TOP ACTIVATIONS
MAX = 4.219

# Unlike ly Deb ate Gu ests have been arrested for
UP will continue to support Pu ig dem ont and his
refers to himself as ' Gu cc ifer 2 . 0
Brazil ian President Dil ma Rousse ff and Cuban
option adopted by Pu ig dem ont and his
First , the address by Pu ig dem ont before the
, motor ized wheelchair ( Figure 2 A , [ Action
as the gray area in Figure 2 ). Then introduce v
e , je les cl ares offic iel lement
s largest party abandoned President Dil ma Rousse ff
as d Gu M ih o
V ir Go Agu ilar near one of the
. That leaves income of roughly $ 177 million . Of
blue v ort on in Figure 2 ). Near those heavier
-- or may perhaps be allev iated or designed out of
cell , as shown in Figure 3 . Figure
marketing campaign . Instead of Techn icol or , Hitchcock shot
far cry from gu arant ee ing pre -
° 17 ). Figure 4 - A Monthly increments
pink v ort on in Figure 2 ). Near those lighter

MIN ACTIVATIONS
MIN = -3.763

to pass into the eternal love of God ," reads the
by suicide . Cambridge , MA : Harvard University Press ;
twitter . com / O JV L F Re K ch
high school ball , the love of English he acquired in
to drive with an ignition inter lock device .
civil - rights office has long been criticized for failing to
dramatic experiences of betrayal , love , disappointment , empowerment and
function . (* join each element of ` se
of this is to highlight INTER M ITT ENT F AST
A US 16 Steele Von Hoff ( Team Chip otle )
month . With love and light George
battery . <|endoftext|> J TA Two photos tweeted as being
' The Brotherhood of Eternal Love : From Flower Power to
. <|endoftext|> Dec 2 , 2015 Cycl oc ross hurts
whether the states have a co - op option . Bob
was sent from Russia with Love . L aid on cloth
. C . K .: Christian s
compiled addresses had such a long and st oried history of
form of exercise a MET AB OL IC WORK OUT
takeover of the M avi Mar m ara . Turkey and

INTERVAL 2.223 - 4.219
CONTAINS 0.227%

10 : 47 ] < c erv ant as > lol
av iator Capt Sir George Hu bert Wil kins who ,
market , and Dallas can clear a lot of money really
glers , the crazy ac robat ics and you get
a season - high 28 points against Boston College on January

INTERVAL 0.228 - 2.223
CONTAINS 35.945%

Mongol ian names to their children , often in the form
. You have to earn the right to put t a
our own , everyday , minimal ways . The
with Dahl 's script and brought in an unknown to rewrite
edition . The Norwegian Police Security Service informed that country

INTERVAL -1.768 - 0.228
CONTAINS 63.019%

up - you can setup in five to ten minutes ,
would have to be constructed , and the project would be
Furthermore , the only speakers I ve heard that
in loans from I hor Kol omo isky 's Priv at
a very active November Project group in Edmonton that regularly draws

INTERVAL -3.763 - -1.768
CONTAINS 0.809%

9 in college at St . Louis , measured in at
their benefits . But Prime members with Amazon Mom can share
s maybe what makes everyone love games . That
K ernel = c v 2 . get Struct uring Element
d need a 7 letter Scottish team beginning AIR
Token #
Token ID1303
Feature activation-4.99e-01

Pos logit contributions
heid+1.432
hips+1.238
ertodd+1.183
 refrain+1.119
olini+1.019
Neg logit contributions
cember-1.269
isphere-1.246
nir-1.221
andum-1.203
asar-1.194
TokenUnlike
Token ID18521
Feature activation-7.83e-01

Pos logit contributions
heid+1.469
hips+1.276
ertodd+1.227
 refrain+1.156
olini+1.070
Neg logit contributions
cember-1.147
isphere-1.121
nir-1.101
andum-1.091
asar-1.081
Tokenly
Token ID306
Feature activation+1.17e+00

Pos logit contributions
heid+2.294
hips+1.985
ertodd+1.874
 refrain+1.785
olini+1.658
Neg logit contributions
cember-1.808
isphere-1.775
nir-1.746
andum-1.729
asar-1.711
TokenDeb
Token ID16587
Feature activation+3.46e-02

Pos logit contributions
cember+2.734
isphere+2.682
nir+2.643
andum+2.596
asar+2.582
Neg logit contributions
heid-3.334
hips-2.913
ertodd-2.862
 refrain-2.623
olini-2.447
Tokenate
Token ID378
Feature activation+8.24e-01

Pos logit contributions
cember+0.065
isphere+0.063
nir+0.062
andum+0.061
asar+0.061
Neg logit contributions
heid-0.116
hips-0.103
ertodd-0.100
 refrain-0.095
olini-0.089
TokenGu
Token ID8205
Feature activation+4.22e+00

Pos logit contributions
cember+2.055
isphere+2.007
nir+1.980
andum+1.947
asar+1.942
Neg logit contributions
heid-2.235
hips-1.930
ertodd-1.898
 refrain-1.723
olini-1.605
Tokenests
Token ID3558
Feature activation+3.43e-01

Pos logit contributions
isphere+8.030
cember+7.820
nir+7.545
andum+7.493
asar+7.488
Neg logit contributions
heid-12.340
hips-10.925
ertodd-10.861
 refrain-10.289
creen-9.298
Token have
Token ID423
Feature activation+1.17e+00

Pos logit contributions
cember+0.852
isphere+0.834
nir+0.823
andum+0.811
asar+0.807
Neg logit contributions
heid-0.944
hips-0.814
ertodd-0.790
 refrain-0.733
olini-0.676
Token been
Token ID587
Feature activation-3.18e-01

Pos logit contributions
cember+2.929
isphere+2.877
nir+2.847
andum+2.791
asar+2.780
Neg logit contributions
heid-3.161
hips-2.708
ertodd-2.679
 refrain-2.440
olini-2.251
Token arrested
Token ID5169
Feature activation+9.60e-01

Pos logit contributions
heid+1.089
hips+0.972
ertodd+0.942
 refrain+0.898
olini+0.842
Neg logit contributions
cember-0.572
isphere-0.556
nir-0.547
andum-0.534
asar-0.530
Token for
Token ID329
Feature activation+9.58e-01

Pos logit contributions
cember+2.425
isphere+2.362
nir+2.328
asar+2.307
andum+2.296
Neg logit contributions
heid-2.588
hips-2.200
ertodd-2.179
 refrain-1.988
olini-1.834
TokenUP
Token ID8577
Feature activation-1.58e+00

Pos logit contributions
cember+0.936
isphere+0.908
nir+0.893
andum+0.873
asar+0.868
Neg logit contributions
heid-1.742
hips-1.552
ertodd-1.509
 refrain-1.427
olini-1.343
Token will
Token ID481
Feature activation-5.07e-01

Pos logit contributions
heid+3.992
hips+3.441
ertodd+3.277
 refrain+3.217
olini+2.816
Neg logit contributions
cember-4.129
isphere-3.991
nir-3.968
andum-3.905
utics-3.890
Token continue
Token ID2555
Feature activation-4.34e-01

Pos logit contributions
heid+1.098
hips+0.907
ertodd+0.868
 refrain+0.788
olini+0.701
Neg logit contributions
cember-1.558
isphere-1.531
nir-1.516
andum-1.497
asar-1.492
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
heid+1.185
hips+1.021
ertodd+0.989
 refrain+0.919
olini+0.846
Neg logit contributions
cember-1.086
isphere-1.064
nir-1.050
andum-1.034
asar-1.030
Token support
Token ID1104
Feature activation-1.16e+00

Pos logit contributions
heid+3.164
hips+2.655
ertodd+2.498
 refrain+2.380
olini+1.995
Neg logit contributions
cember-4.703
isphere-4.617
nir-4.562
andum-4.521
istical-4.471
Token Pu
Token ID11634
Feature activation+4.08e+00

Pos logit contributions
heid+3.002
hips+2.580
ertodd+2.433
 refrain+2.318
olini+2.088
Neg logit contributions
cember-3.079
isphere-3.023
nir-2.965
asar-2.894
istical-2.893
Tokenig
Token ID328
Feature activation+1.08e+00

Pos logit contributions
asar+4.779
nir+4.690
ause+4.659
andum+4.616
istical+4.612
Neg logit contributions
heid-14.632
hips-13.290
ertodd-13.261
 refrain-12.910
 Sins-11.621
Tokendem
Token ID9536
Feature activation+1.54e+00

Pos logit contributions
cember+2.647
isphere+2.587
nir+2.562
andum+2.530
asar+2.520
Neg logit contributions
heid-2.986
hips-2.588
ertodd-2.509
 refrain-2.343
olini-2.150
Tokenont
Token ID756
Feature activation+3.83e-01

Pos logit contributions
cember+3.893
isphere+3.813
nir+3.797
andum+3.797
asar+3.767
Neg logit contributions
heid-4.047
hips-3.481
ertodd-3.390
 refrain-3.152
olini-2.846
Token and
Token ID290
Feature activation+4.84e-01

Pos logit contributions
cember+0.878
isphere+0.857
nir+0.847
andum+0.834
asar+0.833
Neg logit contributions
heid-1.125
hips-0.977
ertodd-0.953
 refrain-0.887
olini-0.824
Token his
Token ID465
Feature activation-3.02e-01

Pos logit contributions
cember+1.295
isphere+1.272
nir+1.259
asar+1.244
andum+1.242
Neg logit contributions
heid-1.230
hips-1.041
ertodd-1.018
 refrain-0.915
olini-0.851
Token refers
Token ID10229
Feature activation+1.08e+00

Pos logit contributions
cember+2.177
isphere+2.143
nir+2.093
andum+2.082
asar+2.056
Neg logit contributions
heid-2.658
hips-2.258
ertodd-2.220
 refrain-2.036
olini-1.921
Token to
Token ID284
Feature activation+8.63e-05

Pos logit contributions
cember+2.254
isphere+2.199
nir+2.171
andum+2.137
istical+2.113
Neg logit contributions
heid-3.338
hips-2.900
ertodd-2.840
 refrain-2.638
olini-2.518
Token himself
Token ID2241
Feature activation-2.45e-01

Pos logit contributions
cember+0.000
isphere+0.000
nir+0.000
andum+0.000
asar+0.000
Neg logit contributions
heid-0.000
hips-0.000
ertodd-0.000
 refrain-0.000
olini-0.000
Token as
Token ID355
Feature activation-6.76e-02

Pos logit contributions
heid+0.683
hips+0.585
ertodd+0.567
 refrain+0.530
olini+0.491
Neg logit contributions
cember-0.602
isphere-0.588
nir-0.579
andum-0.574
asar-0.573
Token '
Token ID705
Feature activation+1.61e-01

Pos logit contributions
heid+0.172
hips+0.146
ertodd+0.141
 refrain+0.130
olini+0.119
Neg logit contributions
cember-0.182
isphere-0.178
nir-0.176
andum-0.175
asar-0.173
TokenGu
Token ID8205
Feature activation+4.01e+00

Pos logit contributions
cember+0.360
isphere+0.350
nir+0.348
andum+0.341
asar+0.339
Neg logit contributions
heid-0.481
hips-0.420
ertodd-0.410
 refrain-0.385
olini-0.357
Tokencc
Token ID535
Feature activation+2.63e-01

Pos logit contributions
isphere+7.051
asar+7.035
nir+7.021
andum+6.979
cember+6.769
Neg logit contributions
heid-11.987
hips-10.827
ertodd-10.681
 refrain-10.276
creen-9.444
Tokenifer
Token ID7087
Feature activation+1.46e+00

Pos logit contributions
cember+0.460
isphere+0.445
nir+0.437
andum+0.427
asar+0.425
Neg logit contributions
heid-0.918
hips-0.819
ertodd-0.798
 refrain-0.757
olini-0.713
Token 2
Token ID362
Feature activation+2.21e-01

Pos logit contributions
cember+2.959
andum+2.888
nir+2.874
isphere+2.857
istical+2.819
Neg logit contributions
heid-4.562
hips-3.969
ertodd-3.965
 refrain-3.679
olini-3.444
Token.
Token ID13
Feature activation-7.64e-01

Pos logit contributions
cember+0.550
isphere+0.538
nir+0.531
andum+0.523
asar+0.521
Neg logit contributions
heid-0.607
hips-0.523
ertodd-0.507
 refrain-0.471
olini-0.434
Token0
Token ID15
Feature activation-1.20e-02

Pos logit contributions
heid+1.972
hips+1.694
ertodd+1.606
 refrain+1.519
olini+1.360
Neg logit contributions
cember-2.018
isphere-1.997
nir-1.917
asar-1.917
istical-1.912
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
heid+1.067
hips+0.917
ertodd+0.882
 refrain+0.820
olini+0.752
Neg logit contributions
cember-1.045
isphere-1.023
nir-1.011
andum-0.994
asar-0.989
Token
Token ID198
Feature activation+4.14e-01

Pos logit contributions
heid+0.605
hips+0.520
ertodd+0.498
 refrain+0.463
olini+0.423
Neg logit contributions
cember-0.612
isphere-0.599
nir-0.589
andum-0.581
asar-0.576
TokenBrazil
Token ID39190
Feature activation+6.60e-01

Pos logit contributions
cember+0.913
isphere+0.892
nir+0.880
andum+0.865
asar+0.861
Neg logit contributions
heid-1.249
hips-1.093
ertodd-1.064
 refrain-0.997
olini-0.927
Tokenian
Token ID666
Feature activation+1.81e-01

Pos logit contributions
cember+1.561
isphere+1.531
nir+1.508
andum+1.490
asar+1.484
Neg logit contributions
heid-1.884
hips-1.627
ertodd-1.595
 refrain-1.477
olini-1.363
Token President
Token ID1992
Feature activation+4.77e-01

Pos logit contributions
cember+0.497
isphere+0.487
nir+0.482
andum+0.477
asar+0.475
Neg logit contributions
heid-0.450
hips-0.380
ertodd-0.374
 refrain-0.337
olini-0.309
Token Dil
Token ID29328
Feature activation+3.76e+00

Pos logit contributions
cember+1.062
isphere+1.028
nir+1.022
asar+1.009
andum+1.008
Neg logit contributions
heid-1.428
hips-1.240
ertodd-1.226
 refrain-1.129
olini-1.046
Tokenma
Token ID2611
Feature activation-9.06e-01

Pos logit contributions
asar+6.531
nir+6.513
ause+6.429
cember+6.267
reens+5.978
Neg logit contributions
heid-11.854
ertodd-10.892
hips-10.856
 refrain-9.842
creen-9.331
Token Rousse
Token ID42849
Feature activation+2.19e+00

Pos logit contributions
heid+2.152
hips+1.813
ertodd+1.721
 refrain+1.621
olini+1.467
Neg logit contributions
cember-2.583
isphere-2.566
nir-2.476
andum-2.475
istical-2.460
Tokenff
Token ID487
Feature activation+9.30e-01

Pos logit contributions
cember+2.721
ause+2.638
asar+2.605
nir+2.600
utics+2.542
Neg logit contributions
heid-8.525
ertodd-7.813
hips-7.706
 refrain-7.148
creen-6.628
Token and
Token ID290
Feature activation+1.44e-01

Pos logit contributions
cember+2.251
isphere+2.200
nir+2.160
asar+2.144
andum+2.131
Neg logit contributions
heid-2.594
hips-2.220
ertodd-2.208
 refrain-2.010
olini-1.865
Token Cuban
Token ID18147
Feature activation+8.03e-01

Pos logit contributions
cember+0.400
isphere+0.393
nir+0.388
andum+0.383
asar+0.382
Neg logit contributions
heid-0.351
hips-0.297
ertodd-0.288
 refrain-0.263
olini-0.239
Token option
Token ID3038
Feature activation+1.57e+00

Pos logit contributions
cember+0.348
isphere+0.341
nir+0.337
andum+0.332
asar+0.330
Neg logit contributions
heid-0.361
hips-0.310
ertodd-0.300
 refrain-0.278
olini-0.255
Token
Token ID447
Feature activation+2.14e-01

Pos logit contributions
cember+3.390
isphere+3.346
nir+3.270
andum+3.247
asar+3.211
Neg logit contributions
heid-4.694
hips-4.077
ertodd-4.027
 refrain-3.693
olini-3.504
Token
Token ID247
Feature activation+3.04e-01

Pos logit contributions
cember+0.339
isphere+0.324
nir+0.321
asar+0.310
istical+0.310
Neg logit contributions
heid-0.780
hips-0.703
ertodd-0.684
 refrain-0.650
olini-0.613
Token adopted
Token ID8197
Feature activation+1.22e+00

Pos logit contributions
cember+0.760
isphere+0.745
nir+0.735
andum+0.725
asar+0.721
Neg logit contributions
heid-0.832
hips-0.716
ertodd-0.695
 refrain-0.644
olini-0.594
Token by
Token ID416
Feature activation+2.71e-01

Pos logit contributions
cember+2.893
isphere+2.817
nir+2.773
andum+2.738
asar+2.732
Neg logit contributions
heid-3.493
hips-2.984
ertodd-2.946
 refrain-2.704
olini-2.542
Token Pu
Token ID11634
Feature activation+3.74e+00

Pos logit contributions
cember+0.713
isphere+0.698
nir+0.692
andum+0.682
asar+0.679
Neg logit contributions
heid-0.706
hips-0.603
ertodd-0.585
 refrain-0.537
olini-0.493
Tokenig
Token ID328
Feature activation+1.27e+00

Pos logit contributions
asar+4.633
nir+4.618
isphere+4.617
istical+4.558
ause+4.510
Neg logit contributions
heid-13.352
hips-12.118
ertodd-12.042
 refrain-11.701
creen-10.392
Tokendem
Token ID9536
Feature activation+1.79e+00

Pos logit contributions
cember+3.072
isphere+3.002
nir+2.978
andum+2.942
asar+2.929
Neg logit contributions
heid-3.543
hips-3.080
ertodd-2.985
 refrain-2.798
olini-2.562
Tokenont
Token ID756
Feature activation+5.75e-01

Pos logit contributions
cember+4.421
isphere+4.333
andum+4.330
nir+4.329
asar+4.289
Neg logit contributions
heid-4.776
hips-4.122
ertodd-4.020
 refrain-3.757
olini-3.378
Token and
Token ID290
Feature activation-3.66e-02

Pos logit contributions
cember+1.451
isphere+1.419
nir+1.401
andum+1.382
asar+1.378
Neg logit contributions
heid-1.557
hips-1.334
ertodd-1.296
 refrain-1.201
olini-1.106
Token his
Token ID465
Feature activation-5.52e-01

Pos logit contributions
heid+0.096
hips+0.083
ertodd+0.080
 refrain+0.074
olini+0.068
Neg logit contributions
cember-0.096
isphere-0.094
nir-0.092
andum-0.091
asar-0.091
TokenFirst
Token ID5962
Feature activation-6.16e-01

Pos logit contributions
cember+0.510
isphere+0.497
nir+0.488
andum+0.480
asar+0.478
Neg logit contributions
heid-0.726
hips-0.637
ertodd-0.617
 refrain-0.580
olini-0.540
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
heid+1.730
hips+1.499
ertodd+1.450
 refrain+1.356
olini+1.249
Neg logit contributions
cember-1.495
isphere-1.457
nir-1.443
andum-1.414
asar-1.413
Token the
Token ID262
Feature activation-2.26e-01

Pos logit contributions
heid+2.709
hips+2.323
ertodd+2.194
 refrain+2.105
olini+1.877
Neg logit contributions
cember-2.870
isphere-2.790
nir-2.755
asar-2.694
andum-2.689
Token address
Token ID2209
Feature activation+6.93e-01

Pos logit contributions
heid+0.571
hips+0.485
ertodd+0.466
 refrain+0.435
olini+0.393
Neg logit contributions
cember-0.610
isphere-0.599
nir-0.592
andum-0.582
asar-0.581
Token by
Token ID416
Feature activation+2.97e-01

Pos logit contributions
cember+1.737
isphere+1.704
nir+1.675
andum+1.658
asar+1.649
Neg logit contributions
heid-1.885
hips-1.625
ertodd-1.579
 refrain-1.459
olini-1.349
Token Pu
Token ID11634
Feature activation+3.74e+00

Pos logit contributions
cember+0.748
isphere+0.731
nir+0.724
andum+0.714
asar+0.710
Neg logit contributions
heid-0.806
hips-0.693
ertodd-0.673
 refrain-0.622
olini-0.574
Tokenig
Token ID328
Feature activation+1.11e+00

Pos logit contributions
asar+4.678
isphere+4.630
nir+4.592
ause+4.556
istical+4.542
Neg logit contributions
heid-13.232
hips-12.086
ertodd-11.914
 refrain-11.519
creen-10.409
Tokendem
Token ID9536
Feature activation+1.68e+00

Pos logit contributions
cember+2.677
isphere+2.615
nir+2.593
andum+2.562
asar+2.547
Neg logit contributions
heid-3.072
hips-2.672
ertodd-2.587
 refrain-2.420
olini-2.224
Tokenont
Token ID756
Feature activation+4.35e-01

Pos logit contributions
cember+4.168
isphere+4.089
andum+4.088
nir+4.081
asar+4.045
Neg logit contributions
heid-4.455
hips-3.847
ertodd-3.737
 refrain-3.498
olini-3.161
Token before
Token ID878
Feature activation-8.30e-01

Pos logit contributions
cember+1.080
isphere+1.057
nir+1.043
andum+1.028
asar+1.024
Neg logit contributions
heid-1.197
hips-1.032
ertodd-1.000
 refrain-0.930
olini-0.856
Token the
Token ID262
Feature activation+3.02e-01

Pos logit contributions
heid+2.108
hips+1.798
ertodd+1.717
 refrain+1.604
olini+1.455
Neg logit contributions
cember-2.228
isphere-2.190
nir-2.160
asar-2.120
andum-2.120
Token,
Token ID11
Feature activation+5.26e-01

Pos logit contributions
isphere+6.044
cember+5.942
nir+5.806
asar+5.792
andum+5.780
Neg logit contributions
heid-6.468
ertodd-5.753
hips-5.658
 refrain-4.946
olini-4.840
Token motor
Token ID5584
Feature activation+4.60e-01

Pos logit contributions
cember+1.350
isphere+1.330
nir+1.311
andum+1.292
asar+1.288
Neg logit contributions
heid-1.389
hips-1.192
ertodd-1.169
 refrain-1.062
olini-0.991
Tokenized
Token ID1143
Feature activation+9.30e-02

Pos logit contributions
cember+1.079
isphere+1.063
nir+1.045
andum+1.029
asar+1.023
Neg logit contributions
heid-1.321
hips-1.150
ertodd-1.120
 refrain-1.039
olini-0.964
Token wheelchair
Token ID27181
Feature activation+1.02e+00

Pos logit contributions
cember+0.221
isphere+0.217
nir+0.214
andum+0.210
asar+0.209
Neg logit contributions
heid-0.265
hips-0.230
ertodd-0.224
 refrain-0.208
olini-0.193
Token (
Token ID357
Feature activation-4.64e-02

Pos logit contributions
cember+2.484
isphere+2.468
nir+2.424
andum+2.381
asar+2.375
Neg logit contributions
heid-2.753
hips-2.376
ertodd-2.362
 refrain-2.135
olini-2.013
TokenFigure
Token ID11337
Feature activation+3.74e+00

Pos logit contributions
heid+0.136
hips+0.118
ertodd+0.114
 refrain+0.107
olini+0.099
Neg logit contributions
cember-0.107
isphere-0.105
nir-0.103
andum-0.102
asar-0.101
Token 2
Token ID362
Feature activation-3.50e-01

Pos logit contributions
cember+6.533
isphere+6.340
nir+6.250
andum+6.072
istical+6.062
Neg logit contributions
heid-11.786
ertodd-10.715
hips-10.295
 refrain-9.483
olini-9.135
TokenA
Token ID32
Feature activation-1.93e-01

Pos logit contributions
heid+0.963
hips+0.833
ertodd+0.799
 refrain+0.751
olini+0.690
Neg logit contributions
cember-0.868
isphere-0.847
nir-0.839
andum-0.825
asar-0.823
Token,
Token ID11
Feature activation-4.44e-01

Pos logit contributions
heid+0.511
hips+0.439
ertodd+0.420
 refrain+0.393
olini+0.359
Neg logit contributions
cember-0.498
isphere-0.487
nir-0.483
andum-0.476
asar-0.473
Token [
Token ID685
Feature activation-9.93e-01

Pos logit contributions
heid+1.238
hips+1.071
ertodd+1.026
 refrain+0.969
olini+0.891
Neg logit contributions
cember-1.085
isphere-1.059
nir-1.052
andum-1.033
asar-1.028
TokenAction
Token ID12502
Feature activation-2.66e-01

Pos logit contributions
heid+2.800
hips+2.439
ertodd+2.296
 refrain+2.191
olini+2.015
Neg logit contributions
cember-2.385
isphere-2.325
nir-2.296
andum-2.274
asar-2.243
Tokenas
Token ID292
Feature activation-2.92e-02

Pos logit contributions
heid+0.527
hips+0.457
ertodd+0.439
 refrain+0.412
olini+0.380
Neg logit contributions
cember-0.452
isphere-0.441
nir-0.434
andum-0.430
asar-0.426
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
heid+0.080
hips+0.069
ertodd+0.067
 refrain+0.063
olini+0.058
Neg logit contributions
cember-0.072
isphere-0.071
nir-0.070
andum-0.069
asar-0.069
Token gray
Token ID12768
Feature activation-1.83e-01

Pos logit contributions
heid+0.545
hips+0.467
ertodd+0.450
 refrain+0.419
olini+0.383
Neg logit contributions
cember-0.544
isphere-0.533
nir-0.527
andum-0.519
asar-0.517
Token area
Token ID1989
Feature activation+2.84e-01

Pos logit contributions
heid+0.497
hips+0.430
ertodd+0.411
 refrain+0.387
olini+0.354
Neg logit contributions
cember-0.462
isphere-0.451
nir-0.445
andum-0.440
asar-0.435
Token in
Token ID287
Feature activation+1.46e-01

Pos logit contributions
cember+0.689
isphere+0.677
nir+0.667
asar+0.655
andum+0.655
Neg logit contributions
heid-0.797
hips-0.687
ertodd-0.671
 refrain-0.620
olini-0.574
Token Figure
Token ID11291
Feature activation+3.69e+00

Pos logit contributions
cember+0.372
isphere+0.366
nir+0.362
asar+0.356
andum+0.355
Neg logit contributions
heid-0.389
hips-0.335
ertodd-0.325
 refrain-0.299
olini-0.276
Token 2
Token ID362
Feature activation+2.48e-02

Pos logit contributions
cember+6.829
nir+6.576
isphere+6.555
asar+6.326
ause+6.310
Neg logit contributions
heid-11.337
ertodd-10.137
hips-9.922
 refrain-9.103
olini-8.506
Token).
Token ID737
Feature activation-1.62e-02

Pos logit contributions
cember+0.060
isphere+0.058
nir+0.058
andum+0.057
asar+0.056
Neg logit contributions
heid-0.070
hips-0.061
ertodd-0.059
 refrain-0.055
olini-0.051
Token Then
Token ID3244
Feature activation-4.05e-01

Pos logit contributions
heid+0.043
hips+0.037
ertodd+0.035
 refrain+0.033
olini+0.030
Neg logit contributions
cember-0.042
isphere-0.041
nir-0.041
andum-0.040
asar-0.040
Token introduce
Token ID10400
Feature activation+4.23e-01

Pos logit contributions
heid+1.084
hips+0.931
ertodd+0.897
 refrain+0.840
olini+0.769
Neg logit contributions
cember-1.038
isphere-1.016
nir-1.003
andum-0.987
asar-0.982
Token v
Token ID410
Feature activation-8.70e-01

Pos logit contributions
cember+1.035
isphere+1.014
nir+1.002
andum+0.989
asar+0.985
Neg logit contributions
heid-1.173
hips-1.010
ertodd-0.987
 refrain-0.910
olini-0.842
Tokene
Token ID68
Feature activation+1.61e+00

Pos logit contributions
cember+1.533
isphere+1.499
nir+1.487
andum+1.466
asar+1.453
Neg logit contributions
heid-1.923
hips-1.668
ertodd-1.633
 refrain-1.512
olini-1.402
Token,
Token ID11
Feature activation+3.46e-02

Pos logit contributions
cember+4.248
nir+4.124
isphere+4.086
andum+4.079
asar+4.051
Neg logit contributions
heid-4.054
hips-3.471
ertodd-3.454
 refrain-3.004
olini-2.822
Token je
Token ID11223
Feature activation+3.28e-01

Pos logit contributions
cember+0.092
isphere+0.091
nir+0.090
andum+0.088
asar+0.088
Neg logit contributions
heid-0.089
hips-0.076
ertodd-0.073
 refrain-0.068
olini-0.062
Token les
Token ID10287
Feature activation-4.22e-01

Pos logit contributions
cember+0.828
isphere+0.811
nir+0.801
andum+0.789
asar+0.786
Neg logit contributions
heid-0.889
hips-0.765
ertodd-0.740
 refrain-0.688
olini-0.632
Token
Token ID39073
Feature activation+2.58e-01

Pos logit contributions
heid+1.110
hips+0.951
ertodd+0.911
 refrain+0.858
olini+0.781
Neg logit contributions
cember-1.097
isphere-1.082
nir-1.061
andum-1.047
asar-1.042
Tokencl
Token ID565
Feature activation+3.64e+00

Pos logit contributions
cember+0.648
isphere+0.635
nir+0.627
andum+0.617
asar+0.615
Neg logit contributions
heid-0.703
hips-0.605
ertodd-0.585
 refrain-0.544
olini-0.501
Tokenares
Token ID3565
Feature activation+3.83e-01

Pos logit contributions
ause+7.035
andum+6.892
nir+6.848
asar+6.774
cember+6.726
Neg logit contributions
heid-10.817
ertodd-9.576
hips-9.472
 refrain-9.283
 predecessor-8.207
Token offic
Token ID1163
Feature activation+7.82e-01

Pos logit contributions
cember+1.021
isphere+0.998
nir+0.993
andum+0.978
asar+0.973
Neg logit contributions
heid-0.980
hips-0.832
ertodd-0.816
 refrain-0.738
olini-0.680
Tokeniel
Token ID8207
Feature activation+2.27e-02

Pos logit contributions
cember+2.003
isphere+1.987
nir+1.982
andum+1.954
asar+1.935
Neg logit contributions
heid-2.053
hips-1.722
ertodd-1.720
 refrain-1.594
olini-1.432
Tokenlement
Token ID1732
Feature activation+5.46e-01

Pos logit contributions
cember+0.057
isphere+0.056
nir+0.055
andum+0.054
asar+0.054
Neg logit contributions
heid-0.062
hips-0.053
ertodd-0.052
 refrain-0.048
olini-0.044
Token
Token ID39073
Feature activation+6.57e-01

Pos logit contributions
cember+1.443
isphere+1.409
nir+1.405
andum+1.383
asar+1.376
Neg logit contributions
heid-1.406
hips-1.196
ertodd-1.174
 refrain-1.066
olini-0.980
Tokens
Token ID82
Feature activation-6.65e-01

Pos logit contributions
cember+1.061
isphere+1.039
nir+1.026
andum+1.010
asar+1.006
Neg logit contributions
heid-1.199
hips-1.033
ertodd-1.007
 refrain-0.935
olini-0.861
Token largest
Token ID4387
Feature activation-4.98e-02

Pos logit contributions
heid+1.736
hips+1.488
ertodd+1.420
 refrain+1.334
olini+1.214
Neg logit contributions
cember-1.740
isphere-1.707
nir-1.683
andum-1.655
istical-1.647
Token party
Token ID2151
Feature activation-8.25e-01

Pos logit contributions
heid+0.127
hips+0.108
ertodd+0.105
 refrain+0.097
olini+0.088
Neg logit contributions
cember-0.133
isphere-0.131
nir-0.129
andum-0.127
asar-0.127
Token abandoned
Token ID9958
Feature activation-6.90e-01

Pos logit contributions
heid+2.184
hips+1.898
ertodd+1.801
 refrain+1.714
olini+1.558
Neg logit contributions
cember-2.105
nir-2.046
isphere-2.045
andum-2.010
istical-1.992
Token President
Token ID1992
Feature activation+2.93e-01

Pos logit contributions
heid+1.778
hips+1.522
ertodd+1.453
 refrain+1.366
olini+1.236
Neg logit contributions
cember-1.829
isphere-1.800
nir-1.773
andum-1.740
istical-1.733
Token Dil
Token ID29328
Feature activation+3.64e+00

Pos logit contributions
cember+0.680
isphere+0.664
nir+0.656
andum+0.645
asar+0.643
Neg logit contributions
heid-0.855
hips-0.743
ertodd-0.723
 refrain-0.675
olini-0.624
Tokenma
Token ID2611
Feature activation-6.47e-01

Pos logit contributions
nir+6.748
asar+6.737
cember+6.574
ause+6.560
isphere+6.246
Neg logit contributions
heid-11.298
hips-10.301
ertodd-10.185
 refrain-9.340
creen-8.699
Token Rousse
Token ID42849
Feature activation+2.22e+00

Pos logit contributions
heid+1.554
hips+1.303
ertodd+1.246
 refrain+1.174
olini+1.059
Neg logit contributions
cember-1.837
isphere-1.819
nir-1.759
andum-1.751
istical-1.744
Tokenff
Token ID487
Feature activation+9.69e-01

Pos logit contributions
cember+2.864
ause+2.705
nir+2.704
asar+2.662
utics+2.626
Neg logit contributions
heid-8.577
ertodd-7.784
hips-7.736
 refrain-7.211
creen-6.714
Token
Token ID447
Feature activation+7.37e-01

Pos logit contributions
cember+2.171
isphere+2.111
nir+2.088
asar+2.063
andum+2.060
Neg logit contributions
heid-2.885
hips-2.505
ertodd-2.456
 refrain-2.281
olini-2.121
Token
Token ID247
Feature activation+5.61e-01

Pos logit contributions
cember+1.148
isphere+1.097
nir+1.077
andum+1.058
asar+1.042
Neg logit contributions
heid-2.718
hips-2.426
ertodd-2.381
 refrain-2.257
olini-2.138
Token
Token ID198
Feature activation+2.15e-01

Pos logit contributions
heid+0.588
hips+0.505
ertodd+0.481
 refrain+0.448
olini+0.408
Neg logit contributions
cember-0.604
isphere-0.591
nir-0.579
andum-0.573
asar-0.567
Tokenas
Token ID292
Feature activation-7.53e-02

Pos logit contributions
cember+0.465
isphere+0.454
nir+0.447
andum+0.439
asar+0.437
Neg logit contributions
heid-0.660
hips-0.579
ertodd-0.563
 refrain-0.529
olini-0.492
Tokend
Token ID67
Feature activation+2.50e-01

Pos logit contributions
heid+0.207
hips+0.178
ertodd+0.173
 refrain+0.161
olini+0.148
Neg logit contributions
cember-0.187
isphere-0.184
nir-0.181
andum-0.178
asar-0.178
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
cember+0.577
isphere+0.565
nir+0.556
asar+0.549
andum+0.547
Neg logit contributions
heid-0.727
hips-0.633
ertodd-0.617
 refrain-0.576
olini-0.532
Token
Token ID198
Feature activation+2.39e-01

Pos logit contributions
heid+0.358
hips+0.307
ertodd+0.294
 refrain+0.273
olini+0.249
Neg logit contributions
cember-0.361
isphere-0.354
nir-0.347
andum-0.343
asar-0.340
TokenGu
Token ID8205
Feature activation+3.61e+00

Pos logit contributions
cember+0.530
isphere+0.518
nir+0.511
andum+0.501
asar+0.499
Neg logit contributions
heid-0.722
hips-0.632
ertodd-0.615
 refrain-0.577
olini-0.536
TokenM
Token ID44
Feature activation+2.02e-01

Pos logit contributions
isphere+8.004
nir+7.930
asar+7.897
cember+7.765
istical+7.549
Neg logit contributions
heid-9.612
ertodd-8.538
hips-8.426
 refrain-7.821
creen-7.113
Tokenih
Token ID4449
Feature activation+3.28e-01

Pos logit contributions
cember+0.405
isphere+0.394
nir+0.388
andum+0.381
asar+0.379
Neg logit contributions
heid-0.655
hips-0.578
ertodd-0.563
 refrain-0.531
olini-0.497
Tokeno
Token ID78
Feature activation+1.72e+00

Pos logit contributions
cember+0.680
isphere+0.665
nir+0.657
andum+0.640
asar+0.639
Neg logit contributions
heid-1.039
hips-0.913
ertodd-0.889
 refrain-0.837
olini-0.781
Token
Token ID198
Feature activation+4.65e-01

Pos logit contributions
cember+4.035
isphere+3.937
nir+3.929
asar+3.881
istical+3.837
Neg logit contributions
heid-4.761
hips-4.144
ertodd-4.066
 refrain-3.722
olini-3.493
Token
Token ID198
Feature activation+8.89e-01

Pos logit contributions
cember+1.151
isphere+1.128
nir+1.122
asar+1.101
andum+1.101
Neg logit contributions
heid-1.272
hips-1.094
ertodd-1.068
 refrain-0.989
olini-0.914
TokenV
Token ID53
Feature activation+3.15e-01

Pos logit contributions
cember+0.146
isphere+0.142
nir+0.140
andum+0.138
asar+0.137
Neg logit contributions
heid-0.193
hips-0.169
ertodd-0.164
 refrain-0.153
olini-0.143
Tokenir
Token ID343
Feature activation-3.47e-01

Pos logit contributions
cember+0.685
isphere+0.666
nir+0.657
andum+0.644
asar+0.640
Neg logit contributions
heid-0.967
hips-0.848
ertodd-0.822
 refrain-0.767
olini-0.720
TokenGo
Token ID5247
Feature activation+1.28e+00

Pos logit contributions
heid+1.096
hips+0.970
ertodd+0.931
 refrain+0.880
olini+0.829
Neg logit contributions
cember-0.719
isphere-0.698
nir-0.685
andum-0.674
asar-0.667
Token
Token ID447
Feature activation+2.67e-01

Pos logit contributions
cember+3.007
isphere+2.941
nir+2.913
andum+2.867
asar+2.860
Neg logit contributions
heid-3.671
hips-3.180
ertodd-3.113
 refrain-2.891
olini-2.662
Token
Token ID251
Feature activation-1.09e-01

Pos logit contributions
cember+0.412
isphere+0.398
nir+0.390
andum+0.380
asar+0.376
Neg logit contributions
heid-0.985
hips-0.884
ertodd-0.864
 refrain-0.822
olini-0.776
Token Agu
Token ID33118
Feature activation+3.61e+00

Pos logit contributions
heid+0.301
hips+0.261
ertodd+0.251
 refrain+0.234
olini+0.216
Neg logit contributions
cember-0.272
isphere-0.266
nir-0.262
andum-0.258
asar-0.257
Tokenilar
Token ID1794
Feature activation+8.09e-01

Pos logit contributions
isphere+5.791
asar+5.773
cember+5.728
istical+5.649
ause+5.631
Neg logit contributions
heid-11.799
hips-10.665
ertodd-10.614
 refrain-10.082
creen-9.299
Token near
Token ID1474
Feature activation+4.87e-01

Pos logit contributions
cember+1.989
isphere+1.948
nir+1.925
andum+1.895
asar+1.889
Neg logit contributions
heid-2.228
hips-1.916
ertodd-1.878
 refrain-1.733
olini-1.592
Token one
Token ID530
Feature activation+1.65e-01

Pos logit contributions
cember+1.237
isphere+1.209
nir+1.204
andum+1.184
asar+1.182
Neg logit contributions
heid-1.307
hips-1.118
ertodd-1.090
 refrain-1.002
olini-0.923
Token of
Token ID286
Feature activation+6.18e-01

Pos logit contributions
cember+0.440
isphere+0.431
nir+0.425
andum+0.419
asar+0.418
Neg logit contributions
heid-0.426
hips-0.364
ertodd-0.351
 refrain-0.323
olini-0.297
Token the
Token ID262
Feature activation-2.75e-02

Pos logit contributions
cember+1.571
isphere+1.538
nir+1.522
andum+1.507
asar+1.505
Neg logit contributions
heid-1.647
hips-1.416
ertodd-1.378
 refrain-1.267
olini-1.166
Token.
Token ID13
Feature activation+4.30e-01

Pos logit contributions
heid+0.023
hips+0.020
ertodd+0.019
 refrain+0.018
olini+0.016
Neg logit contributions
cember-0.022
isphere-0.021
nir-0.021
andum-0.020
asar-0.020
Token That
Token ID1320
Feature activation+6.88e-01

Pos logit contributions
cember+1.064
isphere+1.041
nir+1.033
andum+1.017
asar+1.014
Neg logit contributions
heid-1.182
hips-1.016
ertodd-0.991
 refrain-0.917
olini-0.846
Token leaves
Token ID5667
Feature activation+2.69e-01

Pos logit contributions
cember+1.621
isphere+1.581
nir+1.565
andum+1.540
asar+1.532
Neg logit contributions
heid-1.978
hips-1.718
ertodd-1.666
 refrain-1.553
olini-1.437
Token income
Token ID3739
Feature activation-1.81e-01

Pos logit contributions
cember+0.634
isphere+0.622
nir+0.612
andum+0.602
asar+0.600
Neg logit contributions
heid-0.773
hips-0.674
ertodd-0.652
 refrain-0.611
olini-0.564
Token of
Token ID286
Feature activation+1.60e+00

Pos logit contributions
heid+0.478
hips+0.413
ertodd+0.394
 refrain+0.372
olini+0.337
Neg logit contributions
cember-0.466
isphere-0.457
nir-0.452
andum-0.446
asar-0.443
Token roughly
Token ID7323
Feature activation+3.60e+00

Pos logit contributions
cember+3.438
nir+3.322
isphere+3.277
asar+3.263
andum+3.254
Neg logit contributions
heid-4.859
ertodd-4.186
hips-4.150
 refrain-3.805
olini-3.585
Token $
Token ID720
Feature activation+6.85e-01

Pos logit contributions
cember+6.286
nir+6.122
andum+6.001
asar+5.938
isphere+5.848
Neg logit contributions
heid-11.343
ertodd-10.211
hips-9.659
 refrain-8.924
olini-8.712
Token177
Token ID22413
Feature activation+1.01e+00

Pos logit contributions
cember+1.527
isphere+1.492
nir+1.482
asar+1.449
andum+1.448
Neg logit contributions
heid-2.036
hips-1.775
ertodd-1.742
 refrain-1.628
olini-1.507
Token million
Token ID1510
Feature activation+1.04e-01

Pos logit contributions
cember+1.834
isphere+1.775
nir+1.769
andum+1.764
istical+1.709
Neg logit contributions
heid-3.417
hips-3.013
ertodd-2.925
 refrain-2.751
olini-2.635
Token.
Token ID13
Feature activation+6.06e-01

Pos logit contributions
cember+0.265
isphere+0.259
nir+0.256
andum+0.252
asar+0.251
Neg logit contributions
heid-0.279
hips-0.241
ertodd-0.231
 refrain-0.216
olini-0.197
Token Of
Token ID3226
Feature activation+7.82e-01

Pos logit contributions
cember+1.491
isphere+1.459
nir+1.453
andum+1.429
asar+1.425
Neg logit contributions
heid-1.664
hips-1.429
ertodd-1.400
 refrain-1.291
olini-1.193
Token blue
Token ID4171
Feature activation+5.50e-01

Pos logit contributions
heid+0.081
hips+0.068
ertodd+0.066
 refrain+0.060
olini+0.055
Neg logit contributions
cember-0.095
isphere-0.093
nir-0.092
andum-0.091
asar-0.091
Token v
Token ID410
Feature activation-5.91e-01

Pos logit contributions
cember+1.352
isphere+1.331
nir+1.309
asar+1.294
andum+1.290
Neg logit contributions
heid-1.517
hips-1.302
ertodd-1.280
 refrain-1.169
olini-1.087
Tokenort
Token ID419
Feature activation+5.79e-01

Pos logit contributions
heid+1.910
hips+1.680
ertodd+1.626
 refrain+1.537
olini+1.443
Neg logit contributions
cember-1.185
isphere-1.144
nir-1.134
andum-1.112
istical-1.095
Tokenon
Token ID261
Feature activation-6.42e-02

Pos logit contributions
cember+1.264
isphere+1.260
nir+1.228
andum+1.216
asar+1.215
Neg logit contributions
heid-1.738
hips-1.525
ertodd-1.492
 refrain-1.393
olini-1.281
Token in
Token ID287
Feature activation+2.19e-01

Pos logit contributions
heid+0.172
hips+0.148
ertodd+0.143
 refrain+0.133
olini+0.122
Neg logit contributions
cember-0.164
isphere-0.160
nir-0.158
andum-0.156
asar-0.155
Token Figure
Token ID11291
Feature activation+3.59e+00

Pos logit contributions
cember+0.569
isphere+0.557
nir+0.556
andum+0.546
asar+0.543
Neg logit contributions
heid-0.576
hips-0.492
ertodd-0.478
 refrain-0.438
olini-0.404
Token 2
Token ID362
Feature activation-9.64e-02

Pos logit contributions
cember+6.230
isphere+5.950
nir+5.911
ause+5.799
andum+5.778
Neg logit contributions
heid-11.450
ertodd-10.152
hips-10.056
 refrain-9.147
olini-8.632
Token).
Token ID737
Feature activation+1.60e-01

Pos logit contributions
heid+0.263
hips+0.226
ertodd+0.218
 refrain+0.204
olini+0.187
Neg logit contributions
cember-0.242
isphere-0.237
nir-0.234
andum-0.231
asar-0.229
Token Near
Token ID20173
Feature activation-5.72e-01

Pos logit contributions
cember+0.396
isphere+0.388
nir+0.384
andum+0.378
asar+0.377
Neg logit contributions
heid-0.440
hips-0.379
ertodd-0.368
 refrain-0.342
olini-0.315
Token those
Token ID883
Feature activation+2.87e-01

Pos logit contributions
heid+1.516
hips+1.299
ertodd+1.250
 refrain+1.166
olini+1.066
Neg logit contributions
cember-1.480
isphere-1.451
nir-1.431
andum-1.409
asar-1.400
Token heavier
Token ID20140
Feature activation-8.47e-01

Pos logit contributions
cember+0.759
isphere+0.745
nir+0.736
andum+0.725
asar+0.723
Neg logit contributions
heid-0.742
hips-0.632
ertodd-0.614
 refrain-0.565
olini-0.517
Token --
Token ID1377
Feature activation-8.01e-01

Pos logit contributions
cember+1.271
isphere+1.249
nir+1.230
andum+1.211
asar+1.207
Neg logit contributions
heid-1.464
hips-1.259
ertodd-1.226
 refrain-1.137
olini-1.059
Token or
Token ID393
Feature activation-6.20e-01

Pos logit contributions
heid+2.079
hips+1.807
ertodd+1.701
 refrain+1.618
olini+1.466
Neg logit contributions
cember-2.106
isphere-2.040
nir-2.007
andum-1.988
istical-1.973
Token may
Token ID743
Feature activation+2.51e-02

Pos logit contributions
heid+1.673
hips+1.455
ertodd+1.384
 refrain+1.318
olini+1.196
Neg logit contributions
cember-1.565
isphere-1.524
nir-1.500
andum-1.480
asar-1.476
Token perhaps
Token ID3737
Feature activation-5.52e-02

Pos logit contributions
cember+0.069
isphere+0.067
nir+0.067
andum+0.066
asar+0.066
Neg logit contributions
heid-0.063
hips-0.053
ertodd-0.052
 refrain-0.047
olini-0.043
Token be
Token ID307
Feature activation-1.08e-01

Pos logit contributions
heid+0.143
hips+0.121
ertodd+0.118
 refrain+0.108
olini+0.099
Neg logit contributions
cember-0.147
isphere-0.144
nir-0.143
andum-0.140
asar-0.140
Token allev
Token ID23863
Feature activation+3.58e+00

Pos logit contributions
heid+0.306
hips+0.266
ertodd+0.256
 refrain+0.241
olini+0.222
Neg logit contributions
cember-0.258
isphere-0.252
nir-0.249
andum-0.245
asar-0.244
Tokeniated
Token ID12931
Feature activation+1.33e+00

Pos logit contributions
isphere+4.228
nir+4.224
istical+4.174
ause+4.121
cember+3.945
Neg logit contributions
heid-13.342
ertodd-12.295
hips-12.140
 refrain-11.540
olini-10.867
Token or
Token ID393
Feature activation+5.20e-01

Pos logit contributions
cember+3.260
isphere+3.199
nir+3.186
asar+3.115
andum+3.093
Neg logit contributions
heid-3.617
hips-3.059
ertodd-3.041
 refrain-2.764
olini-2.597
Token designed
Token ID3562
Feature activation+9.59e-01

Pos logit contributions
cember+1.177
isphere+1.154
nir+1.140
andum+1.117
asar+1.113
Neg logit contributions
heid-1.546
hips-1.342
ertodd-1.312
 refrain-1.215
olini-1.136
Token out
Token ID503
Feature activation-7.75e-01

Pos logit contributions
cember+2.324
isphere+2.290
nir+2.266
asar+2.216
andum+2.211
Neg logit contributions
heid-2.670
hips-2.269
ertodd-2.241
 refrain-2.052
olini-1.923
Token of
Token ID286
Feature activation-4.33e-02

Pos logit contributions
heid+2.014
hips+1.740
ertodd+1.668
 refrain+1.553
olini+1.411
Neg logit contributions
cember-2.027
isphere-1.976
nir-1.960
andum-1.935
asar-1.921
Token cell
Token ID2685
Feature activation-3.94e-01

Pos logit contributions
cember+1.891
isphere+1.865
nir+1.838
asar+1.801
andum+1.801
Neg logit contributions
heid-2.103
hips-1.805
ertodd-1.777
 refrain-1.633
olini-1.508
Token,
Token ID11
Feature activation-4.57e-01

Pos logit contributions
heid+1.052
hips+0.912
ertodd+0.863
 refrain+0.813
olini+0.740
Neg logit contributions
cember-1.013
isphere-0.984
nir-0.972
andum-0.966
asar-0.958
Token as
Token ID355
Feature activation-5.92e-01

Pos logit contributions
heid+1.181
hips+1.019
ertodd+0.967
 refrain+0.910
olini+0.826
Neg logit contributions
cember-1.208
isphere-1.179
nir-1.166
andum-1.150
asar-1.143
Token shown
Token ID3402
Feature activation+2.29e+00

Pos logit contributions
heid+1.654
hips+1.441
ertodd+1.379
 refrain+1.297
olini+1.191
Neg logit contributions
cember-1.444
isphere-1.408
nir-1.391
andum-1.371
asar-1.362
Token in
Token ID287
Feature activation+7.31e-01

Pos logit contributions
cember+4.967
isphere+4.866
nir+4.862
asar+4.765
andum+4.736
Neg logit contributions
heid-6.726
ertodd-5.721
hips-5.641
 refrain-5.199
olini-4.920
Token Figure
Token ID11291
Feature activation+3.58e+00

Pos logit contributions
cember+1.841
nir+1.802
isphere+1.800
andum+1.773
asar+1.762
Neg logit contributions
heid-1.956
hips-1.667
ertodd-1.632
 refrain-1.498
olini-1.384
Token 3
Token ID513
Feature activation-2.48e-02

Pos logit contributions
cember+6.499
nir+6.134
isphere+6.132
andum+6.036
ause+5.998
Neg logit contributions
heid-11.287
ertodd-9.973
hips-9.746
 refrain-8.973
olini-8.479
Token.
Token ID13
Feature activation-7.87e-01

Pos logit contributions
heid+0.068
hips+0.059
ertodd+0.057
 refrain+0.053
olini+0.049
Neg logit contributions
cember-0.062
isphere-0.060
nir-0.060
andum-0.059
asar-0.058
Token
Token ID198
Feature activation-7.66e-01

Pos logit contributions
heid+2.038
hips+1.759
ertodd+1.650
 refrain+1.557
olini+1.419
Neg logit contributions
cember-2.094
isphere-2.044
nir-2.006
andum-1.976
asar-1.957
Token
Token ID198
Feature activation+7.40e-02

Pos logit contributions
heid+1.895
hips+1.632
ertodd+1.513
 refrain+1.422
olini+1.275
Neg logit contributions
cember-2.147
isphere-2.097
nir-2.036
andum-2.022
asar-1.989
TokenFigure
Token ID11337
Feature activation+3.31e+00

Pos logit contributions
cember+0.158
isphere+0.154
nir+0.151
andum+0.149
asar+0.148
Neg logit contributions
heid-0.230
hips-0.202
ertodd-0.195
 refrain-0.183
olini-0.171
Token marketing
Token ID7124
Feature activation-1.68e-01

Pos logit contributions
heid+0.474
hips+0.397
ertodd+0.386
 refrain+0.345
olini+0.315
Neg logit contributions
cember-0.578
isphere-0.567
nir-0.560
asar-0.553
andum-0.551
Token campaign
Token ID1923
Feature activation-9.33e-02

Pos logit contributions
heid+0.422
hips+0.359
ertodd+0.346
 refrain+0.320
olini+0.291
Neg logit contributions
cember-0.458
isphere-0.449
nir-0.444
andum-0.438
asar-0.436
Token.
Token ID13
Feature activation-2.48e-01

Pos logit contributions
heid+0.255
hips+0.221
ertodd+0.213
 refrain+0.199
olini+0.182
Neg logit contributions
cember-0.233
isphere-0.228
nir-0.225
andum-0.222
asar-0.221
Token Instead
Token ID5455
Feature activation+5.96e-01

Pos logit contributions
heid+0.654
hips+0.561
ertodd+0.541
 refrain+0.503
olini+0.461
Neg logit contributions
cember-0.642
isphere-0.629
nir-0.621
andum-0.612
asar-0.609
Token of
Token ID286
Feature activation-3.40e-02

Pos logit contributions
cember+1.443
isphere+1.423
nir+1.387
andum+1.371
istical+1.361
Neg logit contributions
heid-1.668
hips-1.434
ertodd-1.397
 refrain-1.292
olini-1.199
TokenTechn
Token ID25574
Feature activation+3.58e+00

Pos logit contributions
heid+0.089
hips+0.076
ertodd+0.074
 refrain+0.068
olini+0.062
Neg logit contributions
cember-0.089
isphere-0.087
nir-0.086
andum-0.085
asar-0.085
Tokenicol
Token ID27045
Feature activation-1.78e-01

Pos logit contributions
isphere+6.399
cember+6.155
ause+6.132
nir+6.113
asar+6.063
Neg logit contributions
heid-11.538
hips-10.355
ertodd-10.014
 refrain-9.867
olini-8.595
Tokenor
Token ID273
Feature activation-3.70e-01

Pos logit contributions
heid+0.548
hips+0.481
ertodd+0.467
 refrain+0.439
olini+0.410
Neg logit contributions
cember-0.383
isphere-0.372
nir-0.367
andum-0.361
asar-0.359
Token,
Token ID11
Feature activation-7.19e-01

Pos logit contributions
heid+1.017
hips+0.879
ertodd+0.847
 refrain+0.792
olini+0.729
Neg logit contributions
cember-0.918
isphere-0.898
nir-0.888
andum-0.874
asar-0.870
Token Hitchcock
Token ID49817
Feature activation+1.73e-01

Pos logit contributions
heid+1.912
hips+1.642
ertodd+1.580
 refrain+1.473
olini+1.351
Neg logit contributions
cember-1.852
isphere-1.811
nir-1.792
andum-1.767
asar-1.755
Token shot
Token ID2823
Feature activation+5.27e-01

Pos logit contributions
cember+0.407
isphere+0.398
nir+0.393
andum+0.387
asar+0.385
Neg logit contributions
heid-0.501
hips-0.434
ertodd-0.422
 refrain-0.394
olini-0.364
Token far
Token ID1290
Feature activation+9.41e-01

Pos logit contributions
cember+0.247
isphere+0.241
nir+0.239
andum+0.235
asar+0.234
Neg logit contributions
heid-0.263
hips-0.227
ertodd-0.220
 refrain-0.202
olini-0.187
Token cry
Token ID3960
Feature activation+2.55e-01

Pos logit contributions
cember+2.707
nir+2.660
isphere+2.654
andum+2.599
ause+2.597
Neg logit contributions
heid-2.139
hips-1.813
ertodd-1.811
 refrain-1.555
olini-1.464
Token from
Token ID422
Feature activation-1.24e-01

Pos logit contributions
cember+0.631
isphere+0.621
nir+0.616
andum+0.604
asar+0.601
Neg logit contributions
heid-0.697
hips-0.605
ertodd-0.587
 refrain-0.541
olini-0.504
Token
Token ID564
Feature activation+4.91e-01

Pos logit contributions
heid+0.341
hips+0.294
ertodd+0.285
 refrain+0.265
olini+0.244
Neg logit contributions
cember-0.308
isphere-0.302
nir-0.298
andum-0.293
asar-0.292
Token
Token ID250
Feature activation-6.51e-03

Pos logit contributions
cember+0.781
isphere+0.756
nir+0.741
andum+0.723
asar+0.718
Neg logit contributions
heid-1.789
hips-1.603
ertodd-1.567
 refrain-1.488
olini-1.405
Tokengu
Token ID5162
Feature activation+3.58e+00

Pos logit contributions
heid+0.019
hips+0.016
ertodd+0.016
 refrain+0.015
olini+0.014
Neg logit contributions
cember-0.015
isphere-0.015
nir-0.015
andum-0.015
asar-0.014
Tokenarant
Token ID4741
Feature activation+6.70e-01

Pos logit contributions
cember+5.402
istical+5.292
asar+5.278
isphere+5.265
ause+5.198
Neg logit contributions
heid-12.156
hips-10.957
ertodd-10.737
 refrain-10.270
creen-9.467
Tokenee
Token ID1453
Feature activation+8.41e-01

Pos logit contributions
cember+1.683
isphere+1.651
nir+1.632
andum+1.617
asar+1.601
Neg logit contributions
heid-1.793
hips-1.533
ertodd-1.505
 refrain-1.395
olini-1.268
Tokening
Token ID278
Feature activation+8.11e-01

Pos logit contributions
cember+1.990
isphere+1.926
nir+1.919
andum+1.906
ause+1.886
Neg logit contributions
heid-2.372
hips-2.060
ertodd-2.022
 refrain-1.864
olini-1.737
Token pre
Token ID662
Feature activation-1.17e+00

Pos logit contributions
cember+2.033
isphere+1.988
nir+1.969
andum+1.943
ause+1.940
Neg logit contributions
heid-2.167
hips-1.846
ertodd-1.829
 refrain-1.654
olini-1.552
Token-
Token ID12
Feature activation-2.82e-01

Pos logit contributions
heid+3.214
hips+2.772
ertodd+2.675
 refrain+2.500
olini+2.291
Neg logit contributions
cember-2.897
isphere-2.841
nir-2.803
andum-2.765
asar-2.746
Token°
Token ID7200
Feature activation-4.82e-02

Pos logit contributions
heid+0.813
hips+0.715
ertodd+0.692
 refrain+0.650
olini+0.605
Neg logit contributions
cember-0.562
isphere-0.551
nir-0.543
andum-0.533
asar-0.531
Token17
Token ID1558
Feature activation-4.58e-01

Pos logit contributions
heid+0.141
hips+0.123
ertodd+0.119
 refrain+0.112
olini+0.103
Neg logit contributions
cember-0.111
isphere-0.109
nir-0.107
andum-0.106
asar-0.105
Token).
Token ID737
Feature activation+1.03e+00

Pos logit contributions
heid+1.201
hips+1.040
ertodd+0.982
 refrain+0.930
olini+0.846
Neg logit contributions
cember-1.188
isphere-1.163
nir-1.145
andum-1.135
asar-1.130
Token
Token ID198
Feature activation-2.33e-01

Pos logit contributions
cember+2.519
isphere+2.467
nir+2.448
asar+2.406
andum+2.397
Neg logit contributions
heid-2.828
hips-2.435
ertodd-2.392
 refrain-2.205
olini-2.036
Token
Token ID198
Feature activation+4.58e-01

Pos logit contributions
heid+0.604
hips+0.519
ertodd+0.494
 refrain+0.461
olini+0.419
Neg logit contributions
cember-0.620
isphere-0.607
nir-0.595
andum-0.588
asar-0.583
TokenFigure
Token ID11337
Feature activation+3.55e+00

Pos logit contributions
cember+0.969
isphere+0.944
nir+0.930
andum+0.914
asar+0.909
Neg logit contributions
heid-1.428
hips-1.256
ertodd-1.219
 refrain-1.146
olini-1.069
Token 4
Token ID604
Feature activation-5.80e-01

Pos logit contributions
cember+6.459
andum+6.198
nir+6.149
istical+6.097
isphere+6.095
Neg logit contributions
heid-11.164
ertodd-9.777
hips-9.704
 refrain-9.013
olini-8.532
Token-
Token ID12
Feature activation+3.57e-03

Pos logit contributions
heid+1.594
hips+1.377
ertodd+1.331
 refrain+1.241
olini+1.139
Neg logit contributions
cember-1.437
isphere-1.407
nir-1.393
andum-1.369
asar-1.363
TokenA
Token ID32
Feature activation-4.45e-01

Pos logit contributions
cember+0.008
isphere+0.008
nir+0.008
andum+0.008
asar+0.008
Neg logit contributions
heid-0.011
hips-0.009
ertodd-0.009
 refrain-0.009
olini-0.008
Token Monthly
Token ID27573
Feature activation-2.09e+00

Pos logit contributions
heid+1.234
hips+1.068
ertodd+1.022
 refrain+0.962
olini+0.882
Neg logit contributions
cember-1.092
isphere-1.063
nir-1.061
andum-1.045
asar-1.033
Token increments
Token ID41867
Feature activation-1.07e+00

Pos logit contributions
heid+5.604
hips+4.937
ertodd+4.489
 refrain+4.388
olini+3.930
Neg logit contributions
cember-5.040
nir-4.912
andum-4.907
isphere-4.907
utics-4.832
Token pink
Token ID11398
Feature activation+1.24e-01

Pos logit contributions
cember+0.062
isphere+0.060
nir+0.060
andum+0.059
asar+0.059
Neg logit contributions
heid-0.058
hips-0.050
ertodd-0.048
 refrain-0.044
olini-0.040
Token v
Token ID410
Feature activation-5.06e-01

Pos logit contributions
cember+0.333
isphere+0.327
nir+0.324
asar+0.319
andum+0.319
Neg logit contributions
heid-0.314
hips-0.267
ertodd-0.259
 refrain-0.237
olini-0.218
Tokenort
Token ID419
Feature activation+4.85e-01

Pos logit contributions
heid+1.631
hips+1.437
ertodd+1.387
 refrain+1.299
olini+1.236
Neg logit contributions
cember-1.027
isphere-0.988
nir-0.974
andum-0.957
istical-0.945
Tokenon
Token ID261
Feature activation-1.51e-01

Pos logit contributions
cember+1.106
isphere+1.090
nir+1.076
andum+1.059
asar+1.058
Neg logit contributions
heid-1.417
hips-1.235
ertodd-1.206
 refrain-1.128
olini-1.038
Token in
Token ID287
Feature activation+1.84e-01

Pos logit contributions
heid+0.408
hips+0.350
ertodd+0.340
 refrain+0.314
olini+0.290
Neg logit contributions
cember-0.380
isphere-0.374
nir-0.369
andum-0.362
asar-0.362
Token Figure
Token ID11291
Feature activation+3.51e+00

Pos logit contributions
cember+0.479
isphere+0.470
nir+0.468
andum+0.460
asar+0.457
Neg logit contributions
heid-0.480
hips-0.410
ertodd-0.398
 refrain-0.366
olini-0.336
Token 2
Token ID362
Feature activation-1.33e-01

Pos logit contributions
cember+5.618
isphere+5.234
andum+5.175
ause+5.173
nir+5.127
Neg logit contributions
heid-11.893
hips-10.499
ertodd-10.349
 refrain-9.592
olini-9.054
Token).
Token ID737
Feature activation+1.92e-01

Pos logit contributions
heid+0.359
hips+0.309
ertodd+0.300
 refrain+0.277
olini+0.255
Neg logit contributions
cember-0.336
isphere-0.329
nir-0.326
andum-0.320
asar-0.319
Token Near
Token ID20173
Feature activation-7.38e-01

Pos logit contributions
cember+0.476
isphere+0.466
nir+0.459
andum+0.453
asar+0.450
Neg logit contributions
heid-0.532
hips-0.459
ertodd-0.444
 refrain-0.414
olini-0.381
Token those
Token ID883
Feature activation+3.46e-01

Pos logit contributions
heid+1.865
hips+1.595
ertodd+1.520
 refrain+1.422
olini+1.289
Neg logit contributions
cember-1.995
isphere-1.953
nir-1.923
andum-1.908
asar-1.889
Token lighter
Token ID14871
Feature activation+5.71e-02

Pos logit contributions
cember+0.846
isphere+0.831
nir+0.820
andum+0.804
asar+0.803
Neg logit contributions
heid-0.965
hips-0.831
ertodd-0.811
 refrain-0.750
olini-0.694
Token to
Token ID284
Feature activation-9.11e-01

Pos logit contributions
heid+0.550
hips+0.477
ertodd+0.463
 refrain+0.431
olini+0.400
Neg logit contributions
cember-0.452
isphere-0.442
nir-0.436
andum-0.429
asar-0.427
Token pass
Token ID1208
Feature activation-8.17e-01

Pos logit contributions
heid+1.955
hips+1.625
ertodd+1.545
 refrain+1.427
olini+1.246
Neg logit contributions
cember-2.801
isphere-2.755
nir-2.727
andum-2.691
asar-2.680
Token into
Token ID656
Feature activation-5.49e-01

Pos logit contributions
heid+2.243
hips+1.944
ertodd+1.850
 refrain+1.762
olini+1.595
Neg logit contributions
cember-2.029
isphere-1.987
nir-1.952
andum-1.935
asar-1.914
Token the
Token ID262
Feature activation-7.42e-02

Pos logit contributions
heid+1.409
hips+1.200
ertodd+1.156
 refrain+1.077
olini+0.978
Neg logit contributions
cember-1.465
isphere-1.438
nir-1.420
andum-1.400
asar-1.394
Token eternal
Token ID15851
Feature activation-2.29e+00

Pos logit contributions
heid+0.198
hips+0.170
ertodd+0.163
 refrain+0.153
olini+0.140
Neg logit contributions
cember-0.191
isphere-0.186
nir-0.185
andum-0.182
asar-0.181
Token love
Token ID1842
Feature activation-3.76e+00

Pos logit contributions
heid+5.739
hips+4.881
 refrain+4.609
ertodd+4.408
olini+3.906
Neg logit contributions
cember-5.958
isphere-5.874
nir-5.814
asar-5.765
utics-5.753
Token of
Token ID286
Feature activation+2.92e-01

Pos logit contributions
heid+8.482
hips+7.465
ertodd+6.590
 refrain+6.480
olini+5.591
Neg logit contributions
cember-10.516
isphere-10.167
nir-10.144
asar-9.926
andum-9.866
Token God
Token ID1793
Feature activation+5.12e-01

Pos logit contributions
cember+0.745
isphere+0.728
nir+0.721
andum+0.711
asar+0.706
Neg logit contributions
heid-0.785
hips-0.672
ertodd-0.654
 refrain-0.601
olini-0.555
Token,"
Token ID553
Feature activation-2.84e-01

Pos logit contributions
cember+1.258
isphere+1.233
nir+1.217
andum+1.197
asar+1.195
Neg logit contributions
heid-1.412
hips-1.212
ertodd-1.196
 refrain-1.092
olini-1.013
Token reads
Token ID9743
Feature activation-6.03e-01

Pos logit contributions
heid+0.734
hips+0.626
ertodd+0.606
 refrain+0.559
olini+0.512
Neg logit contributions
cember-0.753
isphere-0.738
nir-0.730
andum-0.719
asar-0.716
Token the
Token ID262
Feature activation+9.72e-02

Pos logit contributions
heid+1.568
hips+1.340
ertodd+1.292
 refrain+1.203
olini+1.096
Neg logit contributions
cember-1.588
isphere-1.558
nir-1.536
andum-1.513
asar-1.511
Token by
Token ID416
Feature activation+6.72e-01

Pos logit contributions
cember+0.431
isphere+0.422
nir+0.417
andum+0.410
asar+0.409
Neg logit contributions
heid-0.477
hips-0.411
ertodd-0.398
 refrain-0.371
olini-0.341
Token suicide
Token ID7341
Feature activation+6.66e-01

Pos logit contributions
cember+1.535
isphere+1.496
nir+1.482
andum+1.447
asar+1.445
Neg logit contributions
heid-1.983
hips-1.719
ertodd-1.676
 refrain-1.542
olini-1.449
Token.
Token ID13
Feature activation+6.23e-01

Pos logit contributions
cember+1.589
isphere+1.543
nir+1.529
istical+1.495
andum+1.491
Neg logit contributions
heid-1.891
hips-1.626
ertodd-1.609
 refrain-1.472
olini-1.369
Token Cambridge
Token ID14457
Feature activation-3.41e-01

Pos logit contributions
cember+1.632
isphere+1.595
nir+1.580
andum+1.562
asar+1.558
Neg logit contributions
heid-1.608
hips-1.373
ertodd-1.363
 refrain-1.232
olini-1.134
Token,
Token ID11
Feature activation-1.33e+00

Pos logit contributions
heid+0.965
hips+0.836
ertodd+0.810
 refrain+0.756
olini+0.698
Neg logit contributions
cember-0.820
isphere-0.802
nir-0.792
andum-0.779
asar-0.776
Token MA
Token ID8779
Feature activation-3.42e+00

Pos logit contributions
heid+3.385
hips+2.923
ertodd+2.714
 refrain+2.597
olini+2.331
Neg logit contributions
cember-3.532
isphere-3.511
nir-3.437
asar-3.409
andum-3.389
Token:
Token ID25
Feature activation-7.62e-01

Pos logit contributions
heid+8.495
hips+7.328
ertodd+6.938
 refrain+6.508
creen+5.876
Neg logit contributions
isphere-8.622
cember-8.585
nir-8.494
istical-8.307
andum-8.305
Token Harvard
Token ID11131
Feature activation-1.38e+00

Pos logit contributions
heid+1.820
hips+1.537
ertodd+1.453
 refrain+1.360
olini+1.222
Neg logit contributions
cember-2.172
isphere-2.138
nir-2.111
asar-2.081
andum-2.074
Token University
Token ID2059
Feature activation-9.28e-01

Pos logit contributions
heid+3.315
hips+2.866
ertodd+2.649
 refrain+2.505
olini+2.246
Neg logit contributions
cember-3.890
isphere-3.808
nir-3.747
asar-3.683
andum-3.681
Token Press
Token ID4332
Feature activation-1.09e-01

Pos logit contributions
heid+2.285
hips+1.949
ertodd+1.838
 refrain+1.714
olini+1.554
Neg logit contributions
cember-2.564
isphere-2.522
nir-2.487
andum-2.453
asar-2.444
Token;
Token ID26
Feature activation-8.78e-01

Pos logit contributions
heid+0.327
hips+0.285
ertodd+0.279
 refrain+0.261
olini+0.242
Neg logit contributions
cember-0.241
isphere-0.234
nir-0.232
andum-0.228
asar-0.226
Tokentwitter
Token ID6956
Feature activation-1.96e-01

Pos logit contributions
heid+4.405
hips+4.010
ertodd+3.862
 refrain+3.653
olini+3.509
Neg logit contributions
cember-1.354
isphere-1.291
nir-1.199
andum-1.168
istical-1.147
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
heid+0.527
hips+0.455
ertodd+0.437
 refrain+0.406
olini+0.372
Neg logit contributions
cember-0.501
isphere-0.491
nir-0.482
andum-0.476
asar-0.472
Tokencom
Token ID785
Feature activation-8.49e-01

Pos logit contributions
heid+3.191
hips+2.755
ertodd+2.566
 refrain+2.374
olini+2.210
Neg logit contributions
cember-3.293
isphere-3.194
nir-3.078
andum-3.077
istical-3.050
Token/
Token ID14
Feature activation-7.78e-01

Pos logit contributions
heid+2.137
hips+1.842
ertodd+1.719
 refrain+1.602
olini+1.449
Neg logit contributions
cember-2.336
isphere-2.292
nir-2.225
andum-2.212
asar-2.189
TokenO
Token ID46
Feature activation-1.62e+00

Pos logit contributions
heid+2.222
hips+1.939
ertodd+1.848
 refrain+1.711
olini+1.611
Neg logit contributions
cember-1.843
isphere-1.796
nir-1.749
andum-1.748
istical-1.736
TokenJV
Token ID41697
Feature activation-3.38e+00

Pos logit contributions
heid+4.611
hips+4.044
ertodd+3.808
 refrain+3.506
olini+3.334
Neg logit contributions
cember-3.786
isphere-3.688
andum-3.591
nir-3.588
istical-3.562
TokenL
Token ID43
Feature activation-2.34e+00

Pos logit contributions
heid+9.260
hips+8.157
ertodd+7.453
 refrain+6.788
olini+6.703
Neg logit contributions
cember-7.484
isphere-7.168
andum-7.025
istical-6.988
utics-6.875
TokenF
Token ID37
Feature activation-1.40e+00

Pos logit contributions
heid+6.560
hips+5.767
ertodd+5.325
 refrain+4.859
olini+4.709
Neg logit contributions
cember-5.415
isphere-5.236
andum-5.115
istical-5.097
asar-5.021
TokenRe
Token ID3041
Feature activation-5.85e-01

Pos logit contributions
heid+4.015
hips+3.516
ertodd+3.296
 refrain+3.039
olini+2.891
Neg logit contributions
cember-3.285
isphere-3.186
andum-3.104
istical-3.091
nir-3.086
TokenK
Token ID42
Feature activation-1.71e+00

Pos logit contributions
heid+1.684
hips+1.469
ertodd+1.401
 refrain+1.302
olini+1.226
Neg logit contributions
cember-1.373
isphere-1.339
nir-1.308
andum-1.302
istical-1.291
Tokench
Token ID354
Feature activation-5.68e-01

Pos logit contributions
heid+4.811
hips+4.217
ertodd+3.953
 refrain+3.630
olini+3.465
Neg logit contributions
cember-4.032
isphere-3.907
andum-3.803
istical-3.786
nir-3.753
Token high
Token ID1029
Feature activation-5.69e-01

Pos logit contributions
heid+1.496
hips+1.263
ertodd+1.201
 refrain+1.122
olini+1.007
Neg logit contributions
cember-1.776
isphere-1.743
nir-1.723
andum-1.698
asar-1.697
Token school
Token ID1524
Feature activation-6.40e-01

Pos logit contributions
heid+1.037
hips+0.823
ertodd+0.778
 refrain+0.691
olini+0.592
Neg logit contributions
cember-1.939
isphere-1.911
nir-1.893
andum-1.873
asar-1.866
Token ball
Token ID2613
Feature activation+4.53e-01

Pos logit contributions
heid+1.625
hips+1.386
ertodd+1.327
 refrain+1.237
olini+1.120
Neg logit contributions
cember-1.725
isphere-1.690
nir-1.671
andum-1.651
asar-1.644
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
cember+1.131
isphere+1.105
nir+1.091
andum+1.072
asar+1.071
Neg logit contributions
heid-1.242
hips-1.074
ertodd-1.046
 refrain-0.958
olini-0.888
Token the
Token ID262
Feature activation-6.65e-01

Pos logit contributions
heid+2.656
hips+2.254
ertodd+2.138
 refrain+2.021
olini+1.812
Neg logit contributions
cember-3.056
isphere-2.984
nir-2.942
andum-2.906
asar-2.900
Token love
Token ID1842
Feature activation-3.34e+00

Pos logit contributions
heid+1.721
hips+1.472
ertodd+1.406
 refrain+1.348
olini+1.206
Neg logit contributions
cember-1.748
isphere-1.714
nir-1.690
andum-1.662
asar-1.660
Token of
Token ID286
Feature activation+2.00e-01

Pos logit contributions
heid+7.828
hips+6.967
ertodd+6.275
 refrain+6.252
olini+5.512
Neg logit contributions
cember-8.926
nir-8.690
isphere-8.665
asar-8.490
andum-8.386
Token English
Token ID3594
Feature activation+4.36e-01

Pos logit contributions
cember+0.559
isphere+0.550
nir+0.545
andum+0.537
asar+0.534
Neg logit contributions
heid-0.489
hips-0.411
ertodd-0.400
 refrain-0.362
olini-0.330
Token he
Token ID339
Feature activation-1.48e-01

Pos logit contributions
cember+1.143
isphere+1.124
nir+1.106
andum+1.089
asar+1.088
Neg logit contributions
heid-1.133
hips-0.966
ertodd-0.951
 refrain-0.860
olini-0.793
Token acquired
Token ID9477
Feature activation+7.85e-01

Pos logit contributions
heid+0.407
hips+0.351
ertodd+0.340
 refrain+0.316
olini+0.291
Neg logit contributions
cember-0.368
isphere-0.360
nir-0.356
andum-0.350
asar-0.349
Token in
Token ID287
Feature activation+3.28e-01

Pos logit contributions
cember+1.958
isphere+1.911
nir+1.882
andum+1.856
asar+1.849
Neg logit contributions
heid-2.139
hips-1.819
ertodd-1.791
 refrain-1.648
olini-1.527
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
cember+0.700
isphere+0.680
nir+0.669
asar+0.663
andum+0.660
Neg logit contributions
heid-0.918
hips-0.794
ertodd-0.775
 refrain-0.714
olini-0.680
Token drive
Token ID3708
Feature activation-1.66e-01

Pos logit contributions
heid+2.235
hips+1.850
ertodd+1.745
 refrain+1.616
olini+1.380
Neg logit contributions
cember-3.484
isphere-3.422
nir-3.383
andum-3.338
asar-3.322
Token with
Token ID351
Feature activation+1.17e-01

Pos logit contributions
heid+0.453
hips+0.391
ertodd+0.378
 refrain+0.352
olini+0.323
Neg logit contributions
cember-0.416
isphere-0.408
nir-0.402
andum-0.396
asar-0.394
Token an
Token ID281
Feature activation-3.59e-01

Pos logit contributions
cember+0.292
isphere+0.285
nir+0.282
andum+0.278
asar+0.277
Neg logit contributions
heid-0.319
hips-0.275
ertodd-0.267
 refrain-0.247
olini-0.228
Token ignition
Token ID37594
Feature activation-3.21e-02

Pos logit contributions
heid+1.011
hips+0.868
ertodd+0.842
 refrain+0.791
olini+0.732
Neg logit contributions
cember-0.874
isphere-0.852
nir-0.845
andum-0.827
istical-0.823
Token inter
Token ID987
Feature activation-3.30e+00

Pos logit contributions
heid+0.058
hips+0.046
ertodd+0.044
 refrain+0.038
olini+0.033
Neg logit contributions
cember-0.110
isphere-0.108
nir-0.107
andum-0.106
asar-0.106
Tokenlock
Token ID5354
Feature activation-1.90e+00

Pos logit contributions
heid+6.635
hips+5.192
 refrain+4.482
ertodd+4.356
olini+4.084
Neg logit contributions
cember-10.312
utics-9.707
istical-9.699
andum-9.676
isphere-9.479
Token device
Token ID3335
Feature activation+3.31e-01

Pos logit contributions
heid+4.356
hips+3.630
ertodd+3.381
 refrain+3.338
creen+2.897
Neg logit contributions
cember-5.521
isphere-5.290
nir-5.254
andum-5.201
utics-5.189
Token.
Token ID13
Feature activation-6.29e-01

Pos logit contributions
cember+0.822
isphere+0.808
nir+0.798
andum+0.786
asar+0.785
Neg logit contributions
heid-0.906
hips-0.778
ertodd-0.760
 refrain-0.698
olini-0.647
Token
Token ID198
Feature activation-1.13e-01

Pos logit contributions
heid+1.660
hips+1.424
ertodd+1.367
 refrain+1.271
olini+1.161
Neg logit contributions
cember-1.641
isphere-1.607
nir-1.579
andum-1.557
asar-1.542
Token
Token ID198
Feature activation+5.87e-01

Pos logit contributions
heid+0.297
hips+0.255
ertodd+0.244
 refrain+0.227
olini+0.207
Neg logit contributions
cember-0.297
isphere-0.291
nir-0.286
andum-0.283
asar-0.280
Token civil
Token ID3026
Feature activation-5.71e-01

Pos logit contributions
heid+1.248
hips+1.062
ertodd+1.023
 refrain+0.949
olini+0.861
Neg logit contributions
cember-1.326
isphere-1.301
nir-1.287
andum-1.265
asar-1.262
Token-
Token ID12
Feature activation+1.29e+00

Pos logit contributions
heid+1.524
hips+1.304
ertodd+1.235
 refrain+1.175
olini+1.055
Neg logit contributions
cember-1.488
isphere-1.438
nir-1.433
andum-1.408
asar-1.391
Tokenrights
Token ID28046
Feature activation-1.62e-01

Pos logit contributions
cember+1.410
isphere+1.378
nir+1.368
asar+1.325
andum+1.280
Neg logit contributions
heid-5.205
ertodd-4.764
hips-4.702
 refrain-4.527
olini-4.324
Token office
Token ID2607
Feature activation+1.16e-01

Pos logit contributions
heid+0.375
hips+0.313
ertodd+0.303
 refrain+0.275
olini+0.249
Neg logit contributions
cember-0.472
isphere-0.464
nir-0.458
andum-0.453
asar-0.452
Token has
Token ID468
Feature activation-1.64e-01

Pos logit contributions
cember+0.283
isphere+0.277
nir+0.273
andum+0.270
asar+0.268
Neg logit contributions
heid-0.324
hips-0.280
ertodd-0.271
 refrain-0.252
olini-0.234
Token long
Token ID890
Feature activation-3.30e+00

Pos logit contributions
heid+0.451
hips+0.390
ertodd+0.376
 refrain+0.352
olini+0.321
Neg logit contributions
cember-0.409
isphere-0.400
nir-0.395
andum-0.389
asar-0.387
Token been
Token ID587
Feature activation-2.60e+00

Pos logit contributions
heid+8.328
hips+7.319
ertodd+6.855
 refrain+6.799
 practice+5.769
Neg logit contributions
cember-8.165
isphere-7.944
andum-7.767
nir-7.756
asar-7.660
Token criticized
Token ID12318
Feature activation-1.04e+00

Pos logit contributions
heid+7.389
hips+6.625
ertodd+6.092
 refrain+6.072
olini+5.369
Neg logit contributions
cember-5.796
isphere-5.653
nir-5.454
andum-5.402
asar-5.348
Token for
Token ID329
Feature activation-6.07e-02

Pos logit contributions
heid+2.601
hips+2.224
ertodd+2.132
 refrain+1.974
olini+1.790
Neg logit contributions
cember-2.840
isphere-2.783
nir-2.756
andum-2.714
asar-2.699
Token failing
Token ID9894
Feature activation-9.77e-01

Pos logit contributions
heid+0.150
hips+0.127
ertodd+0.123
 refrain+0.112
olini+0.103
Neg logit contributions
cember-0.167
isphere-0.165
nir-0.163
andum-0.161
asar-0.160
Token to
Token ID284
Feature activation-1.07e+00

Pos logit contributions
heid+2.849
hips+2.480
ertodd+2.407
 refrain+2.249
olini+2.085
Neg logit contributions
cember-2.266
isphere-2.215
nir-2.186
andum-2.151
asar-2.141
Token dramatic
Token ID10092
Feature activation+1.29e+00

Pos logit contributions
heid+1.521
hips+1.289
ertodd+1.238
 refrain+1.151
olini+1.038
Neg logit contributions
cember-1.713
isphere-1.682
nir-1.662
andum-1.641
asar-1.632
Token experiences
Token ID6461
Feature activation-8.59e-01

Pos logit contributions
cember+3.511
isphere+3.440
nir+3.415
asar+3.372
istical+3.369
Neg logit contributions
heid-3.154
ertodd-2.680
hips-2.630
 refrain-2.269
olini-2.155
Token of
Token ID286
Feature activation+5.81e-01

Pos logit contributions
heid+2.191
hips+1.881
ertodd+1.796
 refrain+1.674
olini+1.520
Neg logit contributions
cember-2.297
isphere-2.248
nir-2.226
andum-2.195
asar-2.179
Token betrayal
Token ID29355
Feature activation-1.64e+00

Pos logit contributions
cember+1.468
isphere+1.444
nir+1.430
asar+1.408
andum+1.394
Neg logit contributions
heid-1.575
hips-1.343
ertodd-1.312
 refrain-1.193
olini-1.115
Token,
Token ID11
Feature activation-8.85e-02

Pos logit contributions
heid+4.027
hips+3.518
ertodd+3.268
 refrain+3.096
olini+2.767
Neg logit contributions
cember-4.429
isphere-4.371
nir-4.318
andum-4.297
asar-4.208
Token love
Token ID1842
Feature activation-3.29e+00

Pos logit contributions
heid+0.233
hips+0.199
ertodd+0.193
 refrain+0.178
olini+0.164
Neg logit contributions
cember-0.230
isphere-0.226
nir-0.223
andum-0.219
asar-0.219
Token,
Token ID11
Feature activation+2.97e-01

Pos logit contributions
heid+7.263
hips+6.320
ertodd+5.679
 refrain+5.540
olini+4.871
Neg logit contributions
cember-9.140
isphere-9.096
nir-8.982
andum-8.804
asar-8.790
Token disappointment
Token ID18641
Feature activation-1.90e-01

Pos logit contributions
cember+0.829
isphere+0.812
nir+0.807
asar+0.793
andum+0.790
Neg logit contributions
heid-0.728
hips-0.610
ertodd-0.599
 refrain-0.538
olini-0.497
Token,
Token ID11
Feature activation+3.99e-01

Pos logit contributions
heid+0.488
hips+0.413
ertodd+0.404
 refrain+0.370
olini+0.340
Neg logit contributions
cember-0.506
isphere-0.494
nir-0.490
andum-0.482
asar-0.481
Token empowerment
Token ID39309
Feature activation+6.62e-01

Pos logit contributions
cember+1.103
isphere+1.079
nir+1.075
asar+1.053
andum+1.050
Neg logit contributions
heid-0.991
hips-0.830
ertodd-0.819
 refrain-0.732
olini-0.680
Token and
Token ID290
Feature activation+6.55e-01

Pos logit contributions
cember+1.733
isphere+1.688
nir+1.679
istical+1.651
asar+1.651
Neg logit contributions
heid-1.724
hips-1.452
ertodd-1.433
 refrain-1.303
olini-1.215
Token function
Token ID2163
Feature activation+7.05e-01

Pos logit contributions
cember+0.018
isphere+0.017
nir+0.017
andum+0.017
asar+0.017
Neg logit contributions
heid-0.018
hips-0.015
ertodd-0.015
 refrain-0.014
olini-0.012
Token.
Token ID13
Feature activation-2.66e-01

Pos logit contributions
cember+1.732
isphere+1.702
nir+1.681
andum+1.648
asar+1.644
Neg logit contributions
heid-1.950
hips-1.675
ertodd-1.641
 refrain-1.511
olini-1.407
Token
Token ID198
Feature activation-1.24e-01

Pos logit contributions
heid+0.709
hips+0.610
ertodd+0.587
 refrain+0.548
olini+0.499
Neg logit contributions
cember-0.682
isphere-0.667
nir-0.659
andum-0.650
asar-0.646
Token
Token ID198
Feature activation+5.65e-01

Pos logit contributions
heid+0.324
hips+0.279
ertodd+0.267
 refrain+0.248
olini+0.226
Neg logit contributions
cember-0.327
isphere-0.320
nir-0.315
andum-0.311
asar-0.308
Token(*
Token ID46491
Feature activation-1.20e+00

Pos logit contributions
cember+1.204
isphere+1.175
nir+1.163
andum+1.136
asar+1.132
Neg logit contributions
heid-1.748
hips-1.533
ertodd-1.500
 refrain-1.409
olini-1.312
Token join
Token ID4654
Feature activation-3.28e+00

Pos logit contributions
heid+3.116
hips+2.666
ertodd+2.543
 refrain+2.430
olini+2.152
Neg logit contributions
cember-3.133
isphere-3.061
nir-3.018
andum-2.986
asar-2.970
Token each
Token ID1123
Feature activation+4.67e-03

Pos logit contributions
heid+8.369
hips+7.348
 refrain+6.657
ertodd+6.562
 membership+5.779
Neg logit contributions
cember-7.995
isphere-7.508
nir-7.347
andum-7.338
asar-7.329
Token element
Token ID5002
Feature activation+2.24e-01

Pos logit contributions
cember+0.012
isphere+0.012
nir+0.012
andum+0.012
asar+0.012
Neg logit contributions
heid-0.012
hips-0.011
ertodd-0.010
 refrain-0.009
olini-0.009
Token of
Token ID286
Feature activation+4.09e-01

Pos logit contributions
cember+0.580
isphere+0.569
nir+0.562
andum+0.554
asar+0.551
Neg logit contributions
heid-0.593
hips-0.509
ertodd-0.492
 refrain-0.456
olini-0.418
Token `
Token ID4600
Feature activation+6.57e-01

Pos logit contributions
cember+1.043
isphere+1.023
nir+1.015
andum+0.998
asar+0.995
Neg logit contributions
heid-1.093
hips-0.936
ertodd-0.913
 refrain-0.836
olini-0.778
Tokense
Token ID325
Feature activation+1.68e+00

Pos logit contributions
cember+1.452
isphere+1.415
nir+1.413
asar+1.373
andum+1.370
Neg logit contributions
heid-1.979
hips-1.726
ertodd-1.701
 refrain-1.591
olini-1.479
Token of
Token ID286
Feature activation+3.90e-01

Pos logit contributions
heid+0.546
hips+0.466
ertodd+0.454
 refrain+0.420
olini+0.390
Neg logit contributions
cember-0.493
isphere-0.486
nir-0.475
andum-0.470
istical-0.470
Token this
Token ID428
Feature activation+7.01e-01

Pos logit contributions
cember+0.973
isphere+0.955
nir+0.943
andum+0.931
istical+0.923
Neg logit contributions
heid-1.066
hips-0.913
ertodd-0.889
 refrain-0.819
olini-0.762
Token is
Token ID318
Feature activation-2.89e-01

Pos logit contributions
cember+1.878
isphere+1.844
nir+1.823
andum+1.791
ause+1.784
Neg logit contributions
heid-1.770
hips-1.490
ertodd-1.469
 refrain-1.315
olini-1.232
Token to
Token ID284
Feature activation-1.22e+00

Pos logit contributions
heid+0.833
hips+0.724
ertodd+0.703
 refrain+0.656
olini+0.608
Neg logit contributions
cember-0.677
isphere-0.662
nir-0.653
andum-0.643
asar-0.640
Token highlight
Token ID7238
Feature activation-3.22e-01

Pos logit contributions
heid+2.749
hips+2.346
ertodd+2.199
 refrain+2.092
olini+1.814
Neg logit contributions
cember-3.583
isphere-3.520
nir-3.458
andum-3.425
asar-3.418
Token INTER
Token ID23255
Feature activation-3.27e+00

Pos logit contributions
heid+0.861
hips+0.743
ertodd+0.714
 refrain+0.668
olini+0.610
Neg logit contributions
cember-0.826
isphere-0.807
nir-0.796
andum-0.785
asar-0.783
TokenM
Token ID44
Feature activation-8.42e-01

Pos logit contributions
heid+8.643
hips+7.660
ertodd+7.012
 refrain+6.777
olini+6.179
Neg logit contributions
cember-7.737
isphere-7.585
asar-7.545
nir-7.524
andum-7.416
TokenITT
Token ID22470
Feature activation-9.68e-01

Pos logit contributions
heid+2.395
hips+2.093
ertodd+2.012
 refrain+1.897
olini+1.754
Neg logit contributions
cember-2.001
isphere-1.942
nir-1.935
asar-1.890
andum-1.877
TokenENT
Token ID3525
Feature activation-7.13e-01

Pos logit contributions
heid+2.558
hips+2.196
ertodd+2.109
 refrain+1.967
olini+1.801
Neg logit contributions
cember-2.513
isphere-2.458
nir-2.429
asar-2.389
andum-2.388
Token F
Token ID376
Feature activation-3.14e-01

Pos logit contributions
heid+1.968
hips+1.709
ertodd+1.631
 refrain+1.542
olini+1.406
Neg logit contributions
cember-1.769
isphere-1.733
nir-1.709
andum-1.685
asar-1.680
TokenAST
Token ID11262
Feature activation+3.16e-01

Pos logit contributions
heid+0.937
hips+0.820
ertodd+0.787
 refrain+0.742
olini+0.693
Neg logit contributions
cember-0.713
isphere-0.695
nir-0.684
andum-0.673
asar-0.670
Token A
Token ID317
Feature activation-2.89e-01

Pos logit contributions
heid+2.968
hips+2.521
ertodd+2.342
 refrain+2.255
olini+2.039
Neg logit contributions
cember-3.175
isphere-3.148
andum-3.052
nir-3.047
asar-3.017
TokenUS
Token ID2937
Feature activation-1.59e+00

Pos logit contributions
heid+0.632
hips+0.523
ertodd+0.490
 refrain+0.447
olini+0.399
Neg logit contributions
cember-0.887
isphere-0.873
nir-0.862
andum-0.853
asar-0.842
Token 16
Token ID1467
Feature activation-1.67e-01

Pos logit contributions
heid+3.751
hips+3.181
ertodd+3.029
 refrain+2.786
olini+2.524
Neg logit contributions
isphere-4.515
cember-4.512
nir-4.397
andum-4.357
asar-4.336
Token Steele
Token ID28549
Feature activation+1.86e-01

Pos logit contributions
heid+0.435
hips+0.373
ertodd+0.360
 refrain+0.333
olini+0.305
Neg logit contributions
cember-0.437
isphere-0.429
nir-0.424
andum-0.417
asar-0.416
Token Von
Token ID26985
Feature activation-2.05e+00

Pos logit contributions
cember+0.435
isphere+0.427
nir+0.421
andum+0.414
asar+0.412
Neg logit contributions
heid-0.537
hips-0.467
ertodd-0.452
 refrain-0.424
olini-0.393
Token Hoff
Token ID21890
Feature activation-3.27e+00

Pos logit contributions
heid+4.823
hips+3.877
ertodd+3.722
 refrain+3.338
olini+3.198
Neg logit contributions
isphere-5.906
cember-5.864
istical-5.695
andum-5.656
nir-5.634
Token (
Token ID357
Feature activation+5.72e-03

Pos logit contributions
heid+8.058
hips+6.607
ertodd+5.999
 refrain+5.648
olini+5.240
Neg logit contributions
isphere-8.707
cember-8.617
istical-8.516
andum-8.425
asar-8.212
TokenTeam
Token ID15592
Feature activation+9.86e-01

Pos logit contributions
cember+0.013
isphere+0.013
nir+0.013
andum+0.012
asar+0.012
Neg logit contributions
heid-0.017
hips-0.015
ertodd-0.014
 refrain-0.013
olini-0.012
Token Chip
Token ID17869
Feature activation+1.81e+00

Pos logit contributions
cember+2.429
isphere+2.378
nir+2.356
asar+2.321
istical+2.300
Neg logit contributions
heid-2.678
hips-2.350
ertodd-2.283
 refrain-2.088
olini-1.907
Tokenotle
Token ID23556
Feature activation+7.08e-01

Pos logit contributions
isphere+3.861
asar+3.834
nir+3.831
cember+3.826
utics+3.806
Neg logit contributions
heid-5.321
hips-4.688
ertodd-4.645
 refrain-4.319
creen-3.782
Token)
Token ID8
Feature activation-4.85e-01

Pos logit contributions
cember+1.679
nir+1.654
isphere+1.624
asar+1.605
andum+1.598
Neg logit contributions
heid-1.969
hips-1.708
ertodd-1.693
 refrain-1.538
olini-1.414
Token month
Token ID1227
Feature activation-2.37e-01

Pos logit contributions
cember+0.599
isphere+0.582
nir+0.573
andum+0.560
asar+0.559
Neg logit contributions
heid-0.936
hips-0.824
ertodd-0.805
 refrain-0.753
olini-0.709
Token.
Token ID13
Feature activation+7.09e-02

Pos logit contributions
heid+0.637
hips+0.550
ertodd+0.528
 refrain+0.494
olini+0.451
Neg logit contributions
cember-0.602
isphere-0.590
nir-0.582
andum-0.575
asar-0.571
Token
Token ID198
Feature activation-1.77e-01

Pos logit contributions
cember+0.182
isphere+0.179
nir+0.176
andum+0.174
asar+0.173
Neg logit contributions
heid-0.189
hips-0.162
ertodd-0.157
 refrain-0.146
olini-0.134
Token
Token ID198
Feature activation+6.54e-01

Pos logit contributions
heid+0.464
hips+0.398
ertodd+0.381
 refrain+0.355
olini+0.324
Neg logit contributions
cember-0.466
isphere-0.457
nir-0.448
andum-0.443
asar-0.439
TokenWith
Token ID3152
Feature activation+4.45e-01

Pos logit contributions
cember+1.475
isphere+1.442
nir+1.426
andum+1.399
asar+1.394
Neg logit contributions
heid-1.941
hips-1.694
ertodd-1.652
 refrain-1.545
olini-1.435
Token love
Token ID1842
Feature activation-3.26e+00

Pos logit contributions
cember+1.109
isphere+1.086
nir+1.074
andum+1.056
asar+1.052
Neg logit contributions
heid-1.218
hips-1.049
ertodd-1.018
 refrain-0.944
olini-0.870
Token and
Token ID290
Feature activation+7.41e-01

Pos logit contributions
heid+7.976
hips+6.894
ertodd+6.334
 refrain+6.106
olini+5.389
Neg logit contributions
cember-8.432
nir-8.300
isphere-8.283
andum-8.057
asar-8.020
Token light
Token ID1657
Feature activation+8.80e-01

Pos logit contributions
cember+1.931
isphere+1.888
nir+1.886
andum+1.844
asar+1.834
Neg logit contributions
heid-1.924
hips-1.632
ertodd-1.612
 refrain-1.438
olini-1.361
Token
Token ID198
Feature activation-4.00e-01

Pos logit contributions
cember+2.084
isphere+2.041
nir+2.024
asar+1.979
andum+1.974
Neg logit contributions
heid-2.456
ertodd-2.121
hips-2.112
 refrain-1.907
olini-1.808
Token
Token ID198
Feature activation+2.95e-01

Pos logit contributions
heid+1.028
hips+0.882
ertodd+0.835
 refrain+0.781
olini+0.707
Neg logit contributions
cember-1.082
isphere-1.059
nir-1.035
andum-1.025
asar-1.013
TokenGeorge
Token ID20191
Feature activation+2.97e-01

Pos logit contributions
cember+0.653
isphere+0.638
nir+0.630
andum+0.618
asar+0.616
Neg logit contributions
heid-0.889
hips-0.777
ertodd-0.756
 refrain-0.709
olini-0.659
Token battery
Token ID6555
Feature activation-4.96e-01

Pos logit contributions
heid+0.608
hips+0.526
ertodd+0.509
 refrain+0.477
olini+0.439
Neg logit contributions
cember-0.524
isphere-0.513
nir-0.506
andum-0.499
asar-0.495
Token.
Token ID13
Feature activation-5.35e-01

Pos logit contributions
heid+1.313
hips+1.127
ertodd+1.084
 refrain+1.014
olini+0.926
Neg logit contributions
cember-1.284
isphere-1.255
nir-1.239
andum-1.223
asar-1.214
Token<|endoftext|>
Token ID50256
Feature activation-1.04e+00

Pos logit contributions
heid+1.482
hips+1.281
ertodd+1.233
 refrain+1.155
olini+1.060
Neg logit contributions
cember-1.327
isphere-1.295
nir-1.272
andum-1.260
asar-1.250
TokenJ
Token ID41
Feature activation-9.63e-01

Pos logit contributions
heid+3.201
hips+2.817
ertodd+2.661
 refrain+2.487
olini+2.351
Neg logit contributions
cember-2.251
isphere-2.198
andum-2.132
nir-2.125
asar-2.098
TokenTA
Token ID5603
Feature activation-1.58e+00

Pos logit contributions
heid+3.006
hips+2.639
ertodd+2.560
 refrain+2.378
olini+2.255
Neg logit contributions
cember-2.029
isphere-1.993
nir-1.934
andum-1.905
istical-1.894
Token
Token ID851
Feature activation-3.23e+00

Pos logit contributions
heid+4.270
hips+3.670
ertodd+3.490
 refrain+3.318
olini+3.051
Neg logit contributions
cember-3.880
isphere-3.828
nir-3.776
andum-3.714
asar-3.683
Token Two
Token ID4930
Feature activation+1.29e-01

Pos logit contributions
heid+7.907
hips+6.803
ertodd+6.300
 refrain+6.032
olini+5.427
Neg logit contributions
cember-8.404
isphere-8.247
nir-7.862
andum-7.824
istical-7.759
Token photos
Token ID5205
Feature activation-7.10e-01

Pos logit contributions
cember+0.324
isphere+0.318
nir+0.314
andum+0.309
asar+0.308
Neg logit contributions
heid-0.351
hips-0.302
ertodd-0.293
 refrain-0.272
olini-0.251
Token tweeted
Token ID10830
Feature activation-3.85e-01

Pos logit contributions
heid+1.924
hips+1.666
ertodd+1.597
 refrain+1.495
olini+1.364
Neg logit contributions
cember-1.787
isphere-1.743
nir-1.734
andum-1.697
asar-1.694
Token as
Token ID355
Feature activation-3.42e-01

Pos logit contributions
heid+1.081
hips+0.941
ertodd+0.905
 refrain+0.849
olini+0.781
Neg logit contributions
cember-0.933
isphere-0.911
nir-0.901
andum-0.887
asar-0.883
Token being
Token ID852
Feature activation-4.57e-01

Pos logit contributions
heid+0.910
hips+0.781
ertodd+0.755
 refrain+0.700
olini+0.642
Neg logit contributions
cember-0.881
isphere-0.864
nir-0.853
andum-0.841
asar-0.837
Token '
Token ID705
Feature activation-6.80e-01

Pos logit contributions
cember+0.843
isphere+0.825
nir+0.815
andum+0.806
asar+0.802
Neg logit contributions
heid-0.855
hips-0.726
ertodd-0.712
 refrain-0.651
olini-0.600
TokenThe
Token ID464
Feature activation+6.82e-01

Pos logit contributions
heid+2.040
hips+1.796
ertodd+1.701
 refrain+1.622
olini+1.500
Neg logit contributions
cember-1.514
isphere-1.488
nir-1.442
andum-1.435
asar-1.415
Token Brotherhood
Token ID17987
Feature activation-6.40e-01

Pos logit contributions
cember+1.723
isphere+1.683
nir+1.666
andum+1.645
asar+1.635
Neg logit contributions
heid-1.844
hips-1.586
ertodd-1.542
 refrain-1.416
olini-1.308
Token of
Token ID286
Feature activation+6.36e-01

Pos logit contributions
heid+1.700
hips+1.471
ertodd+1.404
 refrain+1.315
olini+1.206
Neg logit contributions
cember-1.639
isphere-1.604
nir-1.589
andum-1.564
asar-1.552
Token Eternal
Token ID21475
Feature activation-1.83e+00

Pos logit contributions
cember+1.594
isphere+1.560
nir+1.557
andum+1.529
asar+1.510
Neg logit contributions
heid-1.724
hips-1.485
ertodd-1.451
 refrain-1.332
olini-1.237
Token Love
Token ID5896
Feature activation-3.22e+00

Pos logit contributions
heid+4.810
hips+4.163
ertodd+3.794
 refrain+3.715
 Sins+3.300
Neg logit contributions
cember-4.624
isphere-4.587
asar-4.470
andum-4.452
nir-4.424
Token:
Token ID25
Feature activation+6.37e-01

Pos logit contributions
heid+7.651
hips+6.898
ertodd+6.090
 refrain+5.744
creen+5.202
Neg logit contributions
cember-8.404
isphere-8.339
nir-8.124
asar-8.066
andum-7.945
Token From
Token ID3574
Feature activation-4.28e-01

Pos logit contributions
cember+1.625
isphere+1.591
nir+1.580
andum+1.562
asar+1.555
Neg logit contributions
heid-1.683
hips-1.434
ertodd-1.416
 refrain-1.294
olini-1.193
Token Flower
Token ID20025
Feature activation-9.99e-01

Pos logit contributions
heid+1.142
hips+0.982
ertodd+0.946
 refrain+0.881
olini+0.808
Neg logit contributions
cember-1.098
isphere-1.077
nir-1.060
andum-1.046
asar-1.042
Token Power
Token ID4333
Feature activation-8.83e-02

Pos logit contributions
heid+2.709
hips+2.360
ertodd+2.233
 refrain+2.076
olini+1.929
Neg logit contributions
cember-2.498
isphere-2.458
nir-2.429
asar-2.384
andum-2.380
Token to
Token ID284
Feature activation-3.37e-01

Pos logit contributions
heid+0.253
hips+0.220
ertodd+0.212
 refrain+0.199
olini+0.184
Neg logit contributions
cember-0.209
isphere-0.205
nir-0.202
andum-0.199
asar-0.198
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
heid+1.234
hips+1.064
ertodd+1.020
 refrain+0.953
olini+0.868
Neg logit contributions
cember-1.211
isphere-1.181
nir-1.165
andum-1.152
asar-1.147
Token<|endoftext|>
Token ID50256
Feature activation-9.49e-01

Pos logit contributions
cember+0.782
isphere+0.767
nir+0.760
andum+0.747
asar+0.745
Neg logit contributions
heid-0.833
hips-0.716
ertodd-0.696
 refrain-0.642
olini-0.593
TokenDec
Token ID10707
Feature activation-5.68e-01

Pos logit contributions
heid+2.917
hips+2.567
ertodd+2.430
 refrain+2.274
olini+2.144
Neg logit contributions
cember-2.050
isphere-2.003
andum-1.942
nir-1.937
asar-1.913
Token 2
Token ID362
Feature activation-1.61e+00

Pos logit contributions
heid+1.653
hips+1.443
ertodd+1.387
 refrain+1.287
olini+1.203
Neg logit contributions
cember-1.304
isphere-1.288
nir-1.269
andum-1.241
asar-1.238
Token,
Token ID11
Feature activation-1.44e+00

Pos logit contributions
heid+4.253
hips+3.660
ertodd+3.455
 refrain+3.255
olini+2.950
Neg logit contributions
isphere-4.093
cember-4.085
nir-3.959
asar-3.915
andum-3.896
Token 2015
Token ID1853
Feature activation-3.21e+00

Pos logit contributions
heid+3.495
hips+2.987
ertodd+2.762
 refrain+2.656
olini+2.355
Neg logit contributions
cember-3.994
isphere-3.988
nir-3.880
andum-3.847
asar-3.789
Token
Token ID784
Feature activation-2.05e+00

Pos logit contributions
heid+7.368
hips+6.230
ertodd+5.665
 refrain+5.643
 membership+4.754
Neg logit contributions
cember-8.818
isphere-8.620
asar-8.352
istical-8.256
andum-8.172
Token Cycl
Token ID28007
Feature activation+7.16e-01

Pos logit contributions
heid+5.247
hips+4.562
ertodd+4.229
 refrain+4.066
olini+3.664
Neg logit contributions
cember-5.363
isphere-5.265
nir-5.105
andum-5.059
asar-5.016
Tokenoc
Token ID420
Feature activation-1.31e+00

Pos logit contributions
cember+1.414
isphere+1.386
nir+1.363
andum+1.336
istical+1.331
Neg logit contributions
heid-2.325
hips-2.052
ertodd-2.003
 refrain-1.895
olini-1.751
Tokenross
Token ID1214
Feature activation-4.94e-01

Pos logit contributions
heid+3.803
hips+3.360
ertodd+3.209
 refrain+2.999
olini+2.841
Neg logit contributions
cember-2.955
isphere-2.891
nir-2.840
istical-2.800
andum-2.798
Token hurts
Token ID20406
Feature activation-1.87e+00

Pos logit contributions
heid+1.334
hips+1.149
ertodd+1.102
 refrain+1.031
olini+0.951
Neg logit contributions
cember-1.252
isphere-1.225
nir-1.210
andum-1.197
asar-1.190
Token whether
Token ID1771
Feature activation-5.37e-01

Pos logit contributions
heid+3.246
hips+2.842
ertodd+2.695
 refrain+2.570
olini+2.308
Neg logit contributions
cember-3.269
isphere-3.188
nir-3.141
andum-3.104
istical-3.073
Token the
Token ID262
Feature activation-6.31e-01

Pos logit contributions
heid+1.375
hips+1.171
ertodd+1.132
 refrain+1.045
olini+0.955
Neg logit contributions
cember-1.435
isphere-1.407
nir-1.391
andum-1.371
asar-1.366
Token states
Token ID2585
Feature activation-6.97e-01

Pos logit contributions
heid+1.634
hips+1.406
ertodd+1.348
 refrain+1.264
olini+1.148
Neg logit contributions
cember-1.663
isphere-1.632
nir-1.610
andum-1.588
asar-1.582
Token have
Token ID423
Feature activation-3.26e-01

Pos logit contributions
heid+1.673
hips+1.409
ertodd+1.357
 refrain+1.245
olini+1.128
Neg logit contributions
cember-1.974
isphere-1.938
nir-1.917
andum-1.891
asar-1.884
Token a
Token ID257
Feature activation-7.04e-01

Pos logit contributions
heid+0.909
hips+0.788
ertodd+0.758
 refrain+0.712
olini+0.652
Neg logit contributions
cember-0.802
isphere-0.782
nir-0.771
andum-0.760
asar-0.755
Token co
Token ID763
Feature activation-3.21e+00

Pos logit contributions
heid+1.904
hips+1.638
ertodd+1.571
 refrain+1.487
olini+1.348
Neg logit contributions
cember-1.785
isphere-1.747
nir-1.718
andum-1.697
asar-1.686
Token-
Token ID12
Feature activation-1.39e+00

Pos logit contributions
heid+8.179
hips+7.046
ertodd+6.580
 refrain+6.015
olini+5.472
Neg logit contributions
cember-8.199
isphere-8.096
istical-7.789
asar-7.752
andum-7.666
Tokenop
Token ID404
Feature activation-1.78e+00

Pos logit contributions
heid+4.207
hips+3.671
ertodd+3.469
 refrain+3.320
olini+3.044
Neg logit contributions
cember-3.137
isphere-3.040
andum-2.914
nir-2.906
istical-2.889
Token option
Token ID3038
Feature activation-2.46e-01

Pos logit contributions
heid+4.325
hips+3.633
ertodd+3.411
 refrain+3.265
olini+2.868
Neg logit contributions
cember-5.027
isphere-4.836
andum-4.784
nir-4.758
asar-4.692
Token.
Token ID13
Feature activation-7.88e-01

Pos logit contributions
heid+0.650
hips+0.559
ertodd+0.538
 refrain+0.500
olini+0.458
Neg logit contributions
cember-0.636
isphere-0.622
nir-0.614
andum-0.606
asar-0.603
Token Bob
Token ID5811
Feature activation-1.34e+00

Pos logit contributions
heid+2.046
hips+1.766
ertodd+1.672
 refrain+1.569
olini+1.427
Neg logit contributions
cember-2.099
isphere-2.048
nir-1.997
andum-1.978
asar-1.972
Token was
Token ID373
Feature activation-6.32e-01

Pos logit contributions
heid+1.007
hips+0.860
ertodd+0.827
 refrain+0.769
olini+0.703
Neg logit contributions
cember-1.001
isphere-0.979
nir-0.970
andum-0.956
asar-0.949
Token sent
Token ID1908
Feature activation-2.37e-01

Pos logit contributions
heid+1.688
hips+1.465
ertodd+1.395
 refrain+1.308
olini+1.196
Neg logit contributions
cember-1.606
isphere-1.564
nir-1.554
andum-1.532
istical-1.522
Token from
Token ID422
Feature activation-7.35e-01

Pos logit contributions
heid+0.651
hips+0.570
ertodd+0.546
 refrain+0.508
olini+0.467
Neg logit contributions
cember-0.586
isphere-0.570
nir-0.564
andum-0.555
ause-0.550
Token Russia
Token ID3284
Feature activation+6.32e-01

Pos logit contributions
heid+1.885
hips+1.630
ertodd+1.546
 refrain+1.451
olini+1.320
Neg logit contributions
cember-1.945
isphere-1.911
nir-1.882
andum-1.853
istical-1.840
Token with
Token ID351
Feature activation+6.19e-01

Pos logit contributions
cember+1.500
isphere+1.468
nir+1.449
andum+1.426
asar+1.420
Neg logit contributions
heid-1.808
hips-1.566
ertodd-1.521
 refrain-1.420
olini-1.313
Token Love
Token ID5896
Feature activation-3.20e+00

Pos logit contributions
cember+1.509
isphere+1.475
nir+1.455
andum+1.440
asar+1.432
Neg logit contributions
heid-1.720
hips-1.479
ertodd-1.443
 refrain-1.331
olini-1.237
Token.
Token ID13
Feature activation-1.22e-01

Pos logit contributions
heid+8.514
hips+7.369
ertodd+6.942
 refrain+6.679
olini+6.305
Neg logit contributions
cember-7.352
isphere-7.289
nir-7.151
ause-7.089
asar-7.088
Token L
Token ID406
Feature activation-1.01e+00

Pos logit contributions
heid+0.332
hips+0.286
ertodd+0.277
 refrain+0.257
olini+0.237
Neg logit contributions
cember-0.306
isphere-0.300
nir-0.296
andum-0.292
asar-0.291
Tokenaid
Token ID1698
Feature activation+1.27e-01

Pos logit contributions
heid+3.114
hips+2.760
ertodd+2.638
 refrain+2.457
olini+2.318
Neg logit contributions
cember-2.156
isphere-2.114
nir-2.075
andum-2.040
asar-2.024
Token on
Token ID319
Feature activation-3.86e-01

Pos logit contributions
cember+0.291
isphere+0.284
nir+0.281
andum+0.276
asar+0.275
Neg logit contributions
heid-0.372
hips-0.323
ertodd-0.315
 refrain-0.294
olini-0.273
Token cloth
Token ID16270
Feature activation+9.39e-01

Pos logit contributions
heid+1.039
hips+0.896
ertodd+0.863
 refrain+0.806
olini+0.737
Neg logit contributions
cember-0.979
isphere-0.962
nir-0.947
andum-0.934
asar-0.930
Token.
Token ID13
Feature activation+7.84e-01

Pos logit contributions
cember+1.290
isphere+1.266
nir+1.251
andum+1.231
asar+1.227
Neg logit contributions
heid-1.380
hips-1.177
ertodd-1.146
 refrain-1.061
olini-0.975
Token
Token ID198
Feature activation+5.75e-01

Pos logit contributions
cember+1.951
isphere+1.906
nir+1.897
andum+1.865
asar+1.860
Neg logit contributions
heid-2.126
hips-1.823
ertodd-1.780
 refrain-1.649
olini-1.514
Token
Token ID198
Feature activation+1.05e+00

Pos logit contributions
cember+1.421
isphere+1.394
nir+1.384
asar+1.360
andum+1.360
Neg logit contributions
heid-1.568
hips-1.348
ertodd-1.318
 refrain-1.222
olini-1.127
TokenC
Token ID34
Feature activation+1.90e+00

Pos logit contributions
cember+2.337
isphere+2.289
nir+2.275
andum+2.227
asar+2.218
Neg logit contributions
heid-3.088
hips-2.685
ertodd-2.647
 refrain-2.475
olini-2.287
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
cember+4.115
isphere+4.020
ause+4.000
nir+3.943
asar+3.930
Neg logit contributions
heid-5.578
ertodd-4.820
hips-4.738
 refrain-4.534
olini-4.115
TokenK
Token ID42
Feature activation-3.18e+00

Pos logit contributions
heid+4.697
hips+4.140
ertodd+3.821
 refrain+3.818
olini+3.445
Neg logit contributions
cember-4.081
isphere-4.049
nir-3.940
andum-3.893
istical-3.778
Token.:
Token ID11207
Feature activation-1.08e+00

Pos logit contributions
heid+9.048
hips+7.943
ertodd+7.603
 refrain+7.078
olini+6.701
Neg logit contributions
cember-6.897
isphere-6.843
nir-6.687
andum-6.513
asar-6.498
Token Christian
Token ID4302
Feature activation-5.12e-01

Pos logit contributions
heid+2.717
hips+2.343
ertodd+2.188
 refrain+2.061
olini+1.874
Neg logit contributions
cember-2.947
isphere-2.892
nir-2.811
andum-2.770
asar-2.750
Token
Token ID447
Feature activation-1.70e-01

Pos logit contributions
heid+1.412
hips+1.224
ertodd+1.174
 refrain+1.104
olini+1.023
Neg logit contributions
cember-1.260
isphere-1.231
nir-1.222
andum-1.201
asar-1.195
Token
Token ID247
Feature activation+4.75e-01

Pos logit contributions
heid+0.634
hips+0.570
ertodd+0.557
 refrain+0.530
olini+0.501
Neg logit contributions
cember-0.255
isphere-0.246
nir-0.241
andum-0.234
asar-0.233
Tokens
Token ID82
Feature activation+1.48e-01

Pos logit contributions
cember+1.271
isphere+1.242
nir+1.232
andum+1.213
asar+1.209
Neg logit contributions
heid-1.215
hips-1.022
ertodd-1.000
 refrain-0.920
olini-0.836
Token compiled
Token ID14102
Feature activation+4.42e-01

Pos logit contributions
heid+0.816
hips+0.699
ertodd+0.674
 refrain+0.629
olini+0.573
Neg logit contributions
cember-0.808
isphere-0.791
nir-0.782
andum-0.771
asar-0.767
Token addresses
Token ID9405
Feature activation-5.05e-01

Pos logit contributions
cember+1.188
isphere+1.167
nir+1.149
asar+1.132
andum+1.131
Neg logit contributions
heid-1.119
hips-0.953
ertodd-0.931
 refrain-0.841
olini-0.783
Token had
Token ID550
Feature activation-1.05e-01

Pos logit contributions
heid+1.331
hips+1.156
ertodd+1.101
 refrain+1.033
olini+0.934
Neg logit contributions
cember-1.307
isphere-1.276
nir-1.270
andum-1.251
asar-1.243
Token such
Token ID884
Feature activation+4.75e-01

Pos logit contributions
heid+0.287
hips+0.249
ertodd+0.239
 refrain+0.224
olini+0.205
Neg logit contributions
cember-0.261
isphere-0.255
nir-0.253
andum-0.249
asar-0.248
Token a
Token ID257
Feature activation-1.09e+00

Pos logit contributions
cember+1.137
isphere+1.122
nir+1.096
andum+1.082
asar+1.077
Neg logit contributions
heid-1.343
hips-1.155
ertodd-1.136
 refrain-1.037
olini-0.971
Token long
Token ID890
Feature activation-3.18e+00

Pos logit contributions
heid+2.982
hips+2.581
ertodd+2.455
 refrain+2.364
olini+2.131
Neg logit contributions
cember-2.690
isphere-2.617
nir-2.607
andum-2.561
asar-2.545
Token and
Token ID290
Feature activation-5.49e-01

Pos logit contributions
heid+6.628
hips+5.374
 refrain+5.024
ertodd+4.759
olini+4.055
Neg logit contributions
cember-9.600
nir-9.337
isphere-9.210
utics-9.117
asar-9.062
Token st
Token ID336
Feature activation-1.47e+00

Pos logit contributions
heid+1.496
hips+1.289
ertodd+1.245
 refrain+1.162
olini+1.066
Neg logit contributions
cember-1.375
isphere-1.346
nir-1.331
andum-1.311
asar-1.305
Tokenoried
Token ID42058
Feature activation-2.77e+00

Pos logit contributions
heid+3.140
hips+2.594
ertodd+2.444
 refrain+2.188
olini+1.958
Neg logit contributions
cember-4.552
isphere-4.423
nir-4.380
andum-4.316
istical-4.309
Token history
Token ID2106
Feature activation-1.97e+00

Pos logit contributions
heid+5.056
hips+4.052
 refrain+3.556
ertodd+3.454
olini+2.783
Neg logit contributions
cember-9.248
nir-9.078
isphere-9.029
andum-8.891
utics-8.829
Token of
Token ID286
Feature activation-6.97e-02

Pos logit contributions
heid+4.669
hips+4.090
ertodd+3.722
 refrain+3.554
olini+3.175
Neg logit contributions
cember-5.515
nir-5.322
isphere-5.286
andum-5.244
asar-5.196
Token form
Token ID1296
Feature activation-5.15e-02

Pos logit contributions
cember+0.221
isphere+0.215
nir+0.213
andum+0.210
asar+0.209
Neg logit contributions
heid-0.243
hips-0.210
ertodd-0.204
 refrain-0.188
olini-0.174
Token of
Token ID286
Feature activation+9.69e-02

Pos logit contributions
heid+0.140
hips+0.120
ertodd+0.117
 refrain+0.108
olini+0.099
Neg logit contributions
cember-0.129
isphere-0.127
nir-0.125
andum-0.124
istical-0.123
Token exercise
Token ID5517
Feature activation+4.95e-01

Pos logit contributions
cember+0.257
isphere+0.252
nir+0.249
andum+0.246
asar+0.245
Neg logit contributions
heid-0.250
hips-0.213
ertodd-0.206
 refrain-0.190
olini-0.174
Token
Token ID960
Feature activation-9.13e-01

Pos logit contributions
cember+1.269
isphere+1.250
nir+1.234
andum+1.212
asar+1.207
Neg logit contributions
heid-1.315
hips-1.125
ertodd-1.094
 refrain-1.009
olini-0.931
Tokena
Token ID64
Feature activation+1.97e-01

Pos logit contributions
heid+2.548
hips+2.225
ertodd+2.091
 refrain+1.994
olini+1.831
Neg logit contributions
cember-2.244
isphere-2.179
nir-2.124
andum-2.114
asar-2.098
Token MET
Token ID31243
Feature activation-3.18e+00

Pos logit contributions
cember+0.508
isphere+0.497
nir+0.491
andum+0.483
asar+0.482
Neg logit contributions
heid-0.524
hips-0.450
ertodd-0.437
 refrain-0.402
olini-0.371
TokenAB
Token ID6242
Feature activation-1.26e+00

Pos logit contributions
heid+7.858
hips+6.781
ertodd+6.453
 refrain+6.323
 membership+5.473
Neg logit contributions
cember-8.035
isphere-7.911
nir-7.847
asar-7.647
andum-7.546
TokenOL
Token ID3535
Feature activation-5.26e-01

Pos logit contributions
heid+2.706
hips+2.255
ertodd+2.048
 refrain+1.946
olini+1.748
Neg logit contributions
cember-3.887
isphere-3.796
nir-3.790
andum-3.697
istical-3.669
TokenIC
Token ID2149
Feature activation-9.33e-01

Pos logit contributions
heid+1.611
hips+1.415
ertodd+1.364
 refrain+1.303
olini+1.205
Neg logit contributions
cember-1.140
isphere-1.103
nir-1.092
asar-1.073
andum-1.070
Token WORK
Token ID30936
Feature activation-1.23e+00

Pos logit contributions
heid+2.343
hips+1.996
ertodd+1.882
 refrain+1.793
olini+1.588
Neg logit contributions
cember-2.541
isphere-2.490
nir-2.459
asar-2.425
andum-2.420
TokenOUT
Token ID12425
Feature activation-1.27e-02

Pos logit contributions
heid+4.725
hips+4.278
ertodd+4.114
 refrain+4.000
olini+3.743
Neg logit contributions
cember-1.674
isphere-1.602
nir-1.530
asar-1.517
andum-1.505
Token takeover
Token ID27011
Feature activation+2.65e-01

Pos logit contributions
heid+1.993
hips+1.688
ertodd+1.567
 refrain+1.520
olini+1.338
Neg logit contributions
cember-2.369
isphere-2.355
nir-2.304
andum-2.273
istical-2.248
Token of
Token ID286
Feature activation+1.11e+00

Pos logit contributions
cember+0.671
isphere+0.655
nir+0.647
andum+0.640
asar+0.638
Neg logit contributions
heid-0.714
hips-0.611
ertodd-0.599
 refrain-0.550
olini-0.510
Token the
Token ID262
Feature activation+1.86e-01

Pos logit contributions
cember+2.825
nir+2.759
isphere+2.740
asar+2.726
andum+2.712
Neg logit contributions
heid-2.941
hips-2.502
ertodd-2.486
 refrain-2.221
olini-2.105
Token M
Token ID337
Feature activation-8.84e-02

Pos logit contributions
cember+0.487
isphere+0.477
nir+0.471
andum+0.464
asar+0.462
Neg logit contributions
heid-0.487
hips-0.417
ertodd-0.401
 refrain-0.374
olini-0.341
Tokenavi
Token ID15820
Feature activation+1.16e+00

Pos logit contributions
heid+0.345
hips+0.311
ertodd+0.305
 refrain+0.291
olini+0.276
Neg logit contributions
cember-0.118
isphere-0.113
nir-0.110
andum-0.107
asar-0.106
Token Mar
Token ID1526
Feature activation-3.17e+00

Pos logit contributions
cember+2.634
isphere+2.593
nir+2.564
asar+2.529
andum+2.527
Neg logit contributions
heid-3.397
hips-2.979
ertodd-2.933
 refrain-2.676
olini-2.501
Tokenm
Token ID76
Feature activation+3.33e-01

Pos logit contributions
heid+6.952
hips+5.601
ertodd+5.282
 refrain+4.887
olini+4.524
Neg logit contributions
cember-9.476
isphere-8.972
istical-8.918
nir-8.684
utics-8.581
Tokenara
Token ID3301
Feature activation-2.70e-01

Pos logit contributions
cember+0.789
isphere+0.771
nir+0.761
andum+0.747
asar+0.743
Neg logit contributions
heid-0.958
hips-0.830
ertodd-0.802
 refrain-0.754
olini-0.695
Token.
Token ID13
Feature activation-2.06e-02

Pos logit contributions
heid+0.718
hips+0.618
ertodd+0.586
 refrain+0.554
olini+0.502
Neg logit contributions
cember-0.698
isphere-0.682
nir-0.672
andum-0.661
istical-0.657
Token Turkey
Token ID7137
Feature activation+1.37e+00

Pos logit contributions
heid+0.056
hips+0.049
ertodd+0.047
 refrain+0.044
olini+0.040
Neg logit contributions
cember-0.051
isphere-0.050
nir-0.049
andum-0.049
asar-0.048
Token and
Token ID290
Feature activation-2.78e-01

Pos logit contributions
cember+3.249
isphere+3.148
nir+3.138
andum+3.098
asar+3.076
Neg logit contributions
heid-3.858
hips-3.311
ertodd-3.289
 refrain-2.981
olini-2.789
Token10
Token ID940
Feature activation+1.08e+00

Pos logit contributions
cember+0.000
isphere+0.000
nir+0.000
andum+0.000
asar+0.000
Neg logit contributions
heid-0.000
hips-0.000
ertodd-0.000
 refrain-0.000
olini-0.000
Token:
Token ID25
Feature activation-4.55e-01

Pos logit contributions
cember+2.234
nir+2.211
isphere+2.208
asar+2.162
andum+2.149
Neg logit contributions
heid-3.330
hips-2.881
ertodd-2.870
 refrain-2.675
olini-2.506
Token47
Token ID2857
Feature activation-8.33e-01

Pos logit contributions
heid+1.242
hips+1.068
ertodd+1.034
 refrain+0.961
olini+0.887
Neg logit contributions
cember-1.139
isphere-1.116
nir-1.103
andum-1.083
asar-1.081
Token]
Token ID60
Feature activation+6.21e-02

Pos logit contributions
heid+2.551
hips+2.265
ertodd+2.151
 refrain+2.022
olini+1.881
Neg logit contributions
cember-1.861
isphere-1.789
nir-1.727
andum-1.710
asar-1.667
Token <
Token ID1279
Feature activation+8.85e-01

Pos logit contributions
cember+0.161
isphere+0.157
nir+0.156
andum+0.154
asar+0.153
Neg logit contributions
heid-0.163
hips-0.140
ertodd-0.134
 refrain-0.125
olini-0.116
Tokenc
Token ID66
Feature activation+2.26e+00

Pos logit contributions
cember+2.147
nir+2.096
isphere+2.095
asar+2.037
andum+2.033
Neg logit contributions
heid-2.447
hips-2.119
ertodd-2.072
 refrain-1.967
olini-1.780
Tokenerv
Token ID712
Feature activation-1.65e-01

Pos logit contributions
cember+5.167
isphere+5.066
nir+5.054
ause+4.959
asar+4.954
Neg logit contributions
heid-6.283
hips-5.421
ertodd-5.345
 refrain-5.190
olini-4.620
Tokenant
Token ID415
Feature activation-9.74e-01

Pos logit contributions
heid+0.521
hips+0.458
ertodd+0.446
 refrain+0.419
olini+0.392
Neg logit contributions
cember-0.345
isphere-0.336
nir-0.331
andum-0.325
asar-0.323
Tokenas
Token ID292
Feature activation-3.18e-01

Pos logit contributions
heid+3.034
hips+2.639
ertodd+2.567
 refrain+2.375
olini+2.255
Neg logit contributions
cember-2.069
isphere-2.007
nir-1.977
andum-1.944
asar-1.925
Token>
Token ID29
Feature activation-7.15e-01

Pos logit contributions
heid+0.945
hips+0.825
ertodd+0.799
 refrain+0.747
olini+0.695
Neg logit contributions
cember-0.720
isphere-0.703
nir-0.693
andum-0.682
asar-0.678
Token lol
Token ID19462
Feature activation-3.73e-01

Pos logit contributions
heid+1.944
hips+1.673
ertodd+1.604
 refrain+1.513
olini+1.380
Neg logit contributions
cember-1.803
isphere-1.760
nir-1.736
andum-1.716
asar-1.705
Token av
Token ID1196
Feature activation-2.01e-01

Pos logit contributions
cember+1.268
isphere+1.247
nir+1.227
andum+1.212
asar+1.211
Neg logit contributions
heid-1.290
hips-1.112
ertodd-1.090
 refrain-0.984
olini-0.920
Tokeniator
Token ID38585
Feature activation+3.45e-01

Pos logit contributions
heid+0.629
hips+0.553
ertodd+0.537
 refrain+0.505
olini+0.472
Neg logit contributions
cember-0.423
isphere-0.411
nir-0.406
andum-0.399
asar-0.395
Token Capt
Token ID6790
Feature activation+3.54e-01

Pos logit contributions
cember+0.939
isphere+0.923
nir+0.912
asar+0.900
andum+0.900
Neg logit contributions
heid-0.855
hips-0.719
ertodd-0.709
 refrain-0.642
olini-0.591
Token Sir
Token ID7361
Feature activation-1.14e+00

Pos logit contributions
cember+0.937
isphere+0.920
nir+0.910
asar+0.896
andum+0.896
Neg logit contributions
heid-0.909
hips-0.775
ertodd-0.762
 refrain-0.699
olini-0.635
Token George
Token ID4502
Feature activation+4.07e-01

Pos logit contributions
heid+2.641
hips+2.233
ertodd+2.065
 refrain+1.928
olini+1.735
Neg logit contributions
cember-3.340
isphere-3.288
nir-3.229
andum-3.188
istical-3.161
Token Hu
Token ID11256
Feature activation+2.82e+00

Pos logit contributions
cember+1.178
isphere+1.164
nir+1.146
asar+1.132
andum+1.131
Neg logit contributions
heid-0.942
hips-0.782
ertodd-0.777
 refrain-0.692
olini-0.628
Tokenbert
Token ID4835
Feature activation+1.01e+00

Pos logit contributions
cember+5.794
isphere+5.690
nir+5.580
asar+5.558
andum+5.500
Neg logit contributions
heid-8.561
ertodd-7.625
hips-7.448
 refrain-6.883
olini-6.342
Token Wil
Token ID5187
Feature activation-2.11e-02

Pos logit contributions
cember+2.698
isphere+2.664
nir+2.632
andum+2.597
asar+2.595
Neg logit contributions
heid-2.514
ertodd-2.149
hips-2.131
 refrain-1.914
olini-1.749
Tokenkins
Token ID5331
Feature activation-6.63e-01

Pos logit contributions
heid+0.052
hips+0.044
ertodd+0.042
 refrain+0.039
olini+0.035
Neg logit contributions
cember-0.059
isphere-0.058
nir-0.057
andum-0.056
asar-0.056
Token who
Token ID508
Feature activation+9.04e-01

Pos logit contributions
heid+1.830
hips+1.583
ertodd+1.520
 refrain+1.422
olini+1.309
Neg logit contributions
cember-1.642
isphere-1.604
nir-1.585
andum-1.560
asar-1.553
Token,
Token ID11
Feature activation-3.69e-01

Pos logit contributions
cember+2.103
isphere+2.077
nir+2.036
asar+2.003
andum+2.000
Neg logit contributions
heid-2.602
hips-2.231
ertodd-2.225
 refrain-2.033
olini-1.902
Token market
Token ID1910
Feature activation+4.33e-01

Pos logit contributions
heid+0.269
hips+0.227
ertodd+0.218
 refrain+0.201
olini+0.181
Neg logit contributions
cember-0.319
isphere-0.313
nir-0.310
andum-0.305
asar-0.305
Token,
Token ID11
Feature activation+3.79e-01

Pos logit contributions
cember+1.064
isphere+1.042
nir+1.026
andum+1.012
asar+1.009
Neg logit contributions
heid-1.206
hips-1.031
ertodd-1.008
 refrain-0.934
olini-0.866
Token and
Token ID290
Feature activation-2.73e-01

Pos logit contributions
cember+1.016
isphere+0.998
nir+0.986
andum+0.973
asar+0.969
Neg logit contributions
heid-0.966
hips-0.819
ertodd-0.795
 refrain-0.730
olini-0.670
Token Dallas
Token ID8533
Feature activation-1.30e+00

Pos logit contributions
heid+0.713
hips+0.614
ertodd+0.587
 refrain+0.552
olini+0.500
Neg logit contributions
cember-0.714
isphere-0.698
nir-0.692
andum-0.679
asar-0.678
Token can
Token ID460
Feature activation+1.77e-01

Pos logit contributions
heid+3.410
hips+3.005
ertodd+2.797
 refrain+2.695
olini+2.398
Neg logit contributions
cember-3.305
isphere-3.266
nir-3.234
asar-3.175
andum-3.174
Token clear
Token ID1598
Feature activation+2.24e+00

Pos logit contributions
cember+0.448
isphere+0.439
nir+0.435
andum+0.429
asar+0.425
Neg logit contributions
heid-0.480
hips-0.410
ertodd-0.402
 refrain-0.366
olini-0.343
Token a
Token ID257
Feature activation-2.46e-01

Pos logit contributions
cember+5.053
isphere+4.990
nir+4.854
asar+4.853
istical+4.819
Neg logit contributions
heid-6.449
ertodd-5.542
hips-5.427
 refrain-4.889
olini-4.666
Token lot
Token ID1256
Feature activation-6.98e-01

Pos logit contributions
heid+0.665
hips+0.574
ertodd+0.551
 refrain+0.523
olini+0.472
Neg logit contributions
cember-0.619
isphere-0.608
nir-0.602
andum-0.594
asar-0.590
Token of
Token ID286
Feature activation+3.44e-02

Pos logit contributions
heid+1.794
hips+1.551
ertodd+1.478
 refrain+1.384
olini+1.258
Neg logit contributions
cember-1.847
isphere-1.794
nir-1.776
andum-1.765
asar-1.748
Token money
Token ID1637
Feature activation-8.99e-01

Pos logit contributions
cember+0.081
isphere+0.079
nir+0.079
andum+0.077
asar+0.077
Neg logit contributions
heid-0.098
hips-0.086
ertodd-0.083
 refrain-0.078
olini-0.072
Token really
Token ID1107
Feature activation+6.21e-01

Pos logit contributions
heid+2.379
hips+2.103
ertodd+1.964
 refrain+1.870
olini+1.690
Neg logit contributions
cember-2.296
isphere-2.221
nir-2.202
andum-2.192
asar-2.158
Tokenglers
Token ID33641
Feature activation+9.51e-01

Pos logit contributions
cember+1.317
isphere+1.265
nir+1.257
asar+1.237
istical+1.234
Neg logit contributions
heid-1.988
hips-1.746
ertodd-1.720
 refrain-1.595
olini-1.490
Token,
Token ID11
Feature activation+2.98e-01

Pos logit contributions
cember+2.195
isphere+2.153
nir+2.140
asar+2.104
andum+2.085
Neg logit contributions
heid-2.739
ertodd-2.322
hips-2.319
 refrain-2.109
olini-1.980
Token the
Token ID262
Feature activation+3.01e-01

Pos logit contributions
cember+0.759
isphere+0.743
nir+0.738
asar+0.727
andum+0.725
Neg logit contributions
heid-0.795
hips-0.678
ertodd-0.664
 refrain-0.603
olini-0.559
Token crazy
Token ID7165
Feature activation-3.21e-01

Pos logit contributions
cember+0.757
isphere+0.738
nir+0.730
andum+0.718
asar+0.718
Neg logit contributions
heid-0.814
hips-0.702
ertodd-0.683
 refrain-0.624
olini-0.580
Token ac
Token ID936
Feature activation+3.99e-01

Pos logit contributions
heid+0.902
hips+0.781
ertodd+0.755
 refrain+0.706
olini+0.651
Neg logit contributions
cember-0.779
isphere-0.762
nir-0.753
andum-0.741
asar-0.737
Tokenrobat
Token ID40655
Feature activation+2.26e+00

Pos logit contributions
cember+0.826
isphere+0.811
nir+0.800
asar+0.781
andum+0.778
Neg logit contributions
heid-1.255
hips-1.103
ertodd-1.080
 refrain-1.018
olini-0.938
Tokenics
Token ID873
Feature activation+1.01e+00

Pos logit contributions
nir+2.768
cember+2.766
isphere+2.737
istical+2.680
asar+2.678
Neg logit contributions
heid-8.661
ertodd-7.791
hips-7.717
 refrain-7.266
olini-6.886
Token
Token ID784
Feature activation-4.88e-01

Pos logit contributions
cember+2.389
isphere+2.357
nir+2.328
asar+2.284
istical+2.279
Neg logit contributions
heid-2.877
hips-2.453
ertodd-2.446
 refrain-2.229
olini-2.077
Token and
Token ID290
Feature activation-5.32e-01

Pos logit contributions
heid+1.273
hips+1.091
ertodd+1.049
 refrain+0.978
olini+0.893
Neg logit contributions
cember-1.281
isphere-1.254
nir-1.238
andum-1.221
asar-1.214
Token you
Token ID345
Feature activation+7.12e-01

Pos logit contributions
heid+1.379
hips+1.179
ertodd+1.136
 refrain+1.056
olini+0.964
Neg logit contributions
cember-1.407
isphere-1.379
nir-1.361
andum-1.343
asar-1.337
Token get
Token ID651
Feature activation+1.76e+00

Pos logit contributions
cember+1.639
isphere+1.610
nir+1.593
andum+1.560
asar+1.556
Neg logit contributions
heid-2.080
hips-1.783
ertodd-1.762
 refrain-1.602
olini-1.506
Token a
Token ID257
Feature activation+1.06e+00

Pos logit contributions
cember+3.845
nir+3.736
isphere+3.709
asar+3.630
istical+3.620
Neg logit contributions
heid-5.135
ertodd-4.490
hips-4.383
 refrain-4.006
olini-3.837
Token season
Token ID1622
Feature activation-8.10e-01

Pos logit contributions
cember+2.507
isphere+2.423
nir+2.409
istical+2.372
asar+2.355
Neg logit contributions
heid-3.026
hips-2.610
ertodd-2.591
 refrain-2.335
olini-2.253
Token-
Token ID12
Feature activation+9.24e-01

Pos logit contributions
heid+2.217
hips+1.924
ertodd+1.835
 refrain+1.735
olini+1.566
Neg logit contributions
cember-2.009
isphere-1.965
nir-1.948
andum-1.920
asar-1.905
Tokenhigh
Token ID8929
Feature activation+3.25e-01

Pos logit contributions
cember+1.672
isphere+1.630
nir+1.628
asar+1.583
andum+1.568
Neg logit contributions
heid-3.134
hips-2.747
ertodd-2.743
 refrain-2.579
olini-2.435
Token 28
Token ID2579
Feature activation+1.43e+00

Pos logit contributions
cember+0.759
isphere+0.741
nir+0.732
andum+0.719
asar+0.716
Neg logit contributions
heid-0.943
hips-0.819
ertodd-0.797
 refrain-0.742
olini-0.691
Token points
Token ID2173
Feature activation+2.41e+00

Pos logit contributions
cember+2.475
isphere+2.416
nir+2.376
andum+2.319
asar+2.309
Neg logit contributions
heid-4.923
ertodd-4.331
hips-4.320
 refrain-4.009
olini-3.872
Token against
Token ID1028
Feature activation+1.56e+00

Pos logit contributions
cember+5.327
isphere+5.173
nir+5.078
asar+5.014
ause+4.961
Neg logit contributions
heid-6.970
ertodd-6.012
hips-5.834
 refrain-5.411
olini-5.263
Token Boston
Token ID6182
Feature activation+3.27e-01

Pos logit contributions
cember+3.948
nir+3.834
isphere+3.818
asar+3.787
andum+3.739
Neg logit contributions
heid-4.060
ertodd-3.521
hips-3.440
 refrain-3.058
olini-2.905
Token College
Token ID5535
Feature activation-9.82e-02

Pos logit contributions
cember+0.867
isphere+0.851
nir+0.840
andum+0.831
asar+0.829
Neg logit contributions
heid-0.840
hips-0.714
ertodd-0.704
 refrain-0.641
olini-0.587
Token on
Token ID319
Feature activation-6.23e-03

Pos logit contributions
heid+0.264
hips+0.227
ertodd+0.218
 refrain+0.203
olini+0.186
Neg logit contributions
cember-0.250
isphere-0.245
nir-0.243
andum-0.239
asar-0.237
Token January
Token ID3269
Feature activation-5.44e-01

Pos logit contributions
heid+0.019
hips+0.016
ertodd+0.016
 refrain+0.015
olini+0.014
Neg logit contributions
cember-0.014
isphere-0.014
nir-0.013
andum-0.013
asar-0.013
Token Mongol
Token ID42188
Feature activation-1.06e-01

Pos logit contributions
cember+0.638
isphere+0.625
nir+0.618
andum+0.608
asar+0.606
Neg logit contributions
heid-0.665
hips-0.569
ertodd-0.552
 refrain-0.510
olini-0.470
Tokenian
Token ID666
Feature activation-5.47e-02

Pos logit contributions
heid+0.378
hips+0.340
ertodd+0.330
 refrain+0.315
olini+0.296
Neg logit contributions
cember-0.178
isphere-0.172
nir-0.168
andum-0.164
asar-0.163
Token names
Token ID3891
Feature activation+1.45e-01

Pos logit contributions
heid+0.141
hips+0.120
ertodd+0.116
 refrain+0.107
olini+0.098
Neg logit contributions
cember-0.146
isphere-0.143
nir-0.141
andum-0.139
asar-0.139
Token to
Token ID284
Feature activation-2.38e-01

Pos logit contributions
cember+0.363
isphere+0.356
nir+0.351
andum+0.346
asar+0.345
Neg logit contributions
heid-0.398
hips-0.342
ertodd-0.333
 refrain-0.308
olini-0.284
Token their
Token ID511
Feature activation+1.83e-01

Pos logit contributions
heid+0.638
hips+0.551
ertodd+0.531
 refrain+0.496
olini+0.454
Neg logit contributions
cember-0.604
isphere-0.592
nir-0.584
andum-0.575
asar-0.572
Token children
Token ID1751
Feature activation+9.27e-01

Pos logit contributions
cember+0.510
isphere+0.500
nir+0.494
andum+0.488
asar+0.487
Neg logit contributions
heid-0.449
hips-0.377
ertodd-0.367
 refrain-0.333
olini-0.305
Token,
Token ID11
Feature activation+8.95e-01

Pos logit contributions
cember+2.245
isphere+2.214
nir+2.186
asar+2.146
andum+2.139
Neg logit contributions
heid-2.581
hips-2.196
ertodd-2.163
 refrain-1.985
olini-1.855
Token often
Token ID1690
Feature activation-3.30e-01

Pos logit contributions
cember+2.315
isphere+2.278
nir+2.247
asar+2.217
andum+2.214
Neg logit contributions
heid-2.350
hips-1.971
ertodd-1.965
 refrain-1.749
olini-1.641
Token in
Token ID287
Feature activation-1.51e-01

Pos logit contributions
heid+0.843
hips+0.724
ertodd+0.693
 refrain+0.649
olini+0.586
Neg logit contributions
cember-0.879
isphere-0.862
nir-0.854
andum-0.841
asar-0.837
Token the
Token ID262
Feature activation-2.72e-01

Pos logit contributions
heid+0.401
hips+0.344
ertodd+0.333
 refrain+0.310
olini+0.283
Neg logit contributions
cember-0.387
isphere-0.379
nir-0.374
andum-0.369
asar-0.367
Token form
Token ID1296
Feature activation+5.84e-01

Pos logit contributions
heid+0.649
hips+0.546
ertodd+0.525
 refrain+0.488
olini+0.436
Neg logit contributions
cember-0.772
isphere-0.760
nir-0.752
andum-0.742
asar-0.737
Token.
Token ID13
Feature activation+8.25e-01

Pos logit contributions
cember+1.153
isphere+1.131
nir+1.122
asar+1.102
andum+1.099
Neg logit contributions
heid-1.283
hips-1.102
ertodd-1.077
 refrain-0.991
olini-0.925
Token You
Token ID921
Feature activation+8.78e-01

Pos logit contributions
cember+2.032
nir+1.995
isphere+1.990
asar+1.959
andum+1.956
Neg logit contributions
heid-2.227
hips-1.903
ertodd-1.891
 refrain-1.709
olini-1.608
Token have
Token ID423
Feature activation+1.20e+00

Pos logit contributions
cember+2.309
isphere+2.268
nir+2.253
asar+2.214
andum+2.206
Neg logit contributions
heid-2.266
hips-1.889
ertodd-1.875
 refrain-1.667
olini-1.583
Token to
Token ID284
Feature activation-1.10e+00

Pos logit contributions
cember+2.820
isphere+2.768
nir+2.742
andum+2.676
asar+2.673
Neg logit contributions
heid-3.419
hips-2.948
ertodd-2.916
 refrain-2.677
olini-2.495
Token earn
Token ID5160
Feature activation+1.92e-02

Pos logit contributions
heid+2.242
hips+1.857
ertodd+1.740
 refrain+1.628
olini+1.383
Neg logit contributions
cember-3.476
isphere-3.422
nir-3.369
andum-3.340
asar-3.334
Token the
Token ID262
Feature activation+6.43e-01

Pos logit contributions
cember+0.048
isphere+0.047
nir+0.047
andum+0.046
asar+0.046
Neg logit contributions
heid-0.052
hips-0.045
ertodd-0.043
 refrain-0.040
olini-0.037
Token right
Token ID826
Feature activation+4.10e-01

Pos logit contributions
cember+1.635
isphere+1.604
nir+1.589
andum+1.555
asar+1.555
Neg logit contributions
heid-1.720
hips-1.474
ertodd-1.444
 refrain-1.305
olini-1.228
Token to
Token ID284
Feature activation-2.89e-01

Pos logit contributions
cember+0.992
isphere+0.972
nir+0.960
andum+0.943
asar+0.940
Neg logit contributions
heid-1.154
hips-0.998
ertodd-0.971
 refrain-0.898
olini-0.834
Token put
Token ID1234
Feature activation+1.55e+00

Pos logit contributions
heid+0.621
hips+0.512
ertodd+0.491
 refrain+0.444
olini+0.396
Neg logit contributions
cember-0.889
isphere-0.874
nir-0.865
andum-0.855
asar-0.852
Tokent
Token ID83
Feature activation+2.90e-01

Pos logit contributions
cember+3.623
isphere+3.613
nir+3.590
andum+3.506
asar+3.504
Neg logit contributions
heid-4.356
hips-3.759
ertodd-3.720
 refrain-3.392
olini-3.156
Token a
Token ID257
Feature activation-4.32e-01

Pos logit contributions
cember+0.742
isphere+0.727
nir+0.718
andum+0.707
asar+0.704
Neg logit contributions
heid-0.778
hips-0.668
ertodd-0.646
 refrain-0.600
olini-0.551
Token our
Token ID674
Feature activation-4.78e-01

Pos logit contributions
heid+0.633
hips+0.541
ertodd+0.522
 refrain+0.483
olini+0.441
Neg logit contributions
cember-0.657
isphere-0.644
nir-0.636
andum-0.627
asar-0.625
Token own
Token ID898
Feature activation-1.27e+00

Pos logit contributions
heid+1.084
hips+0.906
ertodd+0.865
 refrain+0.795
olini+0.711
Neg logit contributions
cember-1.414
isphere-1.390
nir-1.376
andum-1.358
asar-1.354
Token,
Token ID11
Feature activation-1.38e-01

Pos logit contributions
heid+3.071
hips+2.619
ertodd+2.440
 refrain+2.333
olini+2.084
Neg logit contributions
cember-3.579
isphere-3.493
nir-3.461
andum-3.435
asar-3.407
Token everyday
Token ID10908
Feature activation-1.14e+00

Pos logit contributions
heid+0.365
hips+0.312
ertodd+0.302
 refrain+0.280
olini+0.256
Neg logit contributions
cember-0.359
isphere-0.352
nir-0.348
andum-0.342
asar-0.341
Token,
Token ID11
Feature activation-4.71e-01

Pos logit contributions
heid+2.770
hips+2.347
ertodd+2.212
 refrain+2.106
olini+1.856
Neg logit contributions
cember-3.186
isphere-3.116
nir-3.085
andum-3.061
asar-3.041
Token minimal
Token ID10926
Feature activation+6.42e-01

Pos logit contributions
heid+1.220
hips+1.046
ertodd+1.001
 refrain+0.936
olini+0.848
Neg logit contributions
cember-1.244
isphere-1.219
nir-1.207
andum-1.191
asar-1.184
Token ways
Token ID2842
Feature activation+7.34e-01

Pos logit contributions
cember+1.627
isphere+1.596
nir+1.574
istical+1.551
andum+1.549
Neg logit contributions
heid-1.724
hips-1.481
ertodd-1.446
 refrain-1.330
olini-1.229
Token.
Token ID13
Feature activation-3.20e-01

Pos logit contributions
cember+1.746
isphere+1.714
nir+1.688
andum+1.658
istical+1.654
Neg logit contributions
heid-2.077
hips-1.775
ertodd-1.757
 refrain-1.624
olini-1.512
Token
Token ID198
Feature activation-4.54e-01

Pos logit contributions
heid+0.848
hips+0.729
ertodd+0.699
 refrain+0.654
olini+0.597
Neg logit contributions
cember-0.830
isphere-0.814
nir-0.800
andum-0.789
asar-0.785
Token
Token ID198
Feature activation+2.38e-01

Pos logit contributions
heid+1.166
hips+1.003
ertodd+0.950
 refrain+0.888
olini+0.806
Neg logit contributions
cember-1.222
isphere-1.197
nir-1.170
andum-1.158
asar-1.144
TokenThe
Token ID464
Feature activation-7.48e-02

Pos logit contributions
cember+0.518
isphere+0.506
nir+0.498
andum+0.489
asar+0.487
Neg logit contributions
heid-0.730
hips-0.640
ertodd-0.621
 refrain-0.583
olini-0.543
Token with
Token ID351
Feature activation+2.44e-01

Pos logit contributions
heid+0.894
hips+0.763
ertodd+0.742
 refrain+0.684
olini+0.628
Neg logit contributions
cember-0.884
isphere-0.867
nir-0.856
andum-0.844
asar-0.841
Token Dahl
Token ID41471
Feature activation+6.92e-01

Pos logit contributions
cember+0.619
isphere+0.607
nir+0.599
andum+0.592
asar+0.590
Neg logit contributions
heid-0.657
hips-0.562
ertodd-0.549
 refrain-0.501
olini-0.463
Token's
Token ID338
Feature activation-6.57e-01

Pos logit contributions
cember+1.388
isphere+1.345
nir+1.324
asar+1.307
andum+1.299
Neg logit contributions
heid-2.241
hips-1.959
ertodd-1.924
 refrain-1.795
olini-1.676
Token script
Token ID4226
Feature activation+1.30e+00

Pos logit contributions
heid+1.610
hips+1.366
ertodd+1.312
 refrain+1.221
olini+1.100
Neg logit contributions
cember-1.820
isphere-1.788
nir-1.769
andum-1.745
asar-1.736
Token and
Token ID290
Feature activation-1.88e-01

Pos logit contributions
cember+3.178
isphere+3.147
nir+3.050
asar+3.031
istical+3.029
Neg logit contributions
heid-3.601
hips-3.059
ertodd-3.005
 refrain-2.719
olini-2.557
Token brought
Token ID3181
Feature activation+7.76e-01

Pos logit contributions
heid+0.522
hips+0.450
ertodd+0.438
 refrain+0.406
olini+0.375
Neg logit contributions
cember-0.461
isphere-0.452
nir-0.446
andum-0.439
asar-0.437
Token in
Token ID287
Feature activation+1.90e-01

Pos logit contributions
cember+1.894
isphere+1.863
nir+1.842
andum+1.818
istical+1.810
Neg logit contributions
heid-2.155
hips-1.836
ertodd-1.814
 refrain-1.652
olini-1.526
Token an
Token ID281
Feature activation+1.92e-01

Pos logit contributions
cember+0.491
isphere+0.481
nir+0.476
andum+0.470
asar+0.468
Neg logit contributions
heid-0.503
hips-0.430
ertodd-0.418
 refrain-0.384
olini-0.353
Token unknown
Token ID6439
Feature activation-5.08e-03

Pos logit contributions
cember+0.490
isphere+0.480
nir+0.474
andum+0.468
asar+0.466
Neg logit contributions
heid-0.515
hips-0.443
ertodd-0.429
 refrain-0.396
olini-0.364
Token to
Token ID284
Feature activation-4.29e-01

Pos logit contributions
heid+0.013
hips+0.011
ertodd+0.011
 refrain+0.010
olini+0.009
Neg logit contributions
cember-0.014
isphere-0.013
nir-0.013
andum-0.013
asar-0.013
Token rewrite
Token ID28183
Feature activation-2.79e-01

Pos logit contributions
heid+0.993
hips+0.828
ertodd+0.798
 refrain+0.723
olini+0.654
Neg logit contributions
cember-1.257
isphere-1.234
nir-1.221
andum-1.207
asar-1.203
Token edition
Token ID8313
Feature activation-8.10e-01

Pos logit contributions
heid+0.241
hips+0.205
ertodd+0.199
 refrain+0.181
olini+0.166
Neg logit contributions
cember-0.268
isphere-0.263
nir-0.259
andum-0.257
asar-0.255
Token.
Token ID13
Feature activation-2.25e-01

Pos logit contributions
heid+2.232
hips+1.933
ertodd+1.855
 refrain+1.747
olini+1.596
Neg logit contributions
cember-1.990
isphere-1.947
nir-1.937
asar-1.891
andum-1.890
Token The
Token ID383
Feature activation-2.57e-01

Pos logit contributions
heid+0.605
hips+0.521
ertodd+0.502
 refrain+0.468
olini+0.430
Neg logit contributions
cember-0.574
isphere-0.563
nir-0.554
andum-0.545
asar-0.543
Token Norwegian
Token ID22158
Feature activation+5.57e-01

Pos logit contributions
heid+0.650
hips+0.553
ertodd+0.533
 refrain+0.495
olini+0.450
Neg logit contributions
cember-0.693
isphere-0.680
nir-0.672
andum-0.662
asar-0.660
Token Police
Token ID4287
Feature activation+5.56e-01

Pos logit contributions
cember+1.460
isphere+1.436
nir+1.420
andum+1.394
asar+1.389
Neg logit contributions
heid-1.450
hips-1.242
ertodd-1.207
 refrain-1.099
olini-1.018
Token Security
Token ID4765
Feature activation+5.11e-01

Pos logit contributions
cember+1.476
isphere+1.448
nir+1.433
andum+1.412
asar+1.406
Neg logit contributions
heid-1.432
hips-1.219
ertodd-1.184
 refrain-1.085
olini-0.995
Token Service
Token ID4809
Feature activation-4.97e-01

Pos logit contributions
cember+1.428
isphere+1.403
nir+1.391
andum+1.372
asar+1.367
Neg logit contributions
heid-1.241
hips-1.046
ertodd-1.016
 refrain-0.924
olini-0.842
Token informed
Token ID7981
Feature activation-6.84e-01

Pos logit contributions
heid+1.372
hips+1.194
ertodd+1.139
 refrain+1.080
olini+0.988
Neg logit contributions
cember-1.225
isphere-1.197
nir-1.180
andum-1.163
asar-1.156
Token that
Token ID326
Feature activation-4.54e-01

Pos logit contributions
heid+1.831
hips+1.574
ertodd+1.511
 refrain+1.421
olini+1.300
Neg logit contributions
cember-1.741
isphere-1.706
nir-1.685
andum-1.656
asar-1.652
Token country
Token ID1499
Feature activation+1.39e-01

Pos logit contributions
heid+1.190
hips+1.022
ertodd+0.980
 refrain+0.918
olini+0.837
Neg logit contributions
cember-1.182
isphere-1.159
nir-1.142
andum-1.126
asar-1.120
Token
Token ID447
Feature activation+8.68e-02

Pos logit contributions
cember+0.322
isphere+0.315
nir+0.311
andum+0.305
asar+0.304
Neg logit contributions
heid-0.404
hips-0.351
ertodd-0.341
 refrain-0.318
olini-0.295
Tokenup
Token ID929
Feature activation+6.44e-01

Pos logit contributions
heid+1.794
hips+1.571
ertodd+1.518
 refrain+1.426
olini+1.324
Neg logit contributions
cember-1.394
isphere-1.356
nir-1.339
andum-1.317
asar-1.312
Token -
Token ID532
Feature activation-9.50e-01

Pos logit contributions
cember+1.571
isphere+1.562
nir+1.539
andum+1.507
istical+1.503
Neg logit contributions
heid-1.776
hips-1.520
ertodd-1.492
 refrain-1.370
olini-1.273
Token you
Token ID345
Feature activation+5.53e-01

Pos logit contributions
heid+2.437
hips+2.095
ertodd+1.997
 refrain+1.887
olini+1.704
Neg logit contributions
cember-2.522
isphere-2.456
nir-2.433
andum-2.401
asar-2.376
Token can
Token ID460
Feature activation+1.24e+00

Pos logit contributions
cember+1.335
isphere+1.315
nir+1.298
andum+1.274
asar+1.273
Neg logit contributions
heid-1.547
hips-1.323
ertodd-1.307
 refrain-1.184
olini-1.115
Token setup
Token ID9058
Feature activation+1.34e-01

Pos logit contributions
cember+3.389
isphere+3.382
nir+3.342
andum+3.296
ause+3.285
Neg logit contributions
heid-2.974
ertodd-2.508
hips-2.442
 refrain-2.061
olini-2.033
Token in
Token ID287
Feature activation-6.16e-01

Pos logit contributions
cember+0.335
isphere+0.328
nir+0.324
andum+0.319
asar+0.318
Neg logit contributions
heid-0.369
hips-0.317
ertodd-0.308
 refrain-0.286
olini-0.264
Token five
Token ID1936
Feature activation-5.54e-01

Pos logit contributions
heid+1.752
hips+1.528
ertodd+1.463
 refrain+1.390
olini+1.267
Neg logit contributions
cember-1.468
isphere-1.441
nir-1.418
andum-1.391
istical-1.377
Token to
Token ID284
Feature activation-9.66e-01

Pos logit contributions
heid+1.564
hips+1.359
ertodd+1.310
 refrain+1.233
olini+1.127
Neg logit contributions
cember-1.335
isphere-1.298
nir-1.286
andum-1.272
asar-1.256
Token ten
Token ID3478
Feature activation-3.89e-01

Pos logit contributions
heid+2.479
hips+2.119
ertodd+2.033
 refrain+1.918
olini+1.716
Neg logit contributions
cember-2.566
isphere-2.501
nir-2.487
andum-2.457
istical-2.427
Token minutes
Token ID2431
Feature activation+1.76e-01

Pos logit contributions
heid+1.113
hips+0.968
ertodd+0.937
 refrain+0.878
olini+0.808
Neg logit contributions
cember-0.922
isphere-0.900
nir-0.890
andum-0.877
asar-0.870
Token,
Token ID11
Feature activation+8.27e-02

Pos logit contributions
cember+0.445
isphere+0.437
nir+0.431
andum+0.424
asar+0.423
Neg logit contributions
heid-0.473
hips-0.405
ertodd-0.394
 refrain-0.365
olini-0.336
Token would
Token ID561
Feature activation+2.93e-01

Pos logit contributions
cember+3.759
isphere+3.678
nir+3.648
asar+3.607
andum+3.575
Neg logit contributions
heid-4.494
hips-3.901
ertodd-3.865
 refrain-3.534
olini-3.326
Token have
Token ID423
Feature activation+4.71e-01

Pos logit contributions
cember+0.822
isphere+0.805
nir+0.800
andum+0.791
asar+0.787
Neg logit contributions
heid-0.709
hips-0.591
ertodd-0.578
 refrain-0.521
olini-0.482
Token to
Token ID284
Feature activation-8.56e-01

Pos logit contributions
cember+1.090
isphere+1.066
nir+1.052
andum+1.033
asar+1.030
Neg logit contributions
heid-1.372
hips-1.192
ertodd-1.162
 refrain-1.084
olini-1.006
Token be
Token ID307
Feature activation-1.43e-01

Pos logit contributions
heid+1.711
hips+1.402
ertodd+1.316
 refrain+1.203
olini+1.029
Neg logit contributions
cember-2.769
isphere-2.723
nir-2.687
asar-2.655
andum-2.654
Token constructed
Token ID12006
Feature activation+4.10e-01

Pos logit contributions
heid+0.449
hips+0.398
ertodd+0.382
 refrain+0.363
olini+0.336
Neg logit contributions
cember-0.300
isphere-0.291
nir-0.286
andum-0.281
istical-0.279
Token,
Token ID11
Feature activation+1.53e-01

Pos logit contributions
cember+1.034
isphere+1.016
nir+1.003
andum+0.987
asar+0.984
Neg logit contributions
heid-1.110
hips-0.951
ertodd-0.927
 refrain-0.858
olini-0.791
Token and
Token ID290
Feature activation-3.05e-01

Pos logit contributions
cember+0.400
isphere+0.393
nir+0.390
andum+0.383
asar+0.383
Neg logit contributions
heid-0.401
hips-0.341
ertodd-0.333
 refrain-0.304
olini-0.281
Token the
Token ID262
Feature activation-2.25e-02

Pos logit contributions
heid+0.805
hips+0.690
ertodd+0.665
 refrain+0.619
olini+0.566
Neg logit contributions
cember-0.793
isphere-0.777
nir-0.766
andum-0.756
asar-0.753
Token project
Token ID1628
Feature activation+5.93e-01

Pos logit contributions
heid+0.061
hips+0.053
ertodd+0.051
 refrain+0.048
olini+0.044
Neg logit contributions
cember-0.057
isphere-0.055
nir-0.055
andum-0.054
asar-0.053
Token would
Token ID561
Feature activation+1.85e-01

Pos logit contributions
cember+1.423
isphere+1.405
nir+1.377
asar+1.355
andum+1.354
Neg logit contributions
heid-1.663
hips-1.441
ertodd-1.410
 refrain-1.297
olini-1.209
Token be
Token ID307
Feature activation+2.03e-02

Pos logit contributions
cember+0.548
isphere+0.536
nir+0.533
andum+0.527
asar+0.524
Neg logit contributions
heid-0.422
hips-0.346
ertodd-0.338
 refrain-0.299
olini-0.278
Token Furthermore
Token ID11399
Feature activation-1.64e-02

Pos logit contributions
cember+0.500
isphere+0.490
nir+0.484
andum+0.477
asar+0.475
Neg logit contributions
heid-0.525
hips-0.450
ertodd-0.437
 refrain-0.405
olini-0.372
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
heid+0.048
hips+0.042
ertodd+0.040
 refrain+0.038
olini+0.035
Neg logit contributions
cember-0.038
isphere-0.037
nir-0.037
andum-0.036
asar-0.036
Token the
Token ID262
Feature activation-2.69e-01

Pos logit contributions
heid+2.617
hips+2.260
ertodd+2.143
 refrain+2.040
olini+1.832
Neg logit contributions
cember-2.720
isphere-2.645
nir-2.612
andum-2.585
istical-2.570
Token only
Token ID691
Feature activation-5.34e-01

Pos logit contributions
heid+0.714
hips+0.614
ertodd+0.591
 refrain+0.554
olini+0.504
Neg logit contributions
cember-0.693
isphere-0.678
nir-0.669
andum-0.661
asar-0.656
Token speakers
Token ID11636
Feature activation+3.78e-01

Pos logit contributions
heid+1.435
hips+1.244
ertodd+1.188
 refrain+1.138
olini+1.025
Neg logit contributions
cember-1.352
isphere-1.317
nir-1.299
andum-1.283
asar-1.275
Token I
Token ID314
Feature activation+3.83e-02

Pos logit contributions
cember+1.020
isphere+1.008
nir+0.995
andum+0.977
asar+0.976
Neg logit contributions
heid-0.953
hips-0.795
ertodd-0.786
 refrain-0.715
olini-0.657
Token
Token ID447
Feature activation-1.73e-01

Pos logit contributions
cember+0.098
isphere+0.096
nir+0.095
andum+0.094
asar+0.093
Neg logit contributions
heid-0.102
hips-0.087
ertodd-0.085
 refrain-0.078
olini-0.072
Token
Token ID247
Feature activation-2.34e-01

Pos logit contributions
heid+0.624
hips+0.562
ertodd+0.546
 refrain+0.520
olini+0.491
Neg logit contributions
cember-0.281
isphere-0.272
nir-0.268
asar-0.261
andum-0.260
Tokenve
Token ID303
Feature activation+1.22e+00

Pos logit contributions
heid+0.680
hips+0.591
ertodd+0.575
 refrain+0.536
olini+0.497
Neg logit contributions
cember-0.543
isphere-0.531
nir-0.525
andum-0.516
asar-0.513
Token heard
Token ID2982
Feature activation+8.62e-02

Pos logit contributions
cember+2.794
isphere+2.740
nir+2.711
andum+2.643
asar+2.627
Neg logit contributions
heid-3.558
hips-3.062
ertodd-3.024
 refrain-2.768
olini-2.610
Token that
Token ID326
Feature activation+7.17e-01

Pos logit contributions
cember+0.227
isphere+0.223
nir+0.220
andum+0.217
asar+0.216
Neg logit contributions
heid-0.225
hips-0.191
ertodd-0.185
 refrain-0.171
olini-0.157
Token in
Token ID287
Feature activation+6.41e-01

Pos logit contributions
cember+0.346
isphere+0.339
nir+0.335
andum+0.329
asar+0.329
Neg logit contributions
heid-0.352
hips-0.303
ertodd-0.291
 refrain-0.271
olini-0.248
Token loans
Token ID10021
Feature activation-2.37e-01

Pos logit contributions
cember+1.630
isphere+1.592
nir+1.578
andum+1.556
asar+1.549
Neg logit contributions
heid-1.724
hips-1.474
ertodd-1.437
 refrain-1.322
olini-1.220
Token from
Token ID422
Feature activation-5.41e-01

Pos logit contributions
heid+0.622
hips+0.536
ertodd+0.513
 refrain+0.479
olini+0.438
Neg logit contributions
cember-0.617
isphere-0.605
nir-0.598
andum-0.588
asar-0.586
Token I
Token ID314
Feature activation-5.19e-01

Pos logit contributions
heid+1.403
hips+1.201
ertodd+1.152
 refrain+1.076
olini+0.983
Neg logit contributions
cember-1.422
isphere-1.403
nir-1.376
andum-1.356
istical-1.348
Tokenhor
Token ID17899
Feature activation-3.99e-01

Pos logit contributions
heid+1.467
hips+1.269
ertodd+1.221
 refrain+1.143
olini+1.060
Neg logit contributions
cember-1.248
isphere-1.222
nir-1.211
andum-1.185
asar-1.178
Token Kol
Token ID25910
Feature activation-9.03e-01

Pos logit contributions
heid+1.138
hips+0.987
ertodd+0.944
 refrain+0.889
olini+0.824
Neg logit contributions
cember-0.952
isphere-0.933
nir-0.916
andum-0.901
asar-0.897
Tokenomo
Token ID17902
Feature activation-1.21e+00

Pos logit contributions
heid+2.799
hips+2.427
ertodd+2.307
 refrain+2.178
olini+2.083
Neg logit contributions
cember-1.932
isphere-1.877
andum-1.819
nir-1.815
istical-1.786
Tokenisky
Token ID34041
Feature activation-6.09e-01

Pos logit contributions
heid+3.563
hips+3.094
ertodd+2.941
 refrain+2.775
olini+2.596
Neg logit contributions
cember-2.756
isphere-2.714
nir-2.647
andum-2.607
istical-2.579
Token's
Token ID338
Feature activation-9.67e-01

Pos logit contributions
heid+1.675
hips+1.447
ertodd+1.374
 refrain+1.290
olini+1.199
Neg logit contributions
cember-1.519
isphere-1.491
nir-1.454
andum-1.435
istical-1.427
Token Priv
Token ID9243
Feature activation-4.03e-02

Pos logit contributions
heid+2.540
hips+2.167
ertodd+2.063
 refrain+1.940
olini+1.777
Neg logit contributions
cember-2.515
isphere-2.474
nir-2.430
andum-2.405
istical-2.388
Tokenat
Token ID265
Feature activation+1.01e+00

Pos logit contributions
heid+0.143
hips+0.128
ertodd+0.125
 refrain+0.118
olini+0.111
Neg logit contributions
cember-0.068
isphere-0.066
nir-0.065
andum-0.063
asar-0.063
Token a
Token ID257
Feature activation-2.34e-01

Pos logit contributions
heid+1.568
hips+1.340
ertodd+1.289
 refrain+1.202
olini+1.095
Neg logit contributions
cember-1.597
isphere-1.568
nir-1.547
andum-1.524
asar-1.521
Token very
Token ID845
Feature activation-2.94e-02

Pos logit contributions
heid+0.616
hips+0.527
ertodd+0.507
 refrain+0.475
olini+0.433
Neg logit contributions
cember-0.611
isphere-0.600
nir-0.592
andum-0.584
asar-0.582
Token active
Token ID4075
Feature activation-1.55e+00

Pos logit contributions
heid+0.084
hips+0.073
ertodd+0.070
 refrain+0.066
olini+0.061
Neg logit contributions
cember-0.070
isphere-0.068
nir-0.068
andum-0.067
asar-0.066
Token November
Token ID3389
Feature activation-1.32e+00

Pos logit contributions
heid+3.927
hips+3.345
ertodd+3.097
 refrain+3.088
olini+2.725
Neg logit contributions
cember-4.088
isphere-4.068
nir-4.016
andum-3.956
asar-3.938
Token Project
Token ID4935
Feature activation-2.77e-01

Pos logit contributions
heid+3.668
hips+3.183
ertodd+3.086
 refrain+2.902
olini+2.674
Neg logit contributions
cember-3.192
isphere-3.137
nir-3.099
asar-3.035
andum-3.033
Token group
Token ID1448
Feature activation-8.40e-01

Pos logit contributions
heid+0.612
hips+0.507
ertodd+0.485
 refrain+0.444
olini+0.395
Neg logit contributions
cember-0.838
isphere-0.824
nir-0.816
andum-0.806
asar-0.803
Token in
Token ID287
Feature activation+8.73e-02

Pos logit contributions
heid+2.176
hips+1.887
ertodd+1.787
 refrain+1.680
olini+1.524
Neg logit contributions
cember-2.200
isphere-2.154
nir-2.147
andum-2.112
asar-2.090
Token Edmonton
Token ID21165
Feature activation+1.16e+00

Pos logit contributions
cember+0.239
isphere+0.232
nir+0.231
andum+0.228
asar+0.227
Neg logit contributions
heid-0.218
hips-0.185
ertodd-0.180
 refrain-0.164
olini-0.149
Token that
Token ID326
Feature activation+5.08e-01

Pos logit contributions
cember+2.816
isphere+2.747
nir+2.681
asar+2.660
andum+2.648
Neg logit contributions
heid-3.230
hips-2.752
ertodd-2.740
 refrain-2.527
olini-2.326
Token regularly
Token ID7987
Feature activation-1.57e+00

Pos logit contributions
cember+1.282
isphere+1.243
nir+1.225
andum+1.201
asar+1.199
Neg logit contributions
heid-1.383
hips-1.182
ertodd-1.165
 refrain-1.056
olini-0.988
Token draws
Token ID14293
Feature activation-3.66e-01

Pos logit contributions
heid+4.102
hips+3.606
ertodd+3.350
 refrain+3.245
olini+2.899
Neg logit contributions
cember-3.987
isphere-3.939
nir-3.918
andum-3.888
asar-3.837
Token9
Token ID24
Feature activation-7.46e-01

Pos logit contributions
cember+1.325
isphere+1.301
nir+1.288
andum+1.265
asar+1.263
Neg logit contributions
heid-1.076
hips-0.897
ertodd-0.878
 refrain-0.802
olini-0.721
Token in
Token ID287
Feature activation-6.61e-02

Pos logit contributions
heid+1.877
hips+1.612
ertodd+1.520
 refrain+1.437
olini+1.292
Neg logit contributions
cember-2.012
isphere-1.973
nir-1.948
andum-1.924
asar-1.920
Token college
Token ID4152
Feature activation-1.66e-01

Pos logit contributions
heid+0.177
hips+0.152
ertodd+0.146
 refrain+0.137
olini+0.125
Neg logit contributions
cember-0.169
isphere-0.166
nir-0.164
andum-0.161
asar-0.160
Token at
Token ID379
Feature activation-3.78e-01

Pos logit contributions
heid+0.447
hips+0.384
ertodd+0.372
 refrain+0.345
olini+0.317
Neg logit contributions
cember-0.421
isphere-0.413
nir-0.408
andum-0.402
asar-0.400
Token St
Token ID520
Feature activation-3.17e-01

Pos logit contributions
heid+0.972
hips+0.830
ertodd+0.797
 refrain+0.742
olini+0.674
Neg logit contributions
cember-1.008
isphere-0.990
nir-0.977
andum-0.962
asar-0.958
Token.
Token ID13
Feature activation-1.82e+00

Pos logit contributions
heid+0.866
hips+0.746
ertodd+0.722
 refrain+0.671
olini+0.618
Neg logit contributions
cember-0.793
isphere-0.777
nir-0.767
andum-0.755
asar-0.752
Token Louis
Token ID5593
Feature activation-1.02e+00

Pos logit contributions
heid+4.343
hips+3.651
ertodd+3.334
 refrain+3.130
olini+2.857
Neg logit contributions
cember-5.160
isphere-5.042
nir-4.965
andum-4.892
asar-4.867
Token,
Token ID11
Feature activation-4.13e-01

Pos logit contributions
heid+2.699
hips+2.347
ertodd+2.205
 refrain+2.080
olini+1.895
Neg logit contributions
cember-2.617
isphere-2.583
nir-2.544
andum-2.493
asar-2.488
Token measured
Token ID8630
Feature activation+1.08e+00

Pos logit contributions
heid+1.116
hips+0.964
ertodd+0.918
 refrain+0.868
olini+0.792
Neg logit contributions
cember-1.043
isphere-1.024
nir-1.010
andum-0.992
asar-0.990
Token in
Token ID287
Feature activation-3.88e-01

Pos logit contributions
cember+2.581
isphere+2.535
nir+2.508
andum+2.466
asar+2.455
Neg logit contributions
heid-3.048
hips-2.622
ertodd-2.569
 refrain-2.365
olini-2.191
Token at
Token ID379
Feature activation-8.16e-01

Pos logit contributions
heid+1.157
hips+1.019
ertodd+0.979
 refrain+0.929
olini+0.861
Neg logit contributions
cember-0.868
isphere-0.849
nir-0.835
andum-0.824
asar-0.820
Token their
Token ID511
Feature activation-3.29e-01

Pos logit contributions
heid+4.230
hips+3.792
ertodd+3.461
 refrain+3.317
olini+2.978
Neg logit contributions
cember-4.181
isphere-4.097
nir-4.004
andum-3.975
asar-3.935
Token benefits
Token ID4034
Feature activation-2.00e-01

Pos logit contributions
heid+0.854
hips+0.733
ertodd+0.704
 refrain+0.654
olini+0.598
Neg logit contributions
cember-0.868
isphere-0.852
nir-0.842
andum-0.829
asar-0.825
Token.
Token ID13
Feature activation+6.85e-01

Pos logit contributions
heid+0.467
hips+0.392
ertodd+0.377
 refrain+0.345
olini+0.311
Neg logit contributions
cember-0.581
isphere-0.570
nir-0.564
andum-0.557
asar-0.555
Token But
Token ID887
Feature activation-1.47e+00

Pos logit contributions
cember+1.630
nir+1.585
isphere+1.581
andum+1.577
asar+1.564
Neg logit contributions
heid-1.913
hips-1.630
ertodd-1.608
 refrain-1.491
olini-1.382
Token Prime
Token ID5537
Feature activation-1.13e+00

Pos logit contributions
heid+3.697
hips+3.228
ertodd+3.018
 refrain+2.897
olini+2.597
Neg logit contributions
cember-3.913
isphere-3.840
nir-3.785
asar-3.717
istical-3.697
Token members
Token ID1866
Feature activation-1.78e+00

Pos logit contributions
heid+2.475
hips+2.077
ertodd+1.957
 refrain+1.800
olini+1.610
Neg logit contributions
cember-3.410
isphere-3.360
nir-3.328
andum-3.275
asar-3.268
Token with
Token ID351
Feature activation+1.02e+00

Pos logit contributions
heid+4.597
hips+4.143
ertodd+3.764
 refrain+3.639
olini+3.230
Neg logit contributions
cember-4.652
isphere-4.521
nir-4.486
andum-4.425
asar-4.395
Token Amazon
Token ID6186
Feature activation+3.98e-01

Pos logit contributions
cember+2.544
isphere+2.490
nir+2.456
andum+2.441
asar+2.428
Neg logit contributions
heid-2.760
hips-2.310
ertodd-2.307
 refrain-2.095
olini-1.964
Token Mom
Token ID11254
Feature activation-7.03e-01

Pos logit contributions
cember+1.049
isphere+1.023
nir+1.014
andum+1.001
asar+0.997
Neg logit contributions
heid-1.030
hips-0.866
ertodd-0.854
 refrain-0.784
olini-0.715
Token can
Token ID460
Feature activation+1.11e-01

Pos logit contributions
heid+1.780
hips+1.531
ertodd+1.452
 refrain+1.352
olini+1.234
Neg logit contributions
cember-1.895
isphere-1.856
nir-1.832
asar-1.810
andum-1.805
Token share
Token ID2648
Feature activation-1.51e+00

Pos logit contributions
cember+0.273
isphere+0.267
nir+0.265
andum+0.260
asar+0.259
Neg logit contributions
heid-0.306
hips-0.262
ertodd-0.257
 refrain-0.236
olini-0.220
Tokens
Token ID82
Feature activation+3.74e-01

Pos logit contributions
cember+0.438
isphere+0.429
nir+0.423
andum+0.417
asar+0.415
Neg logit contributions
heid-0.491
hips-0.425
ertodd-0.409
 refrain-0.383
olini-0.352
Token maybe
Token ID3863
Feature activation+6.97e-01

Pos logit contributions
cember+0.883
isphere+0.863
nir+0.852
andum+0.838
asar+0.835
Neg logit contributions
heid-1.074
hips-0.932
ertodd-0.905
 refrain-0.844
olini-0.781
Token what
Token ID644
Feature activation+1.13e-01

Pos logit contributions
cember+1.672
isphere+1.632
nir+1.618
andum+1.589
asar+1.582
Neg logit contributions
heid-1.978
hips-1.708
ertodd-1.665
 refrain-1.542
olini-1.428
Token makes
Token ID1838
Feature activation+5.20e-02

Pos logit contributions
cember+0.280
isphere+0.275
nir+0.270
andum+0.266
asar+0.265
Neg logit contributions
heid-0.310
hips-0.267
ertodd-0.258
 refrain-0.241
olini-0.222
Token everyone
Token ID2506
Feature activation-4.05e-01

Pos logit contributions
cember+0.131
isphere+0.128
nir+0.127
andum+0.125
asar+0.124
Neg logit contributions
heid-0.141
hips-0.122
ertodd-0.118
 refrain-0.109
olini-0.101
Token love
Token ID1842
Feature activation-2.66e+00

Pos logit contributions
heid+1.087
hips+0.944
ertodd+0.902
 refrain+0.853
olini+0.771
Neg logit contributions
cember-1.028
isphere-1.010
nir-0.992
andum-0.984
asar-0.974
Token games
Token ID1830
Feature activation+6.43e-01

Pos logit contributions
heid+6.472
hips+5.708
ertodd+5.068
 refrain+4.990
olini+4.521
Neg logit contributions
cember-6.984
isphere-6.847
nir-6.739
asar-6.658
andum-6.594
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
cember+1.538
isphere+1.505
nir+1.486
asar+1.461
andum+1.461
Neg logit contributions
heid-1.820
hips-1.560
ertodd-1.534
 refrain-1.421
olini-1.315
Token
Token ID198
Feature activation-2.36e-01

Pos logit contributions
cember+0.315
isphere+0.308
nir+0.304
andum+0.300
asar+0.299
Neg logit contributions
heid-0.340
hips-0.293
ertodd-0.283
 refrain-0.264
olini-0.242
Token
Token ID198
Feature activation+4.02e-01

Pos logit contributions
heid+0.613
hips+0.527
ertodd+0.501
 refrain+0.467
olini+0.425
Neg logit contributions
cember-0.629
isphere-0.617
nir-0.604
andum-0.597
asar-0.592
TokenThat
Token ID2504
Feature activation+1.09e+00

Pos logit contributions
cember+0.863
isphere+0.842
nir+0.829
andum+0.815
asar+0.811
Neg logit contributions
heid-1.240
hips-1.089
ertodd-1.056
 refrain-0.993
olini-0.925
TokenK
Token ID42
Feature activation-2.89e+00

Pos logit contributions
heid+0.450
hips+0.392
ertodd+0.378
 refrain+0.353
olini+0.329
Neg logit contributions
cember-0.359
isphere-0.348
nir-0.341
andum-0.337
asar-0.334
Tokenernel
Token ID7948
Feature activation-6.04e-01

Pos logit contributions
heid+4.106
hips+3.152
ertodd+2.966
creen+2.234
olini+2.067
Neg logit contributions
cember-10.671
isphere-10.071
andum-9.821
istical-9.752
nir-9.688
Token =
Token ID796
Feature activation-7.60e-01

Pos logit contributions
heid+1.703
hips+1.477
ertodd+1.420
 refrain+1.317
olini+1.225
Neg logit contributions
cember-1.483
isphere-1.434
nir-1.402
andum-1.392
asar-1.372
Token c
Token ID269
Feature activation+3.73e-01

Pos logit contributions
heid+1.693
hips+1.415
ertodd+1.350
 refrain+1.255
olini+1.105
Neg logit contributions
cember-2.277
isphere-2.225
nir-2.208
andum-2.177
asar-2.151
Tokenv
Token ID85
Feature activation-1.75e+00

Pos logit contributions
cember+0.873
isphere+0.855
nir+0.844
andum+0.829
asar+0.826
Neg logit contributions
heid-1.079
hips-0.937
ertodd-0.910
 refrain-0.851
olini-0.787
Token2
Token ID17
Feature activation-1.91e+00

Pos logit contributions
heid+4.539
hips+3.982
ertodd+3.697
 refrain+3.369
creen+3.151
Neg logit contributions
cember-4.616
isphere-4.372
nir-4.212
andum-4.198
utics-4.150
Token.
Token ID13
Feature activation-1.79e+00

Pos logit contributions
heid+4.419
hips+3.808
ertodd+3.457
 refrain+3.166
creen+2.871
Neg logit contributions
cember-5.591
isphere-5.422
nir-5.198
andum-5.184
asar-5.068
Tokenget
Token ID1136
Feature activation-5.42e-01

Pos logit contributions
heid+5.077
hips+4.470
ertodd+4.131
 refrain+3.915
creen+3.705
Neg logit contributions
cember-4.261
isphere-3.990
andum-3.911
istical-3.814
ause-3.803
TokenStruct
Token ID44909
Feature activation-1.44e-01

Pos logit contributions
heid+1.113
hips+0.913
ertodd+0.858
 refrain+0.764
olini+0.675
Neg logit contributions
cember-1.751
isphere-1.707
nir-1.664
asar-1.655
andum-1.649
Tokenuring
Token ID870
Feature activation-6.50e-01

Pos logit contributions
heid+0.451
hips+0.396
ertodd+0.386
 refrain+0.363
olini+0.338
Neg logit contributions
cember-0.301
isphere-0.294
nir-0.289
andum-0.284
asar-0.282
TokenElement
Token ID20180
Feature activation-4.72e-01

Pos logit contributions
heid+1.762
hips+1.510
ertodd+1.445
 refrain+1.348
olini+1.234
Neg logit contributions
cember-1.677
isphere-1.622
nir-1.586
andum-1.565
asar-1.562
Tokend
Token ID67
Feature activation-2.21e-01

Pos logit contributions
heid+1.800
hips+1.575
ertodd+1.511
 refrain+1.436
olini+1.321
Neg logit contributions
cember-1.394
isphere-1.365
nir-1.335
andum-1.321
asar-1.316
Token need
Token ID761
Feature activation+2.57e-01

Pos logit contributions
heid+0.527
hips+0.443
ertodd+0.421
 refrain+0.393
olini+0.352
Neg logit contributions
cember-0.633
isphere-0.622
nir-0.615
andum-0.606
asar-0.605
Token a
Token ID257
Feature activation+1.97e-01

Pos logit contributions
cember+0.609
isphere+0.596
nir+0.587
andum+0.578
asar+0.576
Neg logit contributions
heid-0.737
hips-0.640
ertodd-0.619
 refrain-0.580
olini-0.535
Token 7
Token ID767
Feature activation-3.25e-01

Pos logit contributions
cember+0.507
isphere+0.497
nir+0.492
andum+0.484
asar+0.482
Neg logit contributions
heid-0.520
hips-0.447
ertodd-0.434
 refrain-0.398
olini-0.368
Token
Token ID1906
Feature activation-9.33e-01

Pos logit contributions
heid+0.871
hips+0.746
ertodd+0.716
 refrain+0.674
olini+0.614
Neg logit contributions
cember-0.831
isphere-0.816
nir-0.800
andum-0.793
asar-0.787
Tokenletter
Token ID9291
Feature activation-1.82e+00

Pos logit contributions
heid+2.728
hips+2.361
ertodd+2.237
 refrain+2.144
olini+1.976
Neg logit contributions
cember-2.161
isphere-2.105
nir-2.058
andum-2.046
asar-2.027
Token Scottish
Token ID11905
Feature activation+1.20e-01

Pos logit contributions
heid+4.641
hips+3.907
 refrain+3.633
ertodd+3.616
olini+3.102
Neg logit contributions
cember-4.812
isphere-4.710
nir-4.624
utics-4.538
andum-4.523
Token team
Token ID1074
Feature activation-7.94e-02

Pos logit contributions
cember+0.321
isphere+0.315
nir+0.311
andum+0.307
asar+0.305
Neg logit contributions
heid-0.306
hips-0.261
ertodd-0.252
 refrain-0.232
olini-0.212
Token beginning
Token ID3726
Feature activation+2.70e-01

Pos logit contributions
heid+0.213
hips+0.183
ertodd+0.176
 refrain+0.165
olini+0.150
Neg logit contributions
cember-0.203
isphere-0.199
nir-0.196
andum-0.193
asar-0.193
Token AIR
Token ID31600
Feature activation-1.47e+00

Pos logit contributions
cember+0.690
isphere+0.677
nir+0.669
andum+0.658
asar+0.654
Neg logit contributions
heid-0.720
hips-0.618
ertodd-0.605
 refrain-0.554
olini-0.512
Token
Token ID1906
Feature activation-4.65e-01

Pos logit contributions
heid+4.101
hips+3.569
ertodd+3.345
 refrain+3.240
olini+2.952
Neg logit contributions
cember-3.512
isphere-3.448
nir-3.381
andum-3.322
asar-3.319