
iked-0.033
 onward-0.031
leys-0.029
Token child
Token ID1200
Feature activation-1.31e+01

Pos logit contributions
rig+0.136
 virtue+0.134
vous+0.122
leaf+0.121
Yes+0.118
Neg logit contributions
 down-0.111
iked-0.110
ged-0.107
,-0.106
 ashore-0.101
Token said
Token ID531
Feature activation+2.73e+00

Pos logit contributions
 virtue+0.477
rig+0.460
vous+0.448
 importance+0.433
leaf+0.433
Neg logit contributions
 down-0.354
,-0.344
ged-0.338
am-0.311
iked-0.307
Token,
Token ID11
Feature activation+9.13e+00

Pos logit contributions
ged+0.050
iked+0.050
leys+0.048
 ashore+0.042
rolling+0.041
Neg logit contributions
Yes-0.109
 virtue-0.103
 song-0.103
 bit-0.102
 child-0.101
Token
Token ID6184
Feature activation+1.76e+00

Pos logit contributions
ged+0.165
iked+0.159
 down+0.158
 onward+0.143
leys+0.137
Neg logit contributions
 virtue-0.375
vous-0.374
rig-0.369
Yes-0.367
 importance-0.364
Token
Token ID95
Feature activation+1.02e+00

Pos logit contributions
ged+0.053
 down+0.052
iked+0.051
 onward+0.050
leys+0.049
Neg logit contributions
 virtue-0.053
rig-0.053
vous-0.052
Yes-0.052
leaf-0.050
Token
Token ID26391
Feature activation+3.31e+00

Pos logit contributions
 down+0.029
ged+0.029
iked+0.028
am+0.027
 onward+0.027
Neg logit contributions
 virtue-0.030
rig-0.029
Yes-0.029
 importance-0.029
vous-0.028
Token offered
Token ID4438
Feature activation+2.70e+00

Pos logit contributions
 virtue+0.129
rig+0.125
vous+0.120
 importance+0.117
Yes+0.117
Neg logit contributions
ged-0.128
 down-0.125
iked-0.118
am-0.114
 onward-0.113
Token to
Token ID284
Feature activation-2.34e+00

Pos logit contributions
 down+0.052
 his+0.049
,+0.044
ged+0.042
iked+0.042
Neg logit contributions
vous-0.122
rig-0.121
 virtue-0.118
 importance-0.109
 matter-0.108
Token help
Token ID1037
Feature activation-2.18e+00

Pos logit contributions
vous+0.088
rig+0.086
 virtue+0.082
 importance+0.079
 poet+0.073
Neg logit contributions
 his-0.062
 down-0.062
,-0.056
 their-0.053
 them-0.051
Token the
Token ID262
Feature activation+1.15e-01

Pos logit contributions
vous+0.083
 virtue+0.081
rig+0.081
 importance+0.078
leaf+0.077
Neg logit contributions
 down-0.054
,-0.049
ged-0.049
 his-0.046
iked-0.045
Token other
Token ID584
Feature activation-4.53e+00

Pos logit contributions
 down+0.004
iked+0.004
ged+0.004
 onward+0.004
am+0.004
Neg logit contributions
 virtue-0.003
rig-0.003
vous-0.003
Yes-0.002
leaf-0.002
Token child
Token ID1200
Feature activation-1.31e+01

Pos logit contributions
vous+0.096
 virtue+0.096
rig+0.093
Yes+0.091
 importance+0.091
Neg logit contributions
ged-0.174
 down-0.172
iked-0.171
 onward-0.163
leys-0.159
Token organize
Token ID16481
Feature activation+4.02e+00

Pos logit contributions
vous+0.494
 virtue+0.492
rig+0.480
Yes+0.474
 importance+0.473
Neg logit contributions
 down-0.301
ged-0.282
iked-0.274
 onward-0.256
am-0.251
Token his
Token ID465
Feature activation+5.91e+00

Pos logit contributions
 down+0.086
ged+0.081
,+0.073
iked+0.072
 onward+0.072
Neg logit contributions
vous-0.167
rig-0.160
 virtue-0.159
 importance-0.153
leaf-0.153
Token things
Token ID1243
Feature activation-5.09e+00

Pos logit contributions
ged+0.143
iked+0.138
 down+0.136
 onward+0.129
leys+0.120
Neg logit contributions
vous-0.212
 virtue-0.211
rig-0.207
 importance-0.206
Yes-0.202
Token into
Token ID656
Feature activation+2.69e+00

Pos logit contributions
 virtue+0.187
vous+0.186
rig+0.183
Yes+0.180
 importance+0.180
Neg logit contributions
ged-0.116
 down-0.113
iked-0.113
 onward-0.104
leys-0.099
Token the
Token ID262
Feature activation+7.32e-02

Pos logit contributions
 down+0.058
ged+0.056
 his+0.051
,+0.050
 onward+0.050
Neg logit contributions
rig-0.108
vous-0.106
 virtue-0.102
leaf-0.102
Yes-0.100
Token
Token ID220
Feature activation+4.34e+00

Pos logit contributions
 virtue+0.167
vous+0.165
rig+0.162
 importance+0.159
leaf+0.153
Neg logit contributions
 down-0.101
ged-0.096
iked-0.095
 onward-0.087
am-0.082
Token
Token ID198
Feature activation-1.41e+00

Pos logit contributions
ged+0.134
iked+0.130
 down+0.126
 onward+0.121
leys+0.117
Neg logit contributions
rig-0.125
Yes-0.123
 virtue-0.122
vous-0.122
 importance-0.118
Token
Token ID198
Feature activation-1.42e+00

Pos logit contributions
 virtue+0.051
vous+0.050
rig+0.049
 importance+0.049
 matter+0.047
Neg logit contributions
 down-0.034
ged-0.034
iked-0.033
 onward-0.031
leys-0.030
TokenSo
Token ID2396
Feature activation-3.61e+00

Pos logit contributions
 virtue+0.045
vous+0.044
rig+0.042
 importance+0.042
 least+0.041
Neg logit contributions
 down-0.041
ged-0.039
iked-0.039
 onward-0.037
leys-0.037
Token the
Token ID262
Feature activation+1.59e-01

Pos logit contributions
 virtue+0.148
Yes+0.147
vous+0.146
rig+0.144
 importance+0.143
Neg logit contributions
ged-0.067
iked-0.064
 down-0.061
 onward-0.057
leys-0.056
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
,+0.004
 down+0.003
iked+0.003
ged+0.003
 sand+0.003
Neg logit contributions
 virtue-0.006
rig-0.006
leaf-0.006
 deserve-0.006
vous-0.006
Token and
Token ID290
Feature activation-4.45e+00

Pos logit contributions
 virtue+0.461
vous+0.455
rig+0.449
Yes+0.441
 importance+0.439
Neg logit contributions
 down-0.322
ged-0.319
iked-0.312
 onward-0.287
am-0.284
Token Mom
Token ID11254
Feature activation-5.79e+00

Pos logit contributions
 virtue+0.199
rig+0.196
vous+0.196
 importance+0.189
leaf+0.187
Neg logit contributions
 down-0.078
ged-0.073
iked-0.068
 onward-0.061
am-0.058
Tokenmy
Token ID1820
Feature activation-2.32e+00

Pos logit contributions
vous+0.118
Yes+0.112
 virtue+0.110
rig+0.110
 importance+0.107
Neg logit contributions
ged-0.227
iked-0.222
 down-0.216
 onward-0.215
ls-0.213
Token sn
Token ID3013
Feature activation+3.20e+00

Pos logit contributions
vous+0.076
 virtue+0.074
rig+0.074
Yes+0.074
 importance+0.073
Neg logit contributions
ged-0.060
iked-0.058
 down-0.058
 onward-0.056
leys-0.053
Tokenugg
Token ID6837
Feature activation+3.80e+00

Pos logit contributions
 down+0.111
ged+0.109
ls+0.108
 onward+0.106
iked+0.105
Neg logit contributions
 virtue-0.074
Yes-0.072
vous-0.069
rig-0.069
leaf-0.062
Token is
Token ID318
Feature activation-2.94e+00

Pos logit contributions
 virtue+0.008
vous+0.008
rig+0.008
Yes+0.008
 importance+0.007
Neg logit contributions
 down-0.007
ls-0.006
ged-0.006
iked-0.006
am-0.006
Token a
Token ID257
Feature activation-4.45e+00

Pos logit contributions
vous+0.094
 virtue+0.091
rig+0.090
Yes+0.088
leaf+0.086
Neg logit contributions
 down-0.086
ged-0.083
iked-0.079
 onward-0.077
am-0.074
Token picture
Token ID4286
Feature activation-5.87e+00

Pos logit contributions
vous+0.155
rig+0.152
leaf+0.143
illa+0.133
Sad+0.131
Neg logit contributions
,-0.116
 down-0.115
 sand-0.104
 sail-0.099
ged-0.098
Token of
Token ID286
Feature activation-5.61e+00

Pos logit contributions
 virtue+0.184
rig+0.182
vous+0.181
 importance+0.175
Yes+0.173
Neg logit contributions
 down-0.174
ged-0.167
iked-0.163
 onward-0.157
,-0.154
Token a
Token ID257
Feature activation-4.47e+00

Pos logit contributions
rig+0.224
vous+0.218
 virtue+0.214
leaf+0.190
Yes+0.185
Neg logit contributions
 down-0.133
 his-0.123
ged-0.122
,-0.121
 their-0.120
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
rig+0.156
vous+0.150
leaf+0.139
 virtue+0.138
 importance+0.133
Neg logit contributions
 down-0.121
,-0.118
ged-0.105
 sand-0.105
 onward-0.100
Token with
Token ID351
Feature activation-2.03e+00

Pos logit contributions
 virtue+0.524
vous+0.510
rig+0.510
 importance+0.502
Yes+0.485
Neg logit contributions
 down-0.281
ged-0.279
iked-0.256
 onward-0.243
,-0.238
Token a
Token ID257
Feature activation-4.49e+00

Pos logit contributions
rig+0.071
 virtue+0.069
vous+0.065
 importance+0.063
Yes+0.062
Neg logit contributions
ged-0.056
 down-0.056
iked-0.051
 onward-0.050
,-0.049
Token sad
Token ID6507
Feature activation-1.60e+00

Pos logit contributions
rig+0.148
vous+0.146
 virtue+0.138
 importance+0.132
leaf+0.131
Neg logit contributions
 down-0.130
ged-0.123
,-0.119
 onward-0.115
ls-0.111
Token face
Token ID1986
Feature activation-3.30e+00

Pos logit contributions
 virtue+0.044
vous+0.043
rig+0.042
 importance+0.042
Yes+0.042
Neg logit contributions
ged-0.052
iked-0.051
 down-0.050
 onward-0.048
leys-0.047
Token and
Token ID290
Feature activation-4.43e+00

Pos logit contributions
vous+0.120
 virtue+0.119
rig+0.117
Yes+0.116
 importance+0.116
Neg logit contributions
ged-0.074
iked-0.073
 down-0.072
 onward-0.067
leys-0.064
TokenOne
Token ID3198
Feature activation+2.40e+00

Pos logit contributions
 virtue+0.043
rig+0.043
vous+0.042
 least+0.042
 importance+0.040
Neg logit contributions
iked-0.032
ged-0.032
 down-0.031
 onward-0.030
leys-0.030
Token day
Token ID1110
Feature activation-1.16e+00

Pos logit contributions
,+0.060
 down+0.048
 his+0.046
 their+0.042
 he+0.040
Neg logit contributions
 virtue-0.099
 least-0.094
leaf-0.093
rig-0.092
 importance-0.089
Token,
Token ID11
Feature activation+9.20e+00

Pos logit contributions
 bit+0.038
 child+0.036
Yes+0.036
 matter+0.036
 years+0.035
Neg logit contributions
leys-0.029
cast-0.028
iece-0.026
iked-0.026
am-0.025
Token a
Token ID257
Feature activation-4.48e+00

Pos logit contributions
 down+0.234
ged+0.214
,+0.213
 his+0.194
iked+0.192
Neg logit contributions
rig-0.375
 virtue-0.363
vous-0.354
 importance-0.336
leaf-0.326
Token little
Token ID1310
Feature activation-7.27e+00

Pos logit contributions
rig+0.140
 virtue+0.138
vous+0.134
leaf+0.130
 least+0.129
Neg logit contributions
 down-0.123
,-0.121
ged-0.110
 onward-0.107
ls-0.106
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 virtue+0.203
rig+0.201
vous+0.193
 importance+0.191
leaf+0.176
Neg logit contributions
 down-0.252
ged-0.237
iked-0.224
,-0.220
ls-0.216
Token was
Token ID373
Feature activation-3.41e+00

Pos logit contributions
vous+0.511
 virtue+0.498
Yes+0.492
rig+0.492
 importance+0.485
Neg logit contributions
ged-0.262
 down-0.259
iked-0.258
 onward-0.239
leys-0.224
Token playing
Token ID2712
Feature activation+6.19e+00

Pos logit contributions
 virtue+0.128
rig+0.127
vous+0.125
Yes+0.123
 importance+0.122
Neg logit contributions
 down-0.082
ged-0.078
iked-0.075
 onward-0.070
am-0.068
Token in
Token ID287
Feature activation+7.37e-01

Pos logit contributions
 down+0.139
ged+0.120
,+0.115
 his+0.112
iked+0.102
Neg logit contributions
 virtue-0.262
rig-0.259
vous-0.250
 importance-0.244
 matter-0.242
Token the
Token ID262
Feature activation+8.13e-02

Pos logit contributions
 down+0.015
 his+0.013
ged+0.013
,+0.012
iked+0.011
Neg logit contributions
 virtue-0.032
rig-0.032
vous-0.031
leaf-0.030
 importance-0.029
Token town
Token ID3240
Feature activation+6.17e-01

Pos logit contributions
ged+0.003
iked+0.003
 down+0.003
 onward+0.003
ls+0.002
Neg logit contributions
vous-0.002
 virtue-0.002
rig-0.002
Yes-0.002
 importance-0.002
Token and
Token ID290
Feature activation-4.36e+00

Pos logit contributions
 virtue+0.080
rig+0.079
 importance+0.075
vous+0.073
Yes+0.071
Neg logit contributions
 down-0.057
ged-0.055
,-0.053
iked-0.049
am-0.045
Token a
Token ID257
Feature activation-4.52e+00

Pos logit contributions
vous+0.127
Yes+0.126
 virtue+0.123
 importance+0.121
leaf+0.118
Neg logit contributions
iked-0.131
ged-0.130
 down-0.125
 onward-0.124
leys-0.121
Token 3
Token ID513
Feature activation-9.71e+00

Pos logit contributions
rig+0.140
 virtue+0.138
vous+0.137
leaf+0.127
 importance+0.126
Neg logit contributions
 down-0.137
,-0.125
ged-0.122
iked-0.113
 onward-0.110
Token year
Token ID614
Feature activation-8.88e+00

Pos logit contributions
 virtue+0.263
 least+0.255
rig+0.252
 importance+0.227
leaf+0.217
Neg logit contributions
ged-0.354
,-0.338
 down-0.338
iked-0.326
ls-0.314
Token old
Token ID1468
Feature activation-9.60e-01

Pos logit contributions
vous+0.177
 elderly+0.177
rig+0.175
 virtue+0.170
 years+0.160
Neg logit contributions
ged-0.371
iked-0.346
 onward-0.334
 down-0.330
leys-0.322
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 virtue+0.023
rig+0.022
vous+0.022
 importance+0.021
Yes+0.021
Neg logit contributions
 down-0.035
ged-0.035
iked-0.034
 onward-0.032
ls-0.031
Token.
Token ID13
Feature activation-5.85e-02

Pos logit contributions
 virtue+0.436
rig+0.432
vous+0.428
 importance+0.417
Yes+0.411
Neg logit contributions
ged-0.351
 down-0.346
iked-0.338
 onward-0.314
am-0.304
Token The
Token ID383
Feature activation-3.47e+00

Pos logit contributions
vous+0.002
Yes+0.002
 virtue+0.002
rig+0.002
 importance+0.002
Neg logit contributions
ged-0.002
iked-0.001
 down-0.001
 onward-0.001
ls-0.001
Token mom
Token ID1995
Feature activation-7.99e+00

Pos logit contributions
 virtue+0.122
rig+0.120
leaf+0.116
 deserve+0.116
vous+0.115
Neg logit contributions
,-0.086
 down-0.082
 back-0.074
 sand-0.072
iked-0.072
Tokenmy
Token ID1820
Feature activation-2.23e+00

Pos logit contributions
 virtue+0.309
rig+0.294
leaf+0.278
 importance+0.277
vous+0.273
Neg logit contributions
 down-0.217
,-0.198
ged-0.178
am-0.177
iked-0.167
Token was
Token ID373
Feature activation-3.47e+00

Pos logit contributions
 virtue+0.086
rig+0.083
 matter+0.080
leaf+0.078
vous+0.077
Neg logit contributions
,-0.057
 down-0.053
am-0.050
ged-0.049
iked-0.045
Token seen
Token ID1775
Feature activation-6.51e-01

Pos logit contributions
 virtue+0.172
rig+0.165
Yes+0.160
vous+0.148
leaf+0.147
Neg logit contributions
ged-0.208
 down-0.205
iked-0.192
leys-0.190
,-0.187
Token.
Token ID13
Feature activation-6.68e-03

Pos logit contributions
rig+0.026
 virtue+0.025
vous+0.025
Yes+0.025
leaf+0.024
Neg logit contributions
 down-0.015
ged-0.014
,-0.014
 onward-0.013
iked-0.013
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
vous+0.000
 virtue+0.000
rig+0.000
 matter+0.000
 importance+0.000
Neg logit contributions
 down-0.000
iked-0.000
ged-0.000
 onward-0.000
am-0.000
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
 matter+0.051
vous+0.051
 virtue+0.050
 importance+0.048
rig+0.047
Neg logit contributions
ged-0.028
 down-0.027
iked-0.027
 onward-0.026
am-0.025
TokenThe
Token ID464
Feature activation-4.16e+00

Pos logit contributions
vous+0.039
 matter+0.038
rig+0.037
 virtue+0.037
 meaning+0.036
Neg logit contributions
iked-0.038
ged-0.038
His-0.037
 onward-0.036
leys-0.035
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 virtue+0.154
leaf+0.153
rig+0.150
 deserve+0.146
 losers+0.137
Neg logit contributions
,-0.109
 sand-0.082
 down-0.078
 back-0.074
ged-0.073
Token was
Token ID373
Feature activation-3.44e+00

Pos logit contributions
 virtue+0.497
vous+0.476
rig+0.470
leaf+0.445
 importance+0.444
Neg logit contributions
,-0.328
 down-0.322
am-0.318
ged-0.317
iked-0.292
Token so
Token ID523
Feature activation-7.86e+00

Pos logit contributions
 virtue+0.099
rig+0.098
vous+0.097
 matter+0.095
leaf+0.094
Neg logit contributions
 down-0.117
 onward-0.105
,-0.104
ged-0.103
am-0.099
Token happy
Token ID3772
Feature activation-1.44e+00

Pos logit contributions
 virtue+0.252
vous+0.247
rig+0.241
 importance+0.238
 matter+0.234
Neg logit contributions
 down-0.223
ged-0.217
iked-0.210
 onward-0.206
am-0.194
Token.
Token ID13
Feature activation-3.62e-02

Pos logit contributions
vous+0.050
 virtue+0.050
rig+0.049
 importance+0.047
Yes+0.047
Neg logit contributions
 down-0.038
ged-0.037
iked-0.036
 onward-0.033
ls-0.032
Token From
Token ID3574
Feature activation-2.79e+00

Pos logit contributions
 virtue+0.001
Yes+0.001
rig+0.001
 importance+0.001
vous+0.001
Neg logit contributions
ged-0.001
 down-0.001
iked-0.001
ls-0.001
leys-0.001
Token He
Token ID679
Feature activation+5.27e+00

Pos logit contributions
 virtue+0.004
vous+0.004
rig+0.004
Yes+0.004
 importance+0.004
Neg logit contributions
ged-0.001
 down-0.001
iked-0.001
 onward-0.001
leys-0.001
Token went
Token ID1816
Feature activation+5.37e+00

Pos logit contributions
 down+0.125
ged+0.122
am+0.116
iked+0.113
,+0.113
Neg logit contributions
 virtue-0.199
vous-0.192
rig-0.190
Yes-0.184
leaf-0.182
Token over
Token ID625
Feature activation+3.41e+00

Pos logit contributions
ged+0.156
iked+0.151
leys+0.144
am+0.141
 onward+0.140
Neg logit contributions
rig-0.159
Yes-0.158
leaf-0.156
vous-0.155
 virtue-0.153
Token to
Token ID284
Feature activation-2.32e+00

Pos logit contributions
 down+0.081
ged+0.076
iked+0.073
,+0.070
 onward+0.068
Neg logit contributions
 virtue-0.136
vous-0.131
rig-0.131
 importance-0.126
 matter-0.123
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
 virtue+0.107
rig+0.102
vous+0.101
 importance+0.097
 years+0.092
Neg logit contributions
 down-0.047
 his-0.042
ged-0.037
,-0.037
 them-0.034
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 down+0.003
 castles+0.003
ls+0.003
 back+0.003
iked+0.003
Neg logit contributions
 virtue-0.004
rig-0.004
vous-0.004
 matter-0.004
leaf-0.003
Token who
Token ID508
Feature activation-7.05e+00

Pos logit contributions
 virtue+0.502
vous+0.482
 importance+0.466
Yes+0.461
leaf+0.460
Neg logit contributions
 down-0.336
,-0.319
ged-0.295
iked-0.291
am-0.274
Token was
Token ID373
Feature activation-3.29e+00

Pos logit contributions
 virtue+0.283
rig+0.274
vous+0.253
 importance+0.251
leaf+0.243
Neg logit contributions
ged-0.173
 down-0.173
,-0.162
 his-0.154
 he-0.154
Token yelling
Token ID22187
Feature activation+4.28e+00

Pos logit contributions
 virtue+0.104
rig+0.103
vous+0.099
Yes+0.098
 importance+0.096
Neg logit contributions
 down-0.100
ged-0.093
,-0.089
 onward-0.088
iked-0.086
Token and
Token ID290
Feature activation-4.38e+00

Pos logit contributions
iked+0.126
ged+0.117
leys+0.111
 onward+0.111
ls+0.110
Neg logit contributions
 virtue-0.125
 importance-0.124
vous-0.123
Yes-0.122
rig-0.120
Token asked
Token ID1965
Feature activation+3.63e+00

Pos logit contributions
 virtue+0.129
vous+0.128
rig+0.126
 importance+0.122
Yes+0.121
Neg logit contributions
ged-0.135
 down-0.134
iked-0.131
 onward-0.123
leys-0.119
Token down
Token ID866
Feature activation+9.58e+00

Pos logit contributions
iked+0.167
ged+0.150
am+0.136
 onward+0.135
rolled+0.131
Neg logit contributions
rig-0.251
Yes-0.238
leaf-0.235
 virtue-0.233
 importance-0.231
Token to
Token ID284
Feature activation-2.33e+00

Pos logit contributions
iked+0.280
ged+0.273
drivers+0.262
leys+0.257
rolled+0.248
Neg logit contributions
Yes-0.266
 elderly-0.255
 years-0.248
 importance-0.244
 meaning-0.238
Token see
Token ID766
Feature activation+2.06e+00

Pos logit contributions
vous+0.078
 virtue+0.078
rig+0.077
Yes+0.075
 importance+0.075
Neg logit contributions
ged-0.061
 down-0.060
iked-0.059
 onward-0.056
leys-0.053
Token a
Token ID257
Feature activation-4.52e+00

Pos logit contributions
 down+0.058
ged+0.056
iked+0.053
 onward+0.051
ls+0.050
Neg logit contributions
 virtue-0.068
vous-0.068
rig-0.067
 importance-0.065
Yes-0.063
Token small
Token ID1402
Feature activation+1.23e+00

Pos logit contributions
vous+0.148
rig+0.145
 virtue+0.144
leaf+0.142
 importance+0.135
Neg logit contributions
 down-0.126
,-0.117
ged-0.109
ls-0.105
 onward-0.104
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 down+0.037
ged+0.034
,+0.034
iked+0.032
 onward+0.032
Neg logit contributions
 virtue-0.038
rig-0.037
vous-0.037
leaf-0.036
 importance-0.035
Token standing
Token ID5055
Feature activation+8.72e+00

Pos logit contributions
vous+0.468
 virtue+0.464
rig+0.460
Yes+0.454
 importance+0.448
Neg logit contributions
ged-0.302
iked-0.296
 down-0.294
 onward-0.273
leys-0.262
Token with
Token ID351
Feature activation-1.94e+00

Pos logit contributions
ged+0.216
iked+0.214
 down+0.205
 onward+0.194
leys+0.187
Neg logit contributions
vous-0.300
 virtue-0.299
rig-0.295
Yes-0.293
 importance-0.288
Token its
Token ID663
Feature activation+4.87e+00

Pos logit contributions
vous+0.052
 virtue+0.052
rig+0.050
Yes+0.050
 importance+0.049
Neg logit contributions
ged-0.064
iked-0.063
 down-0.063
 onward-0.059
leys-0.058
Token arms
Token ID5101
Feature activation-3.89e+00

Pos logit contributions
 down+0.132
ged+0.125
iked+0.120
 onward+0.115
am+0.113
Neg logit contributions
 virtue-0.167
rig-0.164
vous-0.164
Yes-0.158
leaf-0.156
Token folded
Token ID24650
Feature activation+6.91e+00

Pos logit contributions
rig+0.094
 meaning+0.093
vous+0.093
 importance+0.090
ight+0.089
Neg logit contributions
iked-0.120
ged-0.109
ls-0.108
 onward-0.107
am-0.102
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
Yes+0.002
 virtue+0.002
rig+0.002
vous+0.002
 importance+0.002
Neg logit contributions
ged-0.002
 down-0.002
iked-0.002
ls-0.002
leys-0.002
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
Yes+0.038
 virtue+0.038
rig+0.037
vous+0.037
 importance+0.036
Neg logit contributions
ged-0.042
 down-0.041
iked-0.040
 onward-0.037
leys-0.037
Token"
Token ID1
Feature activation-6.23e-01

Pos logit contributions
 virtue+0.035
vous+0.035
Yes+0.034
rig+0.034
 importance+0.033
Neg logit contributions
ged-0.046
 down-0.045
iked-0.044
 onward-0.042
ls-0.041
TokenLet
Token ID5756
Feature activation-7.20e+00

Pos logit contributions
 virtue+0.019
rig+0.019
vous+0.018
 least+0.016
 importance+0.016
Neg logit contributions
ged-0.019
 down-0.017
iked-0.016
 onward-0.016
leys-0.015
Token the
Token ID262
Feature activation+1.92e-01

Pos logit contributions
 virtue+0.260
rig+0.256
vous+0.252
leaf+0.246
 importance+0.244
Neg logit contributions
 down-0.186
ged-0.167
,-0.162
am-0.158
 onward-0.155
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 down+0.005
,+0.004
 out+0.004
 off+0.004
 back+0.004
Neg logit contributions
rig-0.008
 virtue-0.006
ampoo-0.006
rou-0.006
leaf-0.006
Token decide
Token ID5409
Feature activation-3.28e-01

Pos logit contributions
 virtue+0.469
vous+0.453
rig+0.453
 importance+0.452
Yes+0.438
Neg logit contributions
 down-0.348
ged-0.308
iked-0.294
,-0.292
am-0.285
Token,"
Token ID553
Feature activation-1.50e+00

Pos logit contributions
vous+0.011
 virtue+0.011
rig+0.011
 importance+0.011
Yes+0.010
Neg logit contributions
 down-0.009
ged-0.009
iked-0.008
 onward-0.008
,-0.008
Token said
Token ID531
Feature activation+2.72e+00

Pos logit contributions
 virtue+0.052
vous+0.051
rig+0.050
 importance+0.049
 matter+0.046
Neg logit contributions
 down-0.040
ged-0.040
iked-0.039
 onward-0.036
am-0.035
Token Mum
Token ID38367
Feature activation-4.40e+00

Pos logit contributions
ged+0.091
iked+0.088
leys+0.087
 down+0.086
 onward+0.083
Neg logit contributions
Yes-0.071
vous-0.065
leaf-0.064
 virtue-0.063
 child-0.063
Token stern
Token ID26370
Feature activation+2.90e+00

Pos logit contributions
vous+0.154
rig+0.152
Yes+0.151
 virtue+0.151
 importance+0.145
Neg logit contributions
ged-0.103
iked-0.102
 down-0.097
 onward-0.095
leys-0.092
Token sand
Token ID6450
Feature activation+6.82e+00

Pos logit contributions
 down+0.008
ged+0.007
iked+0.007
 onward+0.007
leys+0.006
Neg logit contributions
 virtue-0.010
rig-0.010
vous-0.010
Yes-0.010
 importance-0.010
Token box
Token ID3091
Feature activation-4.62e-01

Pos logit contributions
ged+0.184
 down+0.182
iked+0.180
 onward+0.168
leys+0.162
Neg logit contributions
 virtue-0.222
vous-0.221
rig-0.217
Yes-0.213
 importance-0.212
Token.
Token ID13
Feature activation+1.27e-01

Pos logit contributions
 virtue+0.015
vous+0.015
rig+0.015
Yes+0.015
 importance+0.015
Neg logit contributions
ged-0.012
 down-0.012
iked-0.012
 onward-0.011
leys-0.011
Token The
Token ID383
Feature activation-3.25e+00

Pos logit contributions
ged+0.003
 down+0.003
iked+0.003
 onward+0.003
leys+0.003
Neg logit contributions
 virtue-0.004
vous-0.004
rig-0.004
Yes-0.004
 importance-0.004
Token other
Token ID584
Feature activation-4.49e+00

Pos logit contributions
rig+0.105
 virtue+0.102
Yes+0.096
vous+0.091
leaf+0.091
Neg logit contributions
 down-0.099
 castles-0.088
,-0.087
ged-0.085
 sand-0.085
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 virtue+0.114
rig+0.111
Yes+0.098
leaf+0.098
vous+0.095
Neg logit contributions
 down-0.164
iked-0.161
ged-0.160
,-0.156
am-0.156
Token shouted
Token ID17293
Feature activation+3.11e+00

Pos logit contributions
 virtue+0.502
rig+0.480
 importance+0.466
vous+0.458
Yes+0.458
Neg logit contributions
ged-0.332
 down-0.325
,-0.313
am-0.295
iked-0.281
Token:
Token ID25
Feature activation+3.14e+00

Pos logit contributions
iked+0.076
ged+0.074
leys+0.072
 onward+0.069
 valleys+0.068
Neg logit contributions
 virtue-0.101
 importance-0.098
rig-0.097
Yes-0.096
 song-0.094
Token "
Token ID366
Feature activation-1.01e+00

Pos logit contributions
ged+0.081
iked+0.081
ls+0.077
leys+0.075
am+0.074
Neg logit contributions
Yes-0.104
 importance-0.100
 virtue-0.098
rig-0.096
vous-0.093
TokenHelp
Token ID22087
Feature activation-3.37e+00

Pos logit contributions
 virtue+0.034
rig+0.034
 importance+0.029
 years+0.029
 meaning+0.029
Neg logit contributions
ged-0.029
 down-0.026
His-0.024
ging-0.024
iked-0.023
Token!
Token ID0
Feature activation-1.46e+00

Pos logit contributions
 virtue+0.112
rig+0.110
vous+0.108
 importance+0.107
Yes+0.104
Neg logit contributions
 down-0.096
ged-0.095
iked-0.089
 onward-0.084
,-0.083
Token to
Token ID284
Feature activation-2.40e+00

Pos logit contributions
 virtue+0.174
Yes+0.170
 importance+0.169
vous+0.169
rig+0.167
Neg logit contributions
ged-0.153
iked-0.152
 onward-0.139
leys-0.139
ls-0.137
Token everyone
Token ID2506
Feature activation-4.27e+00

Pos logit contributions
 virtue+0.108
rig+0.107
vous+0.106
 importance+0.102
Yes+0.101
Neg logit contributions
 down-0.040
ged-0.036
iked-0.033
 onward-0.032
 his-0.030
Token.
Token ID13
Feature activation+4.33e-02

Pos logit contributions
 virtue+0.163
vous+0.163
rig+0.160
 importance+0.157
Yes+0.157
Neg logit contributions
 down-0.091
ged-0.091
iked-0.088
 onward-0.081
ls-0.077
Token So
Token ID1406
Feature activation-1.80e+00

Pos logit contributions
 down+0.001
ged+0.001
iked+0.001
 onward+0.001
am+0.001
Neg logit contributions
vous-0.002
 virtue-0.002
rig-0.002
 importance-0.002
Yes-0.002
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
Yes+0.081
 virtue+0.081
 importance+0.079
 matter+0.077
vous+0.077
Neg logit contributions
ged-0.026
iked-0.024
leys-0.023
 down-0.020
ls-0.018
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
rig+0.005
 virtue+0.004
vous+0.004
ampoo+0.004
leaf+0.004
Neg logit contributions
 down-0.005
,-0.005
 back-0.004
ged-0.004
ls-0.004
Token started
Token ID2067
Feature activation+4.61e+00

Pos logit contributions
 virtue+0.494
rig+0.485
vous+0.480
Yes+0.456
leaf+0.454
Neg logit contributions
am-0.310
 down-0.307
ged-0.306
,-0.306
iked-0.287
Token to
Token ID284
Feature activation-2.44e+00

Pos logit contributions
ged+0.129
iked+0.127
 down+0.123
leys+0.120
 onward+0.119
Neg logit contributions
 virtue-0.138
vous-0.138
rig-0.138
 importance-0.136
Yes-0.135
Token sing
Token ID1702
Feature activation-5.45e-02

Pos logit contributions
 virtue+0.079
vous+0.079
rig+0.074
leaf+0.072
 importance+0.071
Neg logit contributions
 down-0.072
ged-0.064
,-0.064
iked-0.061
 his-0.060
Token a
Token ID257
Feature activation-4.55e+00

Pos logit contributions
 virtue+0.002
vous+0.002
rig+0.002
Yes+0.002
 importance+0.002
Neg logit contributions
ged-0.001
iked-0.001
 down-0.001
 onward-0.001
leys-0.001
Token special
Token ID2041
Feature activation-1.29e+00

Pos logit contributions
vous+0.135
illa+0.121
leaf+0.120
 virtue+0.115
resa+0.114
Neg logit contributions
,-0.147
 down-0.143
 sail-0.127
 back-0.124
 onward-0.122
Token compassionate
Token ID32533
Feature activation-2.58e+00

Pos logit contributions
vous+0.121
rig+0.118
 virtue+0.113
 importance+0.107
leaf+0.102
Neg logit contributions
 down-0.145
ged-0.135
iked-0.134
 onward-0.129
,-0.127
Token,
Token ID11
Feature activation+9.08e+00

Pos logit contributions
vous+0.109
rig+0.108
 virtue+0.105
leaf+0.103
Yes+0.102
Neg logit contributions
 down-0.049
ged-0.045
iked-0.045
 onward-0.041
,-0.040
Token and
Token ID290
Feature activation-4.36e+00

Pos logit contributions
,+0.235
 down+0.234
 his+0.207
 he+0.202
 onward+0.199
Neg logit contributions
vous-0.336
rig-0.326
 virtue-0.315
resa-0.314
leaf-0.310
Token the
Token ID262
Feature activation+1.81e-02

Pos logit contributions
rig+0.164
vous+0.162
 virtue+0.152
resa+0.144
leaf+0.144
Neg logit contributions
 down-0.111
,-0.100
 his-0.096
ged-0.093
 onward-0.093
Token small
Token ID1402
Feature activation+1.11e+00

Pos logit contributions
 down+0.001
,+0.000
ged+0.000
 his+0.000
 onward+0.000
Neg logit contributions
rig-0.001
 virtue-0.001
vous-0.001
leaf-0.001
icated-0.001
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 down+0.042
ged+0.042
iked+0.040
 onward+0.038
ls+0.038
Neg logit contributions
rig-0.025
 virtue-0.025
vous-0.025
Yes-0.023
leaf-0.023
Token was
Token ID373
Feature activation-3.44e+00

Pos logit contributions
rig+0.431
vous+0.411
leaf+0.398
 virtue+0.397
resa+0.379
Neg logit contributions
,-0.385
 down-0.384
ged-0.362
am-0.351
 onward-0.347
Token always
Token ID1464
Feature activation-2.36e+00

Pos logit contributions
rig+0.096
vous+0.092
 virtue+0.089
leaf+0.087
Yes+0.085
Neg logit contributions
 down-0.118
ged-0.108
,-0.108
 onward-0.108
 his-0.105
Token dressed
Token ID12049
Feature activation+3.84e+00

Pos logit contributions
rig+0.069
vous+0.069
 virtue+0.069
Yes+0.065
 importance+0.065
Neg logit contributions
 down-0.074
ged-0.072
iked-0.068
 onward-0.067
am-0.063
Token nicely
Token ID16576
Feature activation+2.88e+00

Pos logit contributions
 down+0.097
ged+0.095
iked+0.092
 onward+0.087
am+0.082
Neg logit contributions
vous-0.134
 virtue-0.133
rig-0.131
Yes-0.128
 importance-0.127
Token.
Token ID13
Feature activation-5.92e-02

Pos logit contributions
 down+0.059
ged+0.056
iked+0.053
 onward+0.052
,+0.048
Neg logit contributions
vous-0.117
rig-0.114
 virtue-0.114
Yes-0.112
leaf-0.110
Token sky
Token ID6766
Feature activation-3.22e+00

Pos logit contributions
 down+0.001
 sand+0.000
 castles+0.000
 ashore+0.000
,+0.000
Neg logit contributions
vous-0.001
 virtue-0.001
rig-0.001
 teaches-0.001
ampoo-0.001
Token.
Token ID13
Feature activation-3.49e-02

Pos logit contributions
Yes+0.100
rig+0.098
vous+0.098
 importance+0.098
 matter+0.096
Neg logit contributions
ged-0.090
iked-0.085
 onward-0.079
leys-0.078
ls-0.078
Token Suddenly
Token ID24975
Feature activation+3.14e+00

Pos logit contributions
Yes+0.001
 importance+0.001
vous+0.001
rig+0.001
 child+0.001
Neg logit contributions
ged-0.001
ls-0.001
ging-0.001
ooming-0.001
iked-0.001
Token,
Token ID11
Feature activation+9.16e+00

Pos logit contributions
agged+0.101
arl+0.098
agons+0.097
iked+0.097
leys+0.096
Neg logit contributions
 child-0.076
 bit-0.070
 cater-0.068
 never-0.067
 matter-0.066
Token the
Token ID262
Feature activation-6.26e-03

Pos logit contributions
iked+0.277
ged+0.275
am+0.261
leys+0.258
 onward+0.255
Neg logit contributions
Yes-0.259
vous-0.245
 importance-0.241
 matter-0.237
 child-0.235
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 virtue+0.000
rig+0.000
vous+0.000
 deserve+0.000
 teaches+0.000
Neg logit contributions
 down-0.000
 sand-0.000
,-0.000
 back-0.000
iked-0.000
Token heard
Token ID2982
Feature activation+2.83e-01

Pos logit contributions
vous+0.409
 virtue+0.404
rig+0.397
Yes+0.393
 importance+0.392
Neg logit contributions
ged-0.358
iked-0.353
 down-0.353
 onward-0.331
leys-0.316
Token a
Token ID257
Feature activation-4.57e+00

Pos logit contributions
ged+0.009
 down+0.009
iked+0.009
 onward+0.009
leys+0.008
Neg logit contributions
 virtue-0.008
vous-0.008
rig-0.007
Yes-0.007
 importance-0.007
Token noise
Token ID7838
Feature activation-2.46e+00

Pos logit contributions
 virtue+0.133
vous+0.130
rig+0.123
 importance+0.123
leaf+0.120
Neg logit contributions
 down-0.143
ged-0.137
iked-0.131
 onward-0.127
ls-0.127
Token.
Token ID13
Feature activation-6.47e-02

Pos logit contributions
vous+0.082
rig+0.081
Yes+0.080
 importance+0.077
 matter+0.077
Neg logit contributions
iked-0.064
ged-0.063
 onward-0.060
 down-0.059
leys-0.058
Token He
Token ID679
Feature activation+5.15e+00

Pos logit contributions
Yes+0.002
 child+0.001
vous+0.001
rig+0.001
 importance+0.001
Neg logit contributions
ged-0.002
ls-0.002
iked-0.002
ooming-0.002
ging-0.002
Token the
Token ID262
Feature activation+1.91e-01

Pos logit contributions
ged+0.184
 down+0.182
iked+0.179
 onward+0.168
leys+0.160
Neg logit contributions
 virtue-0.252
vous-0.251
rig-0.247
Yes-0.242
 importance-0.241
Token honey
Token ID12498
Feature activation-3.40e-01

Pos logit contributions
 down+0.004
,+0.004
ls+0.003
 out+0.003
 back+0.003
Neg logit contributions
rig-0.008
leaf-0.008
 virtue-0.008
Yes-0.008
vous-0.007
Token and
Token ID290
Feature activation-4.34e+00

Pos logit contributions
 virtue+0.010
vous+0.010
rig+0.010
Yes+0.010
 importance+0.010
Neg logit contributions
ged-0.010
iked-0.010
 down-0.009
 onward-0.009
leys-0.009
Token thanked
Token ID26280
Feature activation+1.65e-01

Pos logit contributions
 virtue+0.153
rig+0.149
vous+0.148
 importance+0.141
Yes+0.137
Neg logit contributions
 down-0.120
ged-0.115
iked-0.110
ls-0.103
 onward-0.101
Token the
Token ID262
Feature activation+1.64e-01

Pos logit contributions
 his+0.003
 down+0.003
,+0.003
 them+0.002
ged+0.002
Neg logit contributions
 virtue-0.008
rig-0.008
vous-0.008
 importance-0.007
leaf-0.007
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
,+0.004
 down+0.003
 hut+0.003
ls+0.003
 deeper+0.003
Neg logit contributions
leaf-0.006
 virtue-0.006
rig-0.006
 deserve-0.005
ampoo-0.005
Token again
Token ID757
Feature activation+2.62e+00

Pos logit contributions
vous+0.494
 virtue+0.492
rig+0.480
Yes+0.474
 importance+0.474
Neg logit contributions
 down-0.284
ged-0.280
iked-0.274
 onward-0.253
am-0.240
Token.
Token ID13
Feature activation+9.28e-02

Pos logit contributions
 down+0.050
ged+0.047
iked+0.046
,+0.045
 onward+0.043
Neg logit contributions
vous-0.110
 virtue-0.109
rig-0.107
leaf-0.105
 importance-0.104
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
ged+0.002
 down+0.002
iked+0.002
 onward+0.002
leys+0.002
Neg logit contributions
 virtue-0.003
vous-0.003
rig-0.003
Yes-0.003
 importance-0.003
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
 virtue+0.045
vous+0.045
 importance+0.044
rig+0.043
 matter+0.043
Neg logit contributions
ged-0.031
 down-0.030
iked-0.029
 onward-0.028
am-0.026
TokenFrom
Token ID4863
Feature activation-3.12e+00

Pos logit contributions
 virtue+0.036
 matter+0.035
vous+0.035
rig+0.034
 importance+0.034
Neg logit contributions
ged-0.039
 onward-0.038
iked-0.038
 down-0.036
His-0.036
Token closed
Token ID4838
Feature activation+7.40e+00

Pos logit contributions
 importance+0.136
vous+0.135
Yes+0.134
 meaning+0.133
rig+0.131
Neg logit contributions
iked-0.152
ged-0.148
am-0.141
leys-0.141
ls-0.138
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
iked+0.195
ged+0.189
leys+0.174
 onward+0.169
am+0.168
Neg logit contributions
 virtue-0.237
rig-0.234
 importance-0.232
 years-0.232
Yes-0.230
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
 virtue+0.000
vous+0.000
rig+0.000
 importance+0.000
 matter+0.000
Neg logit contributions
 down-0.000
ged-0.000
iked-0.000
 onward-0.000
am-0.000
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 virtue+0.049
vous+0.048
rig+0.047
 importance+0.047
 matter+0.046
Neg logit contributions
ged-0.032
 down-0.031
iked-0.030
 onward-0.029
ls-0.027
TokenThe
Token ID464
Feature activation-4.18e+00

Pos logit contributions
 virtue+0.042
 least+0.040
rig+0.040
 importance+0.039
vous+0.038
Neg logit contributions
 down-0.038
ged-0.038
iked-0.037
 onward-0.037
leys-0.035
Token child
Token ID1200
Feature activation-1.30e+01

Pos logit contributions
 virtue+0.147
leaf+0.133
rig+0.131
 deserve+0.131
Yes+0.126
Neg logit contributions
,-0.115
 down-0.106
ls-0.097
 hut-0.094
 back-0.091
Token smiled
Token ID13541
Feature activation+2.79e+00

Pos logit contributions
 virtue+0.495
rig+0.474
leaf+0.457
vous+0.457
Yes+0.454
Neg logit contributions
 down-0.328
ged-0.319
iked-0.298
,-0.297
am-0.295
Token and
Token ID290
Feature activation-4.44e+00

Pos logit contributions
ged+0.103
iked+0.103
 onward+0.094
leys+0.094
drivers+0.092
Neg logit contributions
Yes-0.063
 importance-0.062
rig-0.061
 elderly-0.059
 rather-0.058
Token asked
Token ID1965
Feature activation+3.46e+00

Pos logit contributions
 virtue+0.123
vous+0.123
rig+0.120
Yes+0.118
 importance+0.117
Neg logit contributions
ged-0.141
 down-0.139
iked-0.139
 onward-0.131
leys-0.127
Token the
Token ID262
Feature activation-8.45e-02

Pos logit contributions
ged+0.100
iked+0.099
leys+0.093
am+0.092
ooming+0.091
Neg logit contributions
Yes-0.102
 importance-0.101
 virtue-0.096
 child-0.095
vous-0.095
Token witch
Token ID16365
Feature activation-5.00e+00

Pos logit contributions
 virtue+0.003
rig+0.003
leaf+0.002
Yes+0.002
 deserve+0.002
Neg logit contributions
 down-0.003
,-0.002
ls-0.002
 back-0.002
 his-0.002
Token<|endoftext|>
Token ID50256
Feature activation-1.41e+00

Pos logit contributions
 down+0.005
iked+0.004
ged+0.004
 onward+0.004
,+0.004
Neg logit contributions
vous-0.010
 virtue-0.010
rig-0.010
leaf-0.010
 matter-0.010
TokenOnce
Token ID7454
Feature activation+3.60e+00

Pos logit contributions
vous+0.044
 virtue+0.044
rig+0.043
Yes+0.043
 importance+0.042
Neg logit contributions
ged-0.039
iked-0.039
 down-0.038
 onward-0.036
leys-0.035
Token upon
Token ID2402
Feature activation-1.04e+00

Pos logit contributions
ged+0.112
iked+0.111
 onward+0.103
 down+0.102
 ashore+0.101
Neg logit contributions
rig-0.093
Yes-0.091
vous-0.090
 importance-0.089
 virtue-0.087
Token a
Token ID257
Feature activation-4.09e+00

Pos logit contributions
 virtue+0.040
rig+0.037
vous+0.035
 importance+0.035
resa+0.035
Neg logit contributions
 down-0.026
 his-0.024
ged-0.024
,-0.023
iked-0.021
Token time
Token ID640
Feature activation-5.79e-01

Pos logit contributions
leaf+0.128
 virtue+0.125
vous+0.120
Yes+0.120
 importance+0.117
Neg logit contributions
,-0.111
ged-0.110
 down-0.108
iked-0.103
leys-0.100
Token,
Token ID11
Feature activation+9.68e+00

Pos logit contributions
Yes+0.020
 ever+0.020
vous+0.020
rig+0.019
 years+0.019
Neg logit contributions
ged-0.012
iked-0.012
leys-0.012
 ashore-0.011
 down-0.011
Token a
Token ID257
Feature activation-4.08e+00

Pos logit contributions
iked+0.301
am+0.260
ged+0.259
leys+0.257
 onward+0.252
Neg logit contributions
Yes-0.292
vous-0.287
 matter-0.266
 importance-0.264
 child-0.262
Token little
Token ID1310
Feature activation-6.80e+00

Pos logit contributions
 virtue+0.111
vous+0.106
rig+0.103
 importance+0.102
leaf+0.100
Neg logit contributions
 down-0.133
ged-0.132
iked-0.124
,-0.122
ls-0.121
Token girl
Token ID2576
Feature activation-6.95e+00

Pos logit contributions
 virtue+0.165
vous+0.162
rig+0.160
 importance+0.156
Yes+0.151
Neg logit contributions
 down-0.243
ged-0.243
iked-0.236
 onward-0.225
ls-0.221
Token named
Token ID3706
Feature activation-4.06e+00

Pos logit contributions
vous+0.154
 virtue+0.149
Yes+0.145
rig+0.144
 importance+0.140
Neg logit contributions
ged-0.260
iked-0.258
 down-0.257
 onward-0.247
leys-0.240
Token Lily
Token ID20037
Feature activation-1.08e+00

Pos logit contributions
vous+0.127
 virtue+0.126
Yes+0.123
rig+0.123
 importance+0.121
Neg logit contributions
ged-0.116
iked-0.113
 down-0.111
 onward-0.106
leys-0.102
Token demanded
Token ID12284
Feature activation+2.49e+00

Pos logit contributions
 down+0.136
ged+0.135
iked+0.124
,+0.122
am+0.121
Neg logit contributions
 virtue-0.173
vous-0.158
rig-0.157
 importance-0.156
leaf-0.152
Token.
Token ID13
Feature activation-7.33e-03

Pos logit contributions
ged+0.056
 down+0.055
iked+0.054
 onward+0.050
ls+0.047
Neg logit contributions
vous-0.094
 virtue-0.094
rig-0.092
 importance-0.090
Yes-0.090
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
vous+0.000
 virtue+0.000
rig+0.000
 importance+0.000
Yes+0.000
Neg logit contributions
ged-0.000
 down-0.000
iked-0.000
 onward-0.000
ls-0.000
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
Yes+0.037
rig+0.037
vous+0.036
 virtue+0.036
 importance+0.035
Neg logit contributions
ged-0.038
 down-0.038
iked-0.038
 onward-0.035
leys-0.034
TokenFinally
Token ID11158
Feature activation-1.78e+00

Pos logit contributions
 virtue+0.035
vous+0.035
rig+0.035
 importance+0.034
Yes+0.034
Neg logit contributions
ged-0.040
 down-0.040
iked-0.040
 onward-0.038
leys-0.036
Token,
Token ID11
Feature activation+9.26e+00

Pos logit contributions
Yes+0.074
 virtue+0.071
 years+0.071
 matter+0.071
 importance+0.071
Neg logit contributions
leys-0.028
ged-0.028
iked-0.027
 down-0.025
am-0.025
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
 down+0.251
ged+0.228
 onward+0.220
,+0.218
iked+0.209
Neg logit contributions
vous-0.356
rig-0.346
 virtue-0.344
 importance-0.327
leaf-0.321
Token door
Token ID3420
Feature activation+1.55e-01

Pos logit contributions
 down+0.004
iked+0.004
,+0.004
 castles+0.004
am+0.004
Neg logit contributions
 virtue-0.008
rig-0.007
leaf-0.007
vous-0.007
Yes-0.007
Token opened
Token ID4721
Feature activation+7.11e+00

Pos logit contributions
ged+0.004
iked+0.004
 down+0.004
 onward+0.004
leys+0.004
Neg logit contributions
vous-0.005
 virtue-0.005
Yes-0.005
rig-0.005
 importance-0.005
Token and
Token ID290
Feature activation-4.34e+00

Pos logit contributions
iked+0.234
ged+0.232
leys+0.217
am+0.206
 onward+0.203
Neg logit contributions
Yes-0.186
 importance-0.181
 virtue-0.179
rig-0.176
 matter-0.175
Token an
Token ID281
Feature activation-4.16e+00

Pos logit contributions
 virtue+0.150
rig+0.150
vous+0.150
 importance+0.141
leaf+0.136
Neg logit contributions
 down-0.121
ged-0.111
iked-0.105
 onward-0.103
ls-0.101
Token.
Token ID13
Feature activation+5.34e-02

Pos logit contributions
ged+0.076
iked+0.075
 down+0.072
 onward+0.068
leys+0.066
Neg logit contributions
 virtue-0.115
vous-0.114
rig-0.113
Yes-0.113
 importance-0.112
Token
Token ID198
Feature activation-1.22e+00

Pos logit contributions
ged+0.002
iked+0.001
 down+0.001
ls+0.001
leys+0.001
Neg logit contributions
Yes-0.002
 virtue-0.002
rig-0.002
 importance-0.002
vous-0.002
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
rig+0.034
Yes+0.034
 virtue+0.034
vous+0.034
 importance+0.033
Neg logit contributions
ged-0.038
iked-0.038
 down-0.038
 onward-0.035
leys-0.034
Token"
Token ID1
Feature activation-5.15e-01

Pos logit contributions
Yes+0.036
 virtue+0.034
rig+0.033
vous+0.033
 importance+0.032
Neg logit contributions
 down-0.038
iked-0.037
ged-0.036
 onward-0.035
am-0.034
TokenRing
Token ID39687
Feature activation-4.86e+00

Pos logit contributions
rig+0.020
 virtue+0.019
 years+0.017
illa+0.017
vous+0.017
Neg logit contributions
ged-0.012
 down-0.010
His-0.010
 onward-0.010
 valleys-0.009
Token,
Token ID11
Feature activation+9.25e+00

Pos logit contributions
 virtue+0.222
rig+0.222
vous+0.221
 importance+0.217
Yes+0.214
Neg logit contributions
ged-0.074
 down-0.073
iked-0.062
 onward-0.057
,-0.057
Token ring
Token ID5858
Feature activation+2.61e+00

Pos logit contributions
 down+0.252
ged+0.241
iked+0.217
 onward+0.217
,+0.217
Neg logit contributions
 virtue-0.323
rig-0.313
vous-0.313
 importance-0.296
Yes-0.286
Token,
Token ID11
Feature activation+9.22e+00

Pos logit contributions
 down+0.070
ged+0.066
iked+0.063
 onward+0.061
,+0.060
Neg logit contributions
 virtue-0.090
vous-0.090
rig-0.088
 importance-0.087
Yes-0.085
Token ring
Token ID5858
Feature activation+2.61e+00

Pos logit contributions
 down+0.246
ged+0.234
,+0.215
 onward+0.212
iked+0.210
Neg logit contributions
 virtue-0.334
vous-0.320
rig-0.319
 importance-0.302
leaf-0.289
Token,
Token ID11
Feature activation+9.21e+00

Pos logit contributions
 down+0.073
ged+0.070
iked+0.066
 onward+0.064
ls+0.063
Neg logit contributions
vous-0.087
 virtue-0.087
rig-0.085
 importance-0.084
Yes-0.081
Token we
Token ID356
Feature activation-4.57e+00

Pos logit contributions
 down+0.248
ged+0.232
,+0.218
 onward+0.212
iked+0.212
Neg logit contributions
 virtue-0.335
vous-0.325
rig-0.320
 importance-0.303
resa-0.291
Token and
Token ID290
Feature activation-4.12e+00

Pos logit contributions
 virtue+0.062
leaf+0.062
rig+0.060
Yes+0.060
vous+0.059
Neg logit contributions
 down-0.040
ged-0.040
,-0.039
am-0.038
ls-0.033
Token his
Token ID465
Feature activation+6.65e+00

Pos logit contributions
 virtue+0.167
rig+0.166
vous+0.164
 importance+0.158
leaf+0.157
Neg logit contributions
 down-0.085
ged-0.083
iked-0.078
 onward-0.071
am-0.068
Token dad
Token ID9955
Feature activation-4.43e+00

Pos logit contributions
 down+0.150
,+0.139
ged+0.135
ls+0.126
 his+0.125
Neg logit contributions
vous-0.263
rig-0.260
 virtue-0.254
 deserve-0.246
leaf-0.245
Token lost
Token ID2626
Feature activation+2.29e+00

Pos logit contributions
 virtue+0.157
rig+0.155
vous+0.154
 importance+0.149
Yes+0.147
Neg logit contributions
ged-0.116
 down-0.115
iked-0.107
 onward-0.102
am-0.098
Token everything
Token ID2279
Feature activation-5.99e-01

Pos logit contributions
 down+0.043
ged+0.040
iked+0.037
 onward+0.035
ls+0.032
Neg logit contributions
vous-0.098
 virtue-0.097
rig-0.097
Yes-0.094
 importance-0.093
Token,
Token ID11
Feature activation+9.72e+00

Pos logit contributions
 virtue+0.021
vous+0.021
rig+0.021
Yes+0.021
 importance+0.021
Neg logit contributions
ged-0.014
iked-0.014
 down-0.014
 onward-0.013
leys-0.012
Token including
Token ID1390
Feature activation-8.67e-01

Pos logit contributions
 down+0.288
 his+0.253
ged+0.241
,+0.237
 he+0.234
Neg logit contributions
 virtue-0.372
vous-0.361
rig-0.355
leaf-0.347
resa-0.344
Token their
Token ID511
Feature activation+6.61e+00

Pos logit contributions
vous+0.032
 virtue+0.032
rig+0.032
Yes+0.031
 importance+0.031
Neg logit contributions
 down-0.020
ged-0.019
iked-0.019
 onward-0.017
am-0.017
Token golf
Token ID13126
Feature activation+5.66e+00

Pos logit contributions
 down+0.181
,+0.167
ged+0.155
 castles+0.149
 sand+0.147
Neg logit contributions
vous-0.228
rig-0.223
resa-0.216
 virtue-0.215
Yes-0.214
Token clubs
Token ID9784
Feature activation-3.11e-01

Pos logit contributions
 down+0.147
ged+0.147
iked+0.142
 onward+0.132
am+0.130
Neg logit contributions
 virtue-0.190
vous-0.190
rig-0.189
Yes-0.183
 importance-0.181
Token.
Token ID13
Feature activation+3.62e-01

Pos logit contributions
 virtue+0.010
vous+0.010
rig+0.010
Yes+0.010
 importance+0.010
Neg logit contributions
 down-0.009
ged-0.009
iked-0.008
 onward-0.008
ls-0.007
Token played
Token ID2826
Feature activation+4.41e+00

Pos logit contributions
 his+0.132
,+0.125
 he+0.124
ged+0.107
am+0.107
Neg logit contributions
 virtue-0.255
rig-0.253
vous-0.245
leaf-0.240
resa-0.236
Token with
Token ID351
Feature activation-1.44e+00

Pos logit contributions
 down+0.122
ged+0.120
iked+0.114
 onward+0.110
ls+0.103
Neg logit contributions
vous-0.146
 virtue-0.145
rig-0.143
 importance-0.137
Yes-0.137
Token his
Token ID465
Feature activation+6.96e+00

Pos logit contributions
rig+0.083
 virtue+0.083
vous+0.081
 importance+0.080
Yes+0.078
Neg logit contributions
 down-0.008
 his-0.006
ged-0.006
,-0.002
ls-0.002
Token cars
Token ID5006
Feature activation-2.13e+00

Pos logit contributions
 down+0.130
,+0.121
 his+0.111
ged+0.108
ls+0.106
Neg logit contributions
vous-0.320
 virtue-0.306
rig-0.303
leaf-0.300
 deserve-0.288
Token again
Token ID757
Feature activation+3.21e+00

Pos logit contributions
 virtue+0.080
vous+0.080
rig+0.079
 importance+0.078
leaf+0.077
Neg logit contributions
 down-0.055
ged-0.050
,-0.049
 onward-0.045
iked-0.045
Token,
Token ID11
Feature activation+9.84e+00

Pos logit contributions
 down+0.073
ged+0.067
,+0.065
 onward+0.062
iked+0.061
Neg logit contributions
vous-0.127
rig-0.126
 virtue-0.125
leaf-0.124
 importance-0.120
Token but
Token ID475
Feature activation-5.25e+00

Pos logit contributions
 down+0.286
ged+0.250
 his+0.244
,+0.231
 he+0.224
Neg logit contributions
vous-0.378
 virtue-0.378
rig-0.366
leaf-0.352
 importance-0.326
Token he
Token ID339
Feature activation+7.73e+00

Pos logit contributions
rig+0.239
vous+0.239
 virtue+0.235
leaf+0.228
Yes+0.227
Neg logit contributions
 down-0.082
ged-0.081
iked-0.073
 onward-0.070
ls-0.061
Token kept
Token ID4030
Feature activation+2.78e+00

Pos logit contributions
 he+0.171
,+0.169
 his+0.168
ged+0.164
am+0.146
Neg logit contributions
leaf-0.332
rig-0.327
 virtue-0.294
 meaning-0.287
Yes-0.285
Token them
Token ID606
Feature activation+4.59e+00

Pos logit contributions
 down+0.069
ged+0.068
iked+0.064
 onward+0.061
am+0.057
Neg logit contributions
vous-0.100
 virtue-0.099
rig-0.099
Yes-0.095
 importance-0.095
Token clean
Token ID3424
Feature activation+2.86e+00

Pos logit contributions
ged+0.138
iked+0.136
 down+0.128
 onward+0.127
leys+0.123
Neg logit contributions
 virtue-0.133
rig-0.131
vous-0.129
Yes-0.127
 importance-0.126
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
ged+0.123
 down+0.120
iked+0.120
 onward+0.112
leys+0.107
Neg logit contributions
 virtue-0.139
vous-0.139
rig-0.137
Yes-0.135
 importance-0.133
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
 virtue+0.050
vous+0.049
 importance+0.048
rig+0.047
leaf+0.046
Neg logit contributions
 down-0.030
ged-0.030
iked-0.029
 onward-0.028
ls-0.026
TokenThen
Token ID6423
Feature activation+6.22e-01

Pos logit contributions
 virtue+0.037
vous+0.037
leaf+0.037
rig+0.036
 importance+0.035
Neg logit contributions
 down-0.043
ged-0.043
iked-0.041
 onward-0.040
leys-0.040
Token,
Token ID11
Feature activation+9.11e+00

Pos logit contributions
iked+0.012
 ashore+0.012
leys+0.012
ged+0.011
am+0.011
Neg logit contributions
Yes-0.025
 matter-0.025
 bit-0.024
 years-0.023
 child-0.023
Token Lily
Token ID20037
Feature activation-1.56e+00

Pos logit contributions
 down+0.214
ged+0.208
iked+0.191
 onward+0.182
,+0.177
Neg logit contributions
rig-0.354
vous-0.352
 virtue-0.352
 importance-0.334
leaf-0.331
Token got
Token ID1392
Feature activation+3.65e+00

Pos logit contributions
vous+0.043
rig+0.041
 importance+0.040
Yes+0.039
 virtue+0.039
Neg logit contributions
ged-0.050
iked-0.049
 down-0.048
 onward-0.047
ls-0.044
Token lost
Token ID2626
Feature activation+1.45e+00

Pos logit contributions
 down+0.118
ged+0.113
iked+0.110
 onward+0.106
am+0.102
Neg logit contributions
 virtue-0.108
rig-0.106
vous-0.106
 importance-0.102
Yes-0.099
Token and
Token ID290
Feature activation-4.49e+00

Pos logit contributions
 down+0.038
ged+0.036
iked+0.034
 onward+0.032
,+0.031
Neg logit contributions
vous-0.052
 virtue-0.051
rig-0.051
Yes-0.049
leaf-0.049
Token started
Token ID2067
Feature activation+4.50e+00

Pos logit contributions
 virtue+0.152
rig+0.149
vous+0.148
 importance+0.143
leaf+0.142
Neg logit contributions
 down-0.125
ged-0.121
iked-0.116
 onward-0.110
am-0.107
Token to
Token ID284
Feature activation-2.47e+00

Pos logit contributions
ged+0.131
iked+0.128
 down+0.125
 onward+0.122
leys+0.120
Neg logit contributions
vous-0.133
 virtue-0.132
 importance-0.130
rig-0.130
Yes-0.129
Token cry
Token ID3960
Feature activation-5.59e-01

Pos logit contributions
 virtue+0.053
vous+0.053
rig+0.051
Yes+0.050
 importance+0.050
Neg logit contributions
ged-0.094
 down-0.093
iked-0.093
 onward-0.088
leys-0.086
TokenJ
Token ID41
Feature activation-1.02e+00

Pos logit contributions
vous+0.029
 virtue+0.028
rig+0.028
 importance+0.027
 matter+0.026
Neg logit contributions
ged-0.022
 down-0.021
iked-0.021
 onward-0.021
leys-0.020
Tokenenny
Token ID11870
Feature activation-3.03e+00

Pos logit contributions
 virtue+0.036
vous+0.035
Yes+0.035
 importance+0.034
 matter+0.034
Neg logit contributions
ged-0.026
iked-0.025
 down-0.025
leys-0.024
am-0.023
Token thought
Token ID1807
Feature activation-1.26e+00

Pos logit contributions
vous+0.111
 virtue+0.111
rig+0.105
Yes+0.104
 matter+0.103
Neg logit contributions
,-0.076
 down-0.073
ged-0.072
am-0.072
iked-0.066
Token for
Token ID329
Feature activation-3.60e+00

Pos logit contributions
vous+0.047
 virtue+0.046
Yes+0.045
rig+0.045
 importance+0.043
Neg logit contributions
 down-0.030
ged-0.030
iked-0.028
 onward-0.027
,-0.026
Token a
Token ID257
Feature activation-3.96e+00

Pos logit contributions
rig+0.162
 virtue+0.153
vous+0.148
acco+0.145
arant+0.142
Neg logit contributions
,-0.071
 his-0.069
 down-0.060
 he-0.052
 out-0.050
Token moment
Token ID2589
Feature activation+1.38e+00

Pos logit contributions
vous+0.141
rig+0.135
 virtue+0.135
leaf+0.133
 least+0.131
Neg logit contributions
 down-0.093
ged-0.093
,-0.088
 onward-0.083
 inspection-0.081
Token and
Token ID290
Feature activation-3.94e+00

Pos logit contributions
 down+0.030
ged+0.029
,+0.029
iked+0.027
 onward+0.027
Neg logit contributions
vous-0.055
 virtue-0.055
rig-0.055
leaf-0.052
 importance-0.051
Token said
Token ID531
Feature activation+3.61e+00

Pos logit contributions
 virtue+0.110
vous+0.110
rig+0.108
 importance+0.103
Yes+0.100
Neg logit contributions
ged-0.130
 down-0.129
iked-0.125
 onward-0.118
am-0.115
Token,
Token ID11
Feature activation+9.66e+00

Pos logit contributions
leys+0.065
ged+0.064
iked+0.062
 ashore+0.058
ls+0.058
Neg logit contributions
 virtue-0.142
Yes-0.141
 importance-0.136
 meaning-0.134
 song-0.134
Token "
Token ID366
Feature activation-6.03e-01

Pos logit contributions
ged+0.199
iked+0.196
 down+0.188
ls+0.182
leys+0.178
Neg logit contributions
Yes-0.366
 virtue-0.362
 importance-0.358
vous-0.353
rig-0.352
TokenI
Token ID40
Feature activation-7.65e+00

Pos logit contributions
rig+0.017
 mistake+0.016
 virtue+0.016
vous+0.015
 least+0.015
Neg logit contributions
ged-0.018
 down-0.018
 onward-0.018
His-0.017
iked-0.016
Token Lily
Token ID20037
Feature activation-1.08e+00

Pos logit contributions
 down+0.240
ged+0.218
,+0.208
iked+0.206
 onward+0.204
Neg logit contributions
rig-0.346
vous-0.342
 virtue-0.341
 importance-0.323
leaf-0.322
Token,
Token ID11
Feature activation+9.48e+00

Pos logit contributions
vous+0.047
 virtue+0.045
 importance+0.045
Yes+0.044
 child+0.043
Neg logit contributions
iked-0.020
ged-0.019
 onward-0.017
leys-0.016
 down-0.015
Token I
Token ID314
Feature activation-5.06e+00

Pos logit contributions
 down+0.289
,+0.259
ged+0.258
 his+0.243
iked+0.241
Neg logit contributions
rig-0.317
vous-0.307
 virtue-0.307
 importance-0.284
leaf-0.272
Token found
Token ID1043
Feature activation+5.36e+00

Pos logit contributions
rig+0.180
 virtue+0.176
leaf+0.172
resa+0.172
 song+0.163
Neg logit contributions
ged-0.128
 down-0.124
,-0.123
am-0.115
ed-0.104
Token your
Token ID534
Feature activation+4.50e+00

Pos logit contributions
ged+0.163
 down+0.162
iked+0.160
 onward+0.151
leys+0.146
Neg logit contributions
 virtue-0.156
vous-0.156
rig-0.153
Yes-0.150
 importance-0.149
Token car
Token ID1097
Feature activation+1.98e+00

Pos logit contributions
 down+0.107
ged+0.096
,+0.089
iked+0.087
ls+0.085
Neg logit contributions
vous-0.175
rig-0.172
 virtue-0.169
Yes-0.166
leaf-0.166
Token!"
Token ID2474
Feature activation-3.96e+00

Pos logit contributions
 down+0.066
ged+0.064
iked+0.061
 onward+0.059
am+0.058
Neg logit contributions
 virtue-0.054
vous-0.054
rig-0.054
 importance-0.052
Yes-0.052
Token Max
Token ID5436
Feature activation+1.69e+00

Pos logit contributions
Yes+0.109
vous+0.104
rig+0.103
 virtue+0.100
 importance+0.099
Neg logit contributions
iked-0.129
ged-0.126
 down-0.120
 onward-0.120
leys-0.118
Token says
Token ID1139
Feature activation+3.55e+00

Pos logit contributions
 down+0.051
ged+0.050
iked+0.049
 onward+0.046
am+0.045
Neg logit contributions
 virtue-0.051
vous-0.050
rig-0.049
 importance-0.048
Yes-0.048
Token.
Token ID13
Feature activation+4.67e-01

Pos logit contributions
leys+0.128
iked+0.126
 valleys+0.118
 onward+0.117
ged+0.117
Neg logit contributions
Yes-0.077
 song-0.072
 bit-0.071
rig-0.069
 ever-0.069
Token He
Token ID679
Feature activation+5.60e+00

Pos logit contributions
iked+0.012
ged+0.011
leys+0.011
 onward+0.010
am+0.010
Neg logit contributions
Yes-0.017
vous-0.016
 importance-0.016
 virtue-0.016
rig-0.016
Token?"
Token ID1701
Feature activation-4.04e+00

Pos logit contributions
 virtue+0.056
vous+0.055
rig+0.054
 importance+0.053
Yes+0.053
Neg logit contributions
 down-0.055
ged-0.053
iked-0.051
 onward-0.049
am-0.047
Token
Token ID198
Feature activation-8.80e-01

Pos logit contributions
 virtue+0.134
vous+0.134
rig+0.132
Yes+0.129
 importance+0.129
Neg logit contributions
ged-0.106
 down-0.105
iked-0.104
 onward-0.097
leys-0.093
Token
Token ID198
Feature activation-8.73e-01

Pos logit contributions
Yes+0.025
rig+0.025
 virtue+0.025
vous+0.025
 importance+0.024
Neg logit contributions
ged-0.027
 down-0.027
iked-0.026
 onward-0.024
leys-0.024
TokenN
Token ID45
Feature activation+1.15e+00

Pos logit contributions
vous+0.020
Yes+0.020
 virtue+0.020
rig+0.020
 importance+0.019
Neg logit contributions
ged-0.032
 down-0.032
iked-0.031
ls-0.029
 onward-0.029
Tokenana
Token ID2271
Feature activation-1.87e+00

Pos logit contributions
ged+0.042
 down+0.041
iked+0.041
 onward+0.039
ls+0.038
Neg logit contributions
 virtue-0.027
vous-0.027
rig-0.027
 importance-0.026
Yes-0.025
Token smiled
Token ID13541
Feature activation+3.40e+00

Pos logit contributions
 virtue+0.064
vous+0.063
rig+0.061
 importance+0.059
Yes+0.059
Neg logit contributions
 down-0.050
ged-0.050
iked-0.048
am-0.045
,-0.044
Token and
Token ID290
Feature activation-3.88e+00

Pos logit contributions
iked+0.162
ged+0.158
drivers+0.157
igs+0.155
leys+0.155
Neg logit contributions
Yes-0.041
 elderly-0.039
 child-0.039
rig-0.036
 rather-0.034
Token pointed
Token ID6235
Feature activation+8.81e+00

Pos logit contributions
Yes+0.085
rig+0.081
vous+0.081
 virtue+0.080
 importance+0.078
Neg logit contributions
iked-0.143
ged-0.142
 down-0.138
 onward-0.137
leys-0.133
Token to
Token ID284
Feature activation-1.82e+00

Pos logit contributions
iked+0.268
ged+0.263
leys+0.253
ooming+0.239
 onward+0.237
Neg logit contributions
Yes-0.255
leaf-0.240
 child-0.232
 meaning-0.229
rig-0.229
Token an
Token ID281
Feature activation-3.79e+00

Pos logit contributions
 virtue+0.070
vous+0.069
rig+0.068
 importance+0.065
Yes+0.064
Neg logit contributions
 down-0.041
ged-0.040
iked-0.039
 onward-0.036
,-0.033
Token old
Token ID1468
Feature activation-2.67e-01

Pos logit contributions
 virtue+0.120
Yes+0.116
rig+0.115
vous+0.114
 importance+0.112
Neg logit contributions
 down-0.112
ged-0.104
iked-0.099
,-0.097
 onward-0.096
Token We
Token ID775
Feature activation-5.98e+00

Pos logit contributions
 down+0.008
iked+0.007
 onward+0.007
ged+0.007
,+0.007
Neg logit contributions
 virtue-0.010
vous-0.010
rig-0.010
 importance-0.010
 matter-0.010
Token have
Token ID423
Feature activation-3.37e+00

Pos logit contributions
rig+0.195
vous+0.187
 virtue+0.186
resa+0.185
Yes+0.176
Neg logit contributions
 down-0.171
,-0.161
ged-0.160
am-0.148
 onward-0.148
Token to
Token ID284
Feature activation-2.15e+00

Pos logit contributions
rig+0.143
vous+0.133
 virtue+0.132
Yes+0.125
resa+0.125
Neg logit contributions
 down-0.069
,-0.064
am-0.062
 his-0.061
iked-0.059
Token pray
Token ID12472
Feature activation+2.15e+00

Pos logit contributions
vous+0.076
rig+0.074
 virtue+0.073
leaf+0.072
 importance+0.070
Neg logit contributions
 down-0.053
,-0.053
 his-0.047
am-0.046
 ashore-0.045
Token for
Token ID329
Feature activation-3.79e+00

Pos logit contributions
 down+0.052
,+0.047
ged+0.043
 onward+0.042
iked+0.041
Neg logit contributions
vous-0.087
 virtue-0.080
rig-0.080
 importance-0.079
leaf-0.078
Token them
Token ID606
Feature activation+4.15e+00

Pos logit contributions
rig+0.145
vous+0.141
 virtue+0.136
 importance+0.129
Yes+0.127
Neg logit contributions
 down-0.094
,-0.088
ged-0.086
 his-0.085
 them-0.081
Token and
Token ID290
Feature activation-4.23e+00

Pos logit contributions
 down+0.093
ged+0.082
iked+0.081
,+0.080
 onward+0.079
Neg logit contributions
vous-0.165
 virtue-0.160
rig-0.159
Yes-0.156
leaf-0.154
Token the
Token ID262
Feature activation+4.39e-01

Pos logit contributions
vous+0.142
rig+0.135
 virtue+0.131
 importance+0.122
leaf+0.120
Neg logit contributions
 down-0.130
,-0.116
 his-0.113
iked-0.106
ged-0.106
Token people
Token ID661
Feature activation-6.15e+00

Pos logit contributions
 down+0.011
iked+0.009
,+0.009
 onward+0.009
ged+0.009
Neg logit contributions
rig-0.016
vous-0.015
 virtue-0.015
Yes-0.015
leaf-0.015
Token in
Token ID287
Feature activation+8.21e-01

Pos logit contributions
 virtue+0.205
vous+0.203
rig+0.201
 importance+0.196
Yes+0.193
Neg logit contributions
 down-0.174
ged-0.164
iked-0.154
 onward-0.153
,-0.149
Token the
Token ID262
Feature activation+4.20e-01

Pos logit contributions
,+0.020
 down+0.019
 his+0.019
 their+0.018
 onward+0.017
Neg logit contributions
rig-0.033
vous-0.031
leaf-0.031
 virtue-0.031
resa-0.030
Token it
Token ID340
Feature activation+1.30e+00

Pos logit contributions
 down+0.011
ged+0.011
iked+0.010
 onward+0.009
ls+0.009
Neg logit contributions
vous-0.016
rig-0.016
 virtue-0.016
 importance-0.016
Yes-0.016
Token off
Token ID572
Feature activation+5.27e+00

Pos logit contributions
 down+0.033
ged+0.032
iked+0.031
 onward+0.029
ls+0.028
Neg logit contributions
vous-0.045
 virtue-0.045
rig-0.045
Yes-0.044
 importance-0.043
Token,
Token ID11
Feature activation+8.89e+00

Pos logit contributions
 down+0.127
ged+0.115
iked+0.108
 onward+0.107
,+0.105
Neg logit contributions
vous-0.202
rig-0.197
 virtue-0.197
Yes-0.192
 importance-0.190
Token but
Token ID475
Feature activation-5.55e+00

Pos logit contributions
 down+0.251
ged+0.224
 onward+0.209
,+0.208
iked+0.203
Neg logit contributions
vous-0.323
 virtue-0.316
rig-0.306
leaf-0.299
 importance-0.295
Token it
Token ID340
Feature activation+2.44e+00

Pos logit contributions
vous+0.225
rig+0.224
 virtue+0.218
leaf+0.213
 importance+0.212
Neg logit contributions
 down-0.125
ged-0.116
 onward-0.109
iked-0.107
,-0.103
Token just
Token ID655
Feature activation-4.38e+00

Pos logit contributions
 down+0.066
am+0.063
ls+0.063
,+0.062
ged+0.059
Neg logit contributions
leaf-0.086
Yes-0.082
rig-0.081
vous-0.081
 virtue-0.080
Token got
Token ID1392
Feature activation+4.06e+00

Pos logit contributions
vous+0.134
rig+0.133
 virtue+0.131
Yes+0.127
leaf+0.124
Neg logit contributions
 down-0.137
ged-0.131
iked-0.121
 onward-0.119
,-0.118
Token worse
Token ID4785
Feature activation+1.35e-01

Pos logit contributions
iked+0.145
ged+0.143
 onward+0.134
 down+0.133
leys+0.131
Neg logit contributions
 virtue-0.095
vous-0.093
Yes-0.091
rig-0.090
 importance-0.090
Token and
Token ID290
Feature activation-4.14e+00

Pos logit contributions
ged+0.003
iked+0.003
 down+0.003
 onward+0.003
leys+0.003
Neg logit contributions
 virtue-0.005
vous-0.005
rig-0.005
 importance-0.005
Yes-0.005
Token worse
Token ID4785
Feature activation+1.78e-01

Pos logit contributions
vous+0.129
rig+0.129
 virtue+0.128
Yes+0.123
leaf+0.122
Neg logit contributions
 down-0.122
ged-0.118
iked-0.113
 onward-0.109
ls-0.108
Token.
Token ID13
Feature activation+2.48e-01

Pos logit contributions
iked+0.004
ged+0.004
 down+0.004
 onward+0.004
leys+0.004
Neg logit contributions
 virtue-0.006
vous-0.006
 importance-0.006
rig-0.006
Yes-0.006
Token fire
Token ID2046
Feature activation+4.74e+00

Pos logit contributions
 down+0.090
ged+0.085
iked+0.083
 onward+0.076
am+0.074
Neg logit contributions
 virtue-0.179
vous-0.178
rig-0.176
Yes-0.171
 importance-0.170
Token engine
Token ID3113
Feature activation-4.13e-01

Pos logit contributions
 down+0.113
ged+0.105
iked+0.101
am+0.095
ls+0.093
Neg logit contributions
 virtue-0.176
vous-0.175
rig-0.174
 importance-0.169
leaf-0.167
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
rig+0.016
vous+0.016
 virtue+0.016
leaf+0.016
 importance+0.016
Neg logit contributions
 down-0.009
ged-0.008
,-0.008
iked-0.007
am-0.007
Token It
Token ID632
Feature activation-5.98e-01

Pos logit contributions
 down+0.015
ged+0.015
iked+0.014
 onward+0.014
am+0.013
Neg logit contributions
vous-0.018
 virtue-0.018
rig-0.018
 importance-0.018
 matter-0.017
Token's
Token ID338
Feature activation+1.30e+00

Pos logit contributions
 virtue+0.020
rig+0.020
vous+0.020
leaf+0.019
Yes+0.019
Neg logit contributions
 down-0.017
ls-0.015
am-0.015
ged-0.015
,-0.014
Token red
Token ID2266
Feature activation+5.12e-01

Pos logit contributions
 down+0.042
 his+0.036
,+0.035
ged+0.033
 out+0.033
Neg logit contributions
vous-0.042
rig-0.041
 virtue-0.040
leaf-0.040
Yes-0.040
Token and
Token ID290
Feature activation-4.05e+00

Pos logit contributions
ged+0.013
 down+0.013
iked+0.013
 onward+0.012
leys+0.011
Neg logit contributions
 virtue-0.017
vous-0.017
rig-0.017
Yes-0.017
 importance-0.017
Token shiny
Token ID22441
Feature activation+2.29e+00

Pos logit contributions
 virtue+0.141
vous+0.141
rig+0.139
Yes+0.136
 importance+0.136
Neg logit contributions
ged-0.100
 down-0.099
iked-0.097
 onward-0.091
leys-0.087
Token and
Token ID290
Feature activation-4.05e+00

Pos logit contributions
ged+0.057
 down+0.056
iked+0.056
 onward+0.052
leys+0.050
Neg logit contributions
 virtue-0.079
vous-0.079
rig-0.077
Yes-0.076
 importance-0.076
Token has
Token ID468
Feature activation-1.46e+00

Pos logit contributions
 virtue+0.138
vous+0.137
rig+0.136
 importance+0.131
Yes+0.128
Neg logit contributions
 down-0.109
ged-0.102
 onward-0.095
iked-0.095
ls-0.093
Token a
Token ID257
Feature activation-3.88e+00

Pos logit contributions
rig+0.050
vous+0.047
 virtue+0.047
Yes+0.045
 importance+0.044
Neg logit contributions
 down-0.041
ged-0.038
iked-0.037
am-0.035
 onward-0.035
Token They
Token ID1119
Feature activation+1.49e+00

Pos logit contributions
ged+0.003
iked+0.002
 down+0.002
 onward+0.002
leys+0.002
Neg logit contributions
 virtue-0.004
vous-0.004
rig-0.003
Yes-0.003
 importance-0.003
Token make
Token ID787
Feature activation-3.16e+00

Pos logit contributions
 down+0.042
ged+0.037
,+0.035
 onward+0.033
ls+0.033
Neg logit contributions
 virtue-0.055
vous-0.055
rig-0.053
resa-0.052
 importance-0.051
Token a
Token ID257
Feature activation-4.42e+00

Pos logit contributions
 virtue+0.109
vous+0.108
rig+0.104
Yes+0.102
leaf+0.101
Neg logit contributions
 down-0.087
ged-0.082
iked-0.077
am-0.075
 onward-0.073
Token loud
Token ID7812
Feature activation-4.14e+00

Pos logit contributions
vous+0.148
leaf+0.141
 virtue+0.140
rig+0.138
 importance+0.135
Neg logit contributions
 down-0.122
ged-0.110
ls-0.107
iked-0.102
,-0.102
Token noise
Token ID7838
Feature activation-2.38e+00

Pos logit contributions
 virtue+0.089
vous+0.088
rig+0.085
Yes+0.083
 importance+0.082
Neg logit contributions
ged-0.158
 down-0.158
iked-0.154
 onward-0.147
ls-0.144
Token.
Token ID13
Feature activation+4.77e-02

Pos logit contributions
vous+0.084
 virtue+0.083
rig+0.082
Yes+0.081
 importance+0.080
Neg logit contributions
ged-0.057
iked-0.057
 down-0.056
 onward-0.052
leys-0.050
Token They
Token ID1119
Feature activation+1.44e+00

Pos logit contributions
ged+0.001
iked+0.001
 down+0.001
 onward+0.001
leys+0.001
Neg logit contributions
 virtue-0.002
Yes-0.002
vous-0.002
rig-0.002
 importance-0.002
Token hit
Token ID2277
Feature activation+1.76e+00

Pos logit contributions
 down+0.039
ged+0.034
,+0.033
ls+0.031
 onward+0.030
Neg logit contributions
 virtue-0.054
vous-0.054
rig-0.052
 importance-0.050
resa-0.049
Token the
Token ID262
Feature activation+3.38e-01

Pos logit contributions
 down+0.042
ged+0.039
 onward+0.033
,+0.032
 his+0.032
Neg logit contributions
vous-0.071
 virtue-0.071
rig-0.070
 importance-0.067
leaf-0.067
Token floor
Token ID4314
Feature activation-2.12e+00

Pos logit contributions
 down+0.008
,+0.007
 castles+0.007
ged+0.006
 towers+0.006
Neg logit contributions
rig-0.013
 virtue-0.013
Yes-0.013
leaf-0.013
vous-0.013
Token and
Token ID290
Feature activation-4.39e+00

Pos logit contributions
 virtue+0.063
vous+0.062
rig+0.062
Yes+0.061
 importance+0.061
Neg logit contributions
ged-0.061
iked-0.061
 down-0.059
 onward-0.057
leys-0.056
Token,
Token ID11
Feature activation+9.54e+00

Pos logit contributions
Yes+0.070
rig+0.069
 least+0.069
 years+0.068
vous+0.067
Neg logit contributions
ged-0.083
iked-0.080
leys-0.075
 onward-0.072
am-0.070
Token the
Token ID262
Feature activation+4.12e-01

Pos logit contributions
 down+0.253
 his+0.232
,+0.218
 he+0.212
 castles+0.208
Neg logit contributions
 virtue-0.418
vous-0.374
rig-0.346
 importance-0.337
leaf-0.330
Token birds
Token ID10087
Feature activation-6.07e+00

Pos logit contributions
 down+0.010
 castles+0.009
 sand+0.008
ls+0.008
ged+0.008
Neg logit contributions
 virtue-0.017
vous-0.017
rig-0.016
leaf-0.015
illa-0.015
Token and
Token ID290
Feature activation-3.96e+00

Pos logit contributions
Yes+0.189
 song+0.186
rig+0.183
 least+0.182
vous+0.182
Neg logit contributions
iked-0.152
leys-0.143
ged-0.140
 onward-0.137
am-0.131
Token the
Token ID262
Feature activation+3.89e-01

Pos logit contributions
 virtue+0.153
vous+0.147
rig+0.147
 importance+0.139
Yes+0.134
Neg logit contributions
 down-0.100
ged-0.092
iked-0.086
 onward-0.082
ls-0.080
Token squirrel
Token ID33039
Feature activation-3.42e+00

Pos logit contributions
 down+0.010
ged+0.008
 castles+0.008
ls+0.008
,+0.007
Neg logit contributions
 virtue-0.015
vous-0.015
rig-0.015
leaf-0.014
 matter-0.013
Tokens
Token ID82
Feature activation+3.89e+00

Pos logit contributions
rig+0.129
Yes+0.128
vous+0.127
 years+0.123
 song+0.122
Neg logit contributions
ged-0.064
iked-0.064
 onward-0.060
 down-0.057
leys-0.054
Token.
Token ID13
Feature activation+4.02e-01

Pos logit contributions
ged+0.093
iked+0.092
 down+0.089
 onward+0.087
leys+0.084
Neg logit contributions
 importance-0.127
vous-0.127
 virtue-0.126
Yes-0.126
rig-0.125
Token He
Token ID679
Feature activation+5.79e+00

Pos logit contributions
ged+0.013
iked+0.012
 down+0.011
leys+0.011
ls+0.011
Neg logit contributions
Yes-0.012
rig-0.011
 importance-0.011
 virtue-0.011
vous-0.010
Token ran
Token ID4966
Feature activation+6.36e+00

Pos logit contributions
 down+0.174
ged+0.171
am+0.168
,+0.164
iked+0.163
Neg logit contributions
 virtue-0.183
vous-0.176
rig-0.170
leaf-0.161
Yes-0.160
Token ahead
Token ID4058
Feature activation+6.63e-01

Pos logit contributions
ged+0.179
iked+0.177
leys+0.171
 onward+0.164
am+0.164
Neg logit contributions
Yes-0.194
rig-0.188
vous-0.186
 virtue-0.185
leaf-0.181
Token a
Token ID257
Feature activation-4.40e+00

Pos logit contributions
rig+0.090
 virtue+0.087
vous+0.084
Yes+0.082
leaf+0.080
Neg logit contributions
 down-0.063
ged-0.060
iked-0.059
 onward-0.055
,-0.054
Token y
Token ID331
Feature activation-3.30e+00

Pos logit contributions
vous+0.143
rig+0.139
 virtue+0.139
leaf+0.136
Yes+0.134
Neg logit contributions
 down-0.119
ged-0.112
iked-0.108
,-0.107
 onward-0.105
Tokenummy
Token ID13513
Feature activation-1.73e+00

Pos logit contributions
 virtue+0.094
vous+0.093
rig+0.091
Yes+0.087
 matter+0.085
Neg logit contributions
ged-0.107
 down-0.101
iked-0.098
 onward-0.097
leys-0.097
Token sandwich
Token ID20433
Feature activation+2.53e+00

Pos logit contributions
 virtue+0.058
rig+0.056
vous+0.055
 importance+0.054
Yes+0.054
Neg logit contributions
 down-0.047
ged-0.046
iked-0.044
,-0.042
ls-0.041
Token available
Token ID1695
Feature activation+6.64e+00

Pos logit contributions
 down+0.059
ged+0.058
iked+0.056
 onward+0.052
,+0.050
Neg logit contributions
rig-0.094
 virtue-0.094
vous-0.093
 importance-0.090
Yes-0.090
Token for
Token ID329
Feature activation-3.82e+00

Pos logit contributions
 down+0.144
iked+0.135
ged+0.135
 onward+0.121
,+0.120
Neg logit contributions
vous-0.262
rig-0.260
 virtue-0.259
 importance-0.252
Yes-0.252
Token her
Token ID607
Feature activation+4.53e+00

Pos logit contributions
rig+0.162
 virtue+0.162
vous+0.161
 importance+0.154
Yes+0.154
Neg logit contributions
ged-0.070
 down-0.069
iked-0.068
 onward-0.061
ls-0.056
Token.
Token ID13
Feature activation-9.28e-02

Pos logit contributions
,+0.099
 down+0.086
iked+0.074
am+0.071
 back+0.069
Neg logit contributions
leaf-0.194
 virtue-0.189
rig-0.188
vous-0.186
Sad-0.177
Token Lily
Token ID20037
Feature activation-1.41e+00

Pos logit contributions
 virtue+0.003
vous+0.003
Yes+0.003
rig+0.003
 importance+0.003
Neg logit contributions
ged-0.003
iked-0.003
 down-0.002
 onward-0.002
leys-0.002
Token was
Token ID373
Feature activation-3.24e+00

Pos logit contributions
 virtue+0.049
rig+0.048
leaf+0.047
vous+0.047
Yes+0.046
Neg logit contributions
 down-0.037
ged-0.036
,-0.036
am-0.035
iked-0.034
Token very
Token ID845
Feature activation-5.29e+00

Pos logit contributions
 virtue+0.102
rig+0.102
leaf+0.096
 importance+0.094
vous+0.093
Neg logit contributions
 down-0.107
,-0.092
 onward-0.091
ged-0.089
 his-0.088
Token.
Token ID13
Feature activation+5.66e-01

Pos logit contributions
ged+0.003
 down+0.003
iked+0.003
 onward+0.003
leys+0.003
Neg logit contributions
 virtue-0.005
vous-0.005
rig-0.005
Yes-0.005
 importance-0.005
Token Even
Token ID3412
Feature activation-1.82e+00

Pos logit contributions
 down+0.011
iked+0.010
 onward+0.010
ged+0.010
am+0.008
Neg logit contributions
vous-0.024
 virtue-0.023
 matter-0.023
rig-0.023
 importance-0.023
Token though
Token ID996
Feature activation-1.89e+00

Pos logit contributions
 virtue+0.066
vous+0.063
rig+0.062
leaf+0.061
 importance+0.060
Neg logit contributions
 down-0.053
ged-0.046
,-0.045
 onward-0.043
 his-0.042
Token she
Token ID673
Feature activation+5.48e+00

Pos logit contributions
vous+0.085
rig+0.084
 virtue+0.082
leaf+0.081
Yes+0.078
Neg logit contributions
 down-0.033
,-0.030
ged-0.030
 onward-0.029
iked-0.029
Token was
Token ID373
Feature activation-2.83e+00

Pos logit contributions
ged+0.116
,+0.115
am+0.103
 down+0.098
ed+0.095
Neg logit contributions
 virtue-0.219
rig-0.211
leaf-0.210
Yes-0.207
 Tooth-0.206
Token only
Token ID691
Feature activation-6.78e+00

Pos logit contributions
 virtue+0.083
rig+0.082
vous+0.081
Yes+0.079
leaf+0.078
Neg logit contributions
 down-0.092
ged-0.084
 onward-0.083
iked-0.080
,-0.079
Token small
Token ID1402
Feature activation+1.78e+00

Pos logit contributions
 virtue+0.199
rig+0.195
Yes+0.190
vous+0.190
leaf+0.180
Neg logit contributions
 down-0.225
ged-0.211
iked-0.199
 onward-0.197
,-0.191
Token,
Token ID11
Feature activation+9.71e+00

Pos logit contributions
 down+0.022
ged+0.020
iked+0.018
,+0.017
 onward+0.016
Neg logit contributions
vous-0.087
 virtue-0.086
rig-0.086
Yes-0.084
leaf-0.084
Token she
Token ID673
Feature activation+5.45e+00

Pos logit contributions
 down+0.115
,+0.097
 he+0.086
 onward+0.085
 his+0.077
Neg logit contributions
rig-0.525
vous-0.518
 virtue-0.502
leaf-0.497
resa-0.462
Token had
Token ID550
Feature activation-2.02e+00

Pos logit contributions
,+0.127
ged+0.123
 down+0.120
am+0.119
 he+0.109
Neg logit contributions
leaf-0.202
rig-0.202
 virtue-0.199
vous-0.197
 Tooth-0.196
Token done
Token ID1760
Feature activation+3.82e+00

Pos logit contributions
rig+0.066
vous+0.062
 virtue+0.061
leaf+0.060
Yes+0.059
Neg logit contributions
 down-0.059
ged-0.055
iked-0.055
 onward-0.054
,-0.054
Token moment
Token ID2589
Feature activation+1.26e+00

Pos logit contributions
vous+0.136
 virtue+0.134
rig+0.132
leaf+0.132
 years+0.131
Neg logit contributions
 down-0.102
ged-0.101
,-0.093
iked-0.089
 inspection-0.089
Token and
Token ID290
Feature activation-4.11e+00

Pos logit contributions
,+0.029
 down+0.026
ged+0.025
 onward+0.022
iked+0.022
Neg logit contributions
vous-0.053
 virtue-0.053
rig-0.052
leaf-0.052
 importance-0.049
Token said
Token ID531
Feature activation+3.46e+00

Pos logit contributions
 virtue+0.114
vous+0.112
rig+0.110
 importance+0.107
Yes+0.104
Neg logit contributions
ged-0.136
 down-0.135
iked-0.131
 onward-0.123
ls-0.122
Token,
Token ID11
Feature activation+9.52e+00

Pos logit contributions
leys+0.090
 valleys+0.085
rolling+0.084
 ashore+0.084
packs+0.083
Neg logit contributions
Yes-0.108
 bit-0.106
 ever-0.105
 never-0.101
 virtue-0.101
Token "
Token ID366
Feature activation-6.54e-01

Pos logit contributions
ged+0.215
iked+0.215
ls+0.202
 onward+0.200
 down+0.199
Neg logit contributions
Yes-0.339
 importance-0.328
 virtue-0.326
vous-0.320
rig-0.319
TokenWe
Token ID1135
Feature activation-7.51e+00

Pos logit contributions
rig+0.022
 virtue+0.022
 promise+0.022
 least+0.021
 mistake+0.021
Neg logit contributions
His-0.016
ged-0.015
 he-0.015
He-0.014
 down-0.014
Token need
Token ID761
Feature activation-5.91e+00

Pos logit contributions
rig+0.281
vous+0.244
resa+0.242
leaf+0.240
Yes+0.235
Neg logit contributions
,-0.207
 down-0.205
ged-0.183
am-0.176
 out-0.176
Token an
Token ID281
Feature activation-3.83e+00

Pos logit contributions
rig+0.254
vous+0.245
 virtue+0.232
 importance+0.224
Yes+0.224
Neg logit contributions
 down-0.119
,-0.113
ged-0.110
iked-0.109
 his-0.103
Token intelligent
Token ID12661
Feature activation-5.63e+00

Pos logit contributions
Yes+0.122
 virtue+0.118
rig+0.116
leaf+0.114
vous+0.107
Neg logit contributions
am-0.104
,-0.102
 down-0.100
iked-0.096
 his-0.096
Token plan
Token ID1410
Feature activation-6.02e-01

Pos logit contributions
rig+0.206
leaf+0.185
Sad+0.179
 virtue+0.179
 least+0.173
Neg logit contributions
,-0.168
 down-0.142
 his-0.129
ged-0.126
 sand-0.125
Token to
Token ID284
Feature activation-1.97e+00

Pos logit contributions
rig+0.024
vous+0.023
 virtue+0.023
 importance+0.022
Yes+0.022
Neg logit contributions
 down-0.013
ged-0.013
iked-0.012
,-0.012
 onward-0.011
Token take
Token ID1011
Feature activation+7.18e-01

Pos logit contributions
vous+0.143
rig+0.142
 virtue+0.141
 importance+0.136
leaf+0.133
Neg logit contributions
 down-0.124
,-0.116
ged-0.115
iked-0.114
 onward-0.109
Token it
Token ID340
Feature activation+3.08e+00

Pos logit contributions
ged+0.019
 down+0.018
iked+0.018
 onward+0.017
leys+0.016
Neg logit contributions
 virtue-0.024
vous-0.024
rig-0.024
Yes-0.023
 importance-0.023
Token home
Token ID1363
Feature activation+4.00e+00

Pos logit contributions
ged+0.065
iked+0.063
 down+0.059
 onward+0.056
leys+0.054
Neg logit contributions
 virtue-0.120
vous-0.119
rig-0.118
Yes-0.116
 importance-0.115
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
 down+0.075
ged+0.066
,+0.064
iked+0.062
 onward+0.059
Neg logit contributions
vous-0.175
 virtue-0.171
rig-0.169
 importance-0.167
leaf-0.167
Token Her
Token ID2332
Feature activation+3.35e+00

Pos logit contributions
ged+0.003
iked+0.003
leys+0.003
 ashore+0.002
 down+0.002
Neg logit contributions
Yes-0.004
 virtue-0.003
 importance-0.003
rig-0.003
vous-0.003
Token mom
Token ID1995
Feature activation-7.88e+00

Pos logit contributions
 down+0.070
,+0.067
iked+0.058
ged+0.057
ls+0.055
Neg logit contributions
vous-0.145
rig-0.138
leaf-0.137
 virtue-0.133
 importance-0.122
Token said
Token ID531
Feature activation+3.10e+00

Pos logit contributions
 virtue+0.321
vous+0.307
rig+0.298
 importance+0.284
leaf+0.279
Neg logit contributions
,-0.203
ged-0.181
 down-0.177
am-0.164
iked-0.162
Token yes
Token ID3763
Feature activation+4.79e-02

Pos logit contributions
 down+0.101
iked+0.099
ged+0.098
leys+0.095
 ashore+0.095
Neg logit contributions
 virtue-0.081
Yes-0.081
 importance-0.079
vous-0.076
 matter-0.074
Token,
Token ID11
Feature activation+9.25e+00

Pos logit contributions
ged+0.001
 down+0.001
iked+0.000
 onward+0.000
leys+0.000
Neg logit contributions
vous-0.002
 virtue-0.002
rig-0.002
Yes-0.002
 importance-0.002
Token but
Token ID475
Feature activation-5.82e+00

Pos logit contributions
,+0.189
 down+0.156
 he+0.154
 his+0.145
 they+0.123
Neg logit contributions
 virtue-0.444
vous-0.424
rig-0.417
illa-0.386
resa-0.369
Token they
Token ID484
Feature activation+3.54e+00

Pos logit contributions
vous+0.290
rig+0.274
leaf+0.257
 virtue+0.255
 importance+0.239
Neg logit contributions
 down-0.110
,-0.107
 onward-0.082
 he-0.080
ls-0.076
Token time
Token ID640
Feature activation-9.63e-01

Pos logit contributions
leaf+0.133
 virtue+0.132
vous+0.127
Yes+0.127
 importance+0.123
Neg logit contributions
,-0.121
ged-0.118
 down-0.118
iked-0.113
leys-0.111
Token,
Token ID11
Feature activation+9.46e+00

Pos logit contributions
Yes+0.034
 years+0.033
 ever+0.033
vous+0.033
rig+0.032
Neg logit contributions
ged-0.020
iked-0.020
 ashore-0.019
leys-0.019
 down-0.018
Token there
Token ID612
Feature activation+4.36e+00

Pos logit contributions
iked+0.261
ged+0.235
 onward+0.221
leys+0.219
am+0.218
Neg logit contributions
vous-0.319
Yes-0.318
 importance-0.299
 matter-0.299
rig-0.297
Token was
Token ID373
Feature activation-3.16e+00

Pos logit contributions
ged+0.164
iked+0.164
 down+0.161
 onward+0.155
leys+0.152
Neg logit contributions
vous-0.095
 virtue-0.093
Yes-0.091
 importance-0.091
rig-0.089
Token a
Token ID257
Feature activation-4.40e+00

Pos logit contributions
 virtue+0.112
rig+0.106
vous+0.103
 importance+0.101
Yes+0.098
Neg logit contributions
 down-0.085
ged-0.080
,-0.076
iked-0.075
 his-0.075
Token little
Token ID1310
Feature activation-6.96e+00

Pos logit contributions
 virtue+0.132
vous+0.129
rig+0.125
leaf+0.122
 importance+0.122
Neg logit contributions
 down-0.134
ged-0.124
,-0.123
ls-0.118
iked-0.117
Token girl
Token ID2576
Feature activation-7.29e+00

Pos logit contributions
 virtue+0.199
rig+0.196
vous+0.192
 importance+0.189
leaf+0.179
Neg logit contributions
 down-0.231
ged-0.215
,-0.207
ls-0.204
iked-0.201
Token named
Token ID3706
Feature activation-4.45e+00

Pos logit contributions
 virtue+0.238
rig+0.232
 importance+0.231
vous+0.220
leaf+0.216
Neg logit contributions
 down-0.215
ged-0.210
,-0.208
iked-0.191
am-0.182
Token Lily
Token ID20037
Feature activation-1.39e+00

Pos logit contributions
 virtue+0.156
vous+0.153
rig+0.153
 importance+0.149
Yes+0.146
Neg logit contributions
 down-0.113
ged-0.110
iked-0.108
 onward-0.101
leys-0.097
Token.
Token ID13
Feature activation+5.43e-02

Pos logit contributions
 virtue+0.058
rig+0.057
vous+0.057
 importance+0.056
leaf+0.055
Neg logit contributions
 down-0.026
ged-0.026
iked-0.023
,-0.021
am-0.020
Token She
Token ID1375
Feature activation+3.89e+00

Pos logit contributions
ged+0.001
iked+0.001
ls+0.001
 down+0.001
 ashore+0.001
Neg logit contributions
Yes-0.002
vous-0.002
 importance-0.002
 virtue-0.002
rig-0.002
Token time
Token ID640
Feature activation-2.65e-01

Pos logit contributions
leaf+0.125
 virtue+0.122
Yes+0.117
vous+0.115
 importance+0.114
Neg logit contributions
,-0.110
 down-0.108
ged-0.108
 onward-0.101
am-0.101
Token,
Token ID11
Feature activation+9.93e+00

Pos logit contributions
Yes+0.009
 ever+0.009
 years+0.008
vous+0.008
rig+0.008
Neg logit contributions
ged-0.006
iked-0.006
leys-0.006
 ashore-0.006
iece-0.006
Token there
Token ID612
Feature activation+4.88e+00

Pos logit contributions
iked+0.285
ged+0.246
am+0.240
 onward+0.238
leys+0.233
Neg logit contributions
Yes-0.314
vous-0.313
rig-0.303
 virtue-0.297
 importance-0.296
Token was
Token ID373
Feature activation-2.79e+00

Pos logit contributions
ged+0.173
 down+0.171
iked+0.171
 onward+0.162
leys+0.158
Neg logit contributions
vous-0.117
 virtue-0.116
rig-0.113
Yes-0.111
 importance-0.111
Token a
Token ID257
Feature activation-3.96e+00

Pos logit contributions
 virtue+0.099
rig+0.094
 importance+0.090
vous+0.090
 matter+0.086
Neg logit contributions
 down-0.074
ged-0.072
iked-0.066
,-0.066
 his-0.065
Token little
Token ID1310
Feature activation-6.33e+00

Pos logit contributions
 virtue+0.111
vous+0.109
rig+0.106
 importance+0.103
leaf+0.103
Neg logit contributions
 down-0.127
ged-0.121
,-0.116
iked-0.114
ls-0.114
Token bear
Token ID6842
Feature activation-3.50e+00

Pos logit contributions
 virtue+0.167
rig+0.163
vous+0.163
 importance+0.159
leaf+0.150
Neg logit contributions
 down-0.217
ged-0.211
iked-0.201
ls-0.197
 onward-0.193
Token.
Token ID13
Feature activation+3.63e-01

Pos logit contributions
 virtue+0.133
 importance+0.130
rig+0.126
leaf+0.124
 matter+0.120
Neg logit contributions
,-0.094
 down-0.086
ged-0.084
 his-0.076
am-0.076
Token The
Token ID383
Feature activation-2.64e+00

Pos logit contributions
ged+0.009
iked+0.008
leys+0.008
 down+0.008
ls+0.008
Neg logit contributions
vous-0.014
Yes-0.013
 importance-0.013
 virtue-0.013
rig-0.012
Token little
Token ID1310
Feature activation-6.40e+00

Pos logit contributions
 virtue+0.090
rig+0.088
vous+0.088
leaf+0.086
Yes+0.083
Neg logit contributions
 down-0.070
ged-0.066
iked-0.063
 onward-0.062
,-0.060
Token bear
Token ID6842
Feature activation-3.50e+00

Pos logit contributions
vous+0.144
Yes+0.141
 importance+0.137
 child+0.135
 virtue+0.131
Neg logit contributions
iked-0.246
ged-0.239
leys-0.230
 onward-0.229
am-0.217