TOP ACTIVATIONS
MAX = 6.464

tools such as the Block Bot can help .
era its ) on the Mongol ian Plate au . The
among the Turk ic and Mongol peoples ( especially Ong uts
The most common category of Mongol names were those of ausp
et ernal " in the Mongol ian language ).[ 1 ]
in ) tribe and the Mongol general Mang gh ud ai
America and the Wall Street cabal is their complete lack of
origin were introduced when the Mongol Empire expanded all over Euras
be joined in the next big marriage equality case . This
healing power of water . Bot an ics , on the
in Italy were named after Mongol rulers , including H ü
ents SELECT * FROM [ big query - public - data
support from former Ku Klux Klan leader David Duke . (
do and shared with a bunch of different classes . The
flag in front of a bull . http :// ce pr
alliance 's role as the bul wark of Western defence .
rejected by both Burma and neighbouring Bangladesh . MS
circus . Bring on the clown s , the jug glers
ies The Good Wife CBS Tat iana Mas l any Or
Islands 14 . 6 8 Bots wana 14 . 9 9

MIN ACTIVATIONS
MIN = -6.543

the PAX East app ( iOS , Android ), get it
. Exercise also improves insulin sensitivity . Cal oric
as well as response and remission rates at week four .
usal rules mean judges often pres ide over cases involving major
, they re irre ve rent , they
than three weeks ," says Es a mission manager Dr Rune
it s an obligation , said Morton
you 've now got Lord Hes elt ine saying that he
. Increases insulin sensitivity . Increases lip
slack . The Center for Respons ive Politics has the full
is that we must be responsive the changing environment .
r ims , laced to Suz ue road hubs with an
- aged Italians had been cons cript ed into forced labour
uart H ogg , Tommy Seymour and Lee Jones make up
touch of cl ove ( pres umably from the sa ison
, and they are . Writ es Bridges Out Official :
lower the wife 's life expectancy . This is the case
B art 's owner , Ellis Hut son , told the
a skin condition , an autos omal dominant palm opl ant
it is , without further ado : one man

INTERVAL 3.212 - 6.464
CONTAINS 0.349%

close Bit map $ b mp . Save ($ Out File
by pro - K iev fascists working with Black water mercenaries
and his allies of the Mil itant faction on the one
& Danny Fight With Each other 200 80 205 O &
win for Out standing Supporting Actor in a Comedy , for

INTERVAL -0.040 - 3.212
CONTAINS 51.017%

. But even though Republicans took 10 days off , the
…… .. Dear George ,
and bring around 100 jobs to the surrounding communities .
Democrat who announced his support for the bill Monday , came
catching up to an established fact on the ground : Cities

INTERVAL -3.291 - -0.040
CONTAINS 48.387%

[ nn [ Keys [ search Space ][ [ i ]]
conferences over a three - year period , travelling to California
the camera will pan over or Lem ony will walk into
the U . N . Scientific Committee on the Effects of
eg le , Colorado Hemp Company . The timing

INTERVAL -6.543 - -3.291
CONTAINS 0.246%

s an ambitious rock op us written by and for a
. Walton was taken into custody based upon probable cause ,
is a series about health care from a nurse
usal rules mean judges often pres ide over cases involving major
very small . US Naval React ors average annual
Token tools
Token ID4899
Feature activation+9.11e-01

Pos logit contributions
rieg+0.918
 bloc+0.899
ambo+0.895
anooga+0.875
 Rove+0.866
Neg logit contributions
terday-1.053
 confir-1.020
pring-0.983
clair-0.977
cale-0.933
Token such
Token ID884
Feature activation+6.34e-01

Pos logit contributions
rieg+1.227
ambo+1.210
 bloc+1.201
anooga+1.171
 Rove+1.170
Neg logit contributions
terday-1.138
 confir-1.109
clair-1.053
pring-1.024
cale-0.973
Token as
Token ID355
Feature activation+9.40e-01

Pos logit contributions
rieg+0.925
ambo+0.898
 bloc+0.897
anooga+0.875
 Rove+0.873
Neg logit contributions
terday-0.746
 confir-0.728
pring-0.681
clair-0.676
cale-0.638
Token the
Token ID262
Feature activation+6.90e-01

Pos logit contributions
rieg+1.002
 bloc+0.979
ambo+0.965
anooga+0.937
 Rove+0.936
Neg logit contributions
terday-1.465
 confir-1.413
clair-1.368
pring-1.367
cale-1.308
Token Block
Token ID9726
Feature activation+2.62e+00

Pos logit contributions
rieg+0.807
 bloc+0.790
ambo+0.776
anooga+0.761
 Rove+0.757
Neg logit contributions
terday-1.006
 confir-0.971
clair-0.937
pring-0.933
cale-0.892
Token Bot
Token ID18579
Feature activation+6.46e+00

Pos logit contributions
rieg+3.125
 bloc+3.049
ambo+3.017
anooga+2.929
 Rove+2.924
Neg logit contributions
terday-3.753
 confir-3.608
clair-3.457
pring-3.450
cale-3.332
Token can
Token ID460
Feature activation+1.32e+00

Pos logit contributions
rieg+8.293
ambo+8.195
anooga+8.006
 bloc+7.976
 Rove+7.738
Neg logit contributions
terday-7.863
 confir-7.697
clair-7.319
pring-7.120
cale-6.895
Token help
Token ID1037
Feature activation+5.73e-01

Pos logit contributions
rieg+1.659
 bloc+1.640
ambo+1.630
 Rove+1.550
anooga+1.543
Neg logit contributions
terday-1.767
 confir-1.684
pring-1.644
clair-1.633
cale-1.542
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
rieg+0.739
 bloc+0.726
ambo+0.726
anooga+0.707
 Rove+0.701
Neg logit contributions
terday-0.764
 confir-0.726
pring-0.705
clair-0.704
cale-0.666
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
rieg+0.611
ambo+0.592
 bloc+0.590
anooga+0.577
 Rove+0.577
Neg logit contributions
terday-0.610
 confir-0.603
pring-0.563
clair-0.563
cale-0.537
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
terday+0.191
 confir+0.187
pring+0.176
clair+0.175
cale+0.166
Neg logit contributions
rieg-0.220
ambo-0.213
 bloc-0.211
anooga-0.208
 Rove-0.206
Tokenera
Token ID8607
Feature activation-8.19e-01

Pos logit contributions
rieg+2.816
ambo+2.723
anooga+2.597
 bloc+2.591
 Rove+2.493
Neg logit contributions
terday-3.091
 confir-3.011
pring-2.812
clair-2.791
cale-2.706
Tokenits
Token ID896
Feature activation-1.76e-02

Pos logit contributions
terday+1.054
 confir+1.016
pring+0.977
clair+0.973
cale+0.928
Neg logit contributions
rieg-1.102
ambo-1.071
 bloc-1.060
anooga-1.047
 Rove-1.029
Token)
Token ID8
Feature activation+3.74e-01

Pos logit contributions
terday+0.023
 confir+0.022
clair+0.021
pring+0.021
cale+0.020
Neg logit contributions
rieg-0.024
ambo-0.023
 bloc-0.023
anooga-0.023
 Rove-0.022
Token on
Token ID319
Feature activation-3.06e-01

Pos logit contributions
rieg+0.482
ambo+0.473
 bloc+0.469
anooga+0.457
 Rove+0.453
Neg logit contributions
terday-0.497
 confir-0.480
pring-0.461
clair-0.459
cale-0.438
Token the
Token ID262
Feature activation-1.13e-01

Pos logit contributions
terday+0.459
 confir+0.444
pring+0.431
clair+0.430
cale+0.411
Neg logit contributions
rieg-0.345
ambo-0.334
 bloc-0.334
anooga-0.323
 Rove-0.320
Token Mongol
Token ID42188
Feature activation+5.84e+00

Pos logit contributions
terday+0.171
 confir+0.166
clair+0.161
pring+0.160
cale+0.153
Neg logit contributions
rieg-0.125
 bloc-0.122
ambo-0.120
anooga-0.117
 Rove-0.117
Tokenian
Token ID666
Feature activation+1.36e+00

Pos logit contributions
 bloc+6.587
rieg+6.484
ambo+6.375
 Rove+6.053
anooga+5.873
Neg logit contributions
terday-8.276
 confir-7.913
clair-7.721
pring-7.474
utics-7.211
Token Plate
Token ID23648
Feature activation+1.14e+00

Pos logit contributions
rieg+1.494
 bloc+1.483
ambo+1.446
 Rove+1.393
anooga+1.370
Neg logit contributions
terday-2.061
 confir-1.985
clair-1.922
pring-1.904
utics-1.817
Tokenau
Token ID559
Feature activation-7.07e-01

Pos logit contributions
rieg+1.297
ambo+1.277
 bloc+1.273
anooga+1.227
 Rove+1.219
Neg logit contributions
terday-1.703
 confir-1.649
pring-1.586
clair-1.569
cale-1.484
Token.
Token ID13
Feature activation-7.89e-01

Pos logit contributions
terday+0.847
 confir+0.813
pring+0.778
clair+0.775
cale+0.734
Neg logit contributions
rieg-1.015
ambo-0.989
 bloc-0.982
anooga-0.966
 Rove-0.952
Token The
Token ID383
Feature activation-5.56e-01

Pos logit contributions
terday+1.080
 confir+1.044
pring+1.007
clair+1.002
cale+0.958
Neg logit contributions
rieg-0.994
ambo-0.964
 bloc-0.953
anooga-0.943
 Rove-0.924
Token among
Token ID1871
Feature activation+8.39e-01

Pos logit contributions
terday+0.855
 confir+0.828
clair+0.793
pring+0.792
cale+0.754
Neg logit contributions
rieg-0.891
ambo-0.869
 bloc-0.863
anooga-0.842
 Rove-0.833
Token the
Token ID262
Feature activation-2.20e-01

Pos logit contributions
rieg+0.664
ambo+0.630
 bloc+0.629
anooga+0.600
 Rove+0.598
Neg logit contributions
terday-1.541
 confir-1.502
clair-1.467
pring-1.462
cale-1.409
Token Turk
Token ID8484
Feature activation+1.97e+00

Pos logit contributions
terday+0.441
 confir+0.431
pring+0.420
clair+0.420
cale+0.407
Neg logit contributions
rieg-0.137
ambo-0.129
 bloc-0.127
anooga-0.122
 Rove-0.119
Tokenic
Token ID291
Feature activation-4.21e-01

Pos logit contributions
rieg+2.365
 bloc+2.261
ambo+2.258
anooga+2.189
 Rove+2.145
Neg logit contributions
terday-2.880
 confir-2.739
clair-2.638
pring-2.636
cale-2.522
Token and
Token ID290
Feature activation-2.87e-01

Pos logit contributions
terday+0.635
 confir+0.615
pring+0.595
clair+0.593
cale+0.569
Neg logit contributions
rieg-0.475
ambo-0.458
 bloc-0.454
anooga-0.446
 Rove-0.437
Token Mongol
Token ID42188
Feature activation+5.84e+00

Pos logit contributions
terday+0.489
 confir+0.475
pring+0.463
clair+0.462
cale+0.444
Neg logit contributions
rieg-0.265
ambo-0.255
 bloc-0.253
anooga-0.244
 Rove-0.243
Token peoples
Token ID14366
Feature activation+1.28e+00

Pos logit contributions
rieg+5.902
 bloc+5.803
ambo+5.766
 Rove+5.427
anooga+5.270
Neg logit contributions
terday-8.941
 confir-8.599
clair-8.538
pring-8.317
utics-7.971
Token (
Token ID357
Feature activation+8.16e-03

Pos logit contributions
rieg+1.770
 bloc+1.744
ambo+1.738
 Rove+1.676
anooga+1.664
Neg logit contributions
terday-1.561
 confir-1.518
clair-1.445
pring-1.429
cale-1.355
Tokenespecially
Token ID16480
Feature activation+1.80e+00

Pos logit contributions
rieg+0.010
ambo+0.010
 bloc+0.009
anooga+0.009
 Rove+0.009
Neg logit contributions
terday-0.012
 confir-0.011
pring-0.011
clair-0.011
cale-0.010
Token Ong
Token ID48041
Feature activation+1.18e+00

Pos logit contributions
rieg+1.953
ambo+1.898
 bloc+1.888
 Rove+1.834
anooga+1.805
Neg logit contributions
terday-2.750
 confir-2.659
clair-2.588
pring-2.574
cale-2.465
Tokenuts
Token ID5500
Feature activation+4.34e-01

Pos logit contributions
rieg+1.503
ambo+1.472
 bloc+1.442
anooga+1.420
 Rove+1.384
Neg logit contributions
terday-1.603
 confir-1.554
pring-1.482
clair-1.480
cale-1.408
TokenThe
Token ID464
Feature activation-3.36e-01

Pos logit contributions
terday+0.276
 confir+0.272
pring+0.255
clair+0.254
cale+0.242
Neg logit contributions
rieg-0.271
ambo-0.262
 bloc-0.257
anooga-0.255
 Rove-0.251
Token most
Token ID749
Feature activation+1.49e+00

Pos logit contributions
terday+0.592
 confir+0.578
pring+0.562
clair+0.562
cale+0.540
Neg logit contributions
rieg-0.293
 bloc-0.279
ambo-0.278
anooga-0.266
 Rove-0.264
Token common
Token ID2219
Feature activation-5.32e-01

Pos logit contributions
rieg+1.642
 bloc+1.607
ambo+1.562
 Rove+1.516
anooga+1.486
Neg logit contributions
terday-2.252
 confir-2.156
clair-2.110
pring-2.108
cale-2.019
Token category
Token ID6536
Feature activation+6.19e-02

Pos logit contributions
terday+0.808
 confir+0.785
clair+0.763
pring+0.759
cale+0.727
Neg logit contributions
rieg-0.589
 bloc-0.567
ambo-0.567
anooga-0.550
 Rove-0.544
Token of
Token ID286
Feature activation-2.09e-01

Pos logit contributions
rieg+0.086
ambo+0.084
 bloc+0.083
anooga+0.081
 Rove+0.081
Neg logit contributions
terday-0.077
 confir-0.074
clair-0.071
pring-0.071
cale-0.067
Token Mongol
Token ID42188
Feature activation+5.74e+00

Pos logit contributions
terday+0.384
 confir+0.375
clair+0.366
pring+0.365
cale+0.352
Neg logit contributions
rieg-0.164
 bloc-0.156
ambo-0.156
anooga-0.149
 Rove-0.147
Token names
Token ID3891
Feature activation-6.95e-01

Pos logit contributions
rieg+5.190
 bloc+5.075
ambo+5.061
 Rove+4.742
anooga+4.566
Neg logit contributions
terday-9.287
 confir-8.994
clair-8.967
pring-8.763
cale-8.327
Token were
Token ID547
Feature activation+1.09e+00

Pos logit contributions
terday+0.925
 confir+0.898
clair+0.863
pring+0.856
cale+0.814
Neg logit contributions
rieg-0.895
ambo-0.872
 bloc-0.868
anooga-0.843
 Rove-0.838
Token those
Token ID883
Feature activation+2.87e-01

Pos logit contributions
rieg+1.300
 bloc+1.265
ambo+1.262
 Rove+1.220
anooga+1.206
Neg logit contributions
terday-1.537
 confir-1.480
clair-1.455
pring-1.444
cale-1.373
Token of
Token ID286
Feature activation-5.50e-01

Pos logit contributions
rieg+0.368
 bloc+0.358
ambo+0.357
 Rove+0.345
anooga+0.341
Neg logit contributions
terday-0.387
 confir-0.370
clair-0.360
pring-0.357
cale-0.340
Token ausp
Token ID45062
Feature activation-1.08e+00

Pos logit contributions
terday+0.829
 confir+0.804
pring+0.777
clair+0.776
cale+0.743
Neg logit contributions
rieg-0.617
ambo-0.595
 bloc-0.590
anooga-0.578
 Rove-0.570
Tokenet
Token ID316
Feature activation+1.48e+00

Pos logit contributions
rieg+0.090
ambo+0.088
 bloc+0.086
anooga+0.086
 Rove+0.084
Neg logit contributions
terday-0.098
 confir-0.096
pring-0.090
clair-0.090
cale-0.086
Tokenernal
Token ID35220
Feature activation-4.69e-01

Pos logit contributions
rieg+1.521
ambo+1.477
 bloc+1.441
anooga+1.409
 Rove+1.381
Neg logit contributions
terday-2.375
 confir-2.311
clair-2.207
pring-2.204
cale-2.141
Token"
Token ID1
Feature activation-4.30e-02

Pos logit contributions
terday+0.619
 confir+0.600
clair+0.578
pring+0.574
cale+0.548
Neg logit contributions
rieg-0.609
 bloc-0.594
ambo-0.591
anooga-0.578
 Rove-0.572
Token in
Token ID287
Feature activation-3.52e-01

Pos logit contributions
terday+0.058
 confir+0.056
pring+0.054
clair+0.054
cale+0.051
Neg logit contributions
rieg-0.055
ambo-0.054
 bloc-0.053
anooga-0.052
 Rove-0.051
Token the
Token ID262
Feature activation+1.53e-01

Pos logit contributions
terday+0.563
 confir+0.547
pring+0.529
clair+0.527
cale+0.508
Neg logit contributions
rieg-0.362
ambo-0.348
 bloc-0.346
anooga-0.337
 Rove-0.333
Token Mongol
Token ID42188
Feature activation+5.68e+00

Pos logit contributions
rieg+0.168
 bloc+0.163
ambo+0.163
 Rove+0.157
anooga+0.156
Neg logit contributions
terday-0.234
 confir-0.227
pring-0.219
clair-0.219
cale-0.210
Tokenian
Token ID666
Feature activation+1.37e+00

Pos logit contributions
rieg+5.828
 bloc+5.670
ambo+5.633
 Rove+5.318
anooga+5.194
Neg logit contributions
terday-8.599
 confir-8.472
clair-8.215
pring-8.038
utics-7.585
Token language
Token ID3303
Feature activation-3.91e-01

Pos logit contributions
rieg+1.734
 bloc+1.706
ambo+1.683
 Rove+1.635
anooga+1.607
Neg logit contributions
terday-1.835
 confir-1.773
clair-1.715
pring-1.697
cale-1.609
Token).[
Token ID42669
Feature activation+1.47e+00

Pos logit contributions
terday+0.468
 confir+0.451
clair+0.430
pring+0.429
cale+0.405
Neg logit contributions
rieg-0.557
ambo-0.545
 bloc-0.543
anooga-0.531
 Rove-0.526
Token1
Token ID16
Feature activation-1.26e+00

Pos logit contributions
rieg+2.239
ambo+2.199
 bloc+2.163
 Rove+2.113
anooga+2.062
Neg logit contributions
terday-1.613
 confir-1.577
clair-1.446
pring-1.431
cale-1.342
Token]
Token ID60
Feature activation+2.00e+00

Pos logit contributions
terday+1.638
 confir+1.578
pring+1.521
clair+1.512
cale+1.443
Neg logit contributions
rieg-1.687
ambo-1.638
 bloc-1.621
anooga-1.608
 Rove-1.574
Tokenin
Token ID259
Feature activation-4.22e-01

Pos logit contributions
rieg+1.565
ambo+1.536
 bloc+1.505
anooga+1.472
 Rove+1.447
Neg logit contributions
terday-1.669
 confir-1.627
pring-1.534
clair-1.530
cale-1.454
Token)
Token ID8
Feature activation+9.41e-01

Pos logit contributions
terday+0.582
 confir+0.563
pring+0.542
clair+0.540
cale+0.516
Neg logit contributions
rieg-0.530
ambo-0.515
 bloc-0.510
anooga-0.500
 Rove-0.492
Token tribe
Token ID14893
Feature activation+8.53e-01

Pos logit contributions
rieg+1.209
 bloc+1.189
ambo+1.188
anooga+1.142
 Rove+1.140
Neg logit contributions
terday-1.260
 confir-1.212
pring-1.158
clair-1.157
cale-1.102
Token and
Token ID290
Feature activation-3.87e-01

Pos logit contributions
rieg+1.190
 bloc+1.169
ambo+1.166
anooga+1.130
 Rove+1.126
Neg logit contributions
terday-1.047
 confir-1.006
pring-0.961
clair-0.957
cale-0.911
Token the
Token ID262
Feature activation+1.96e-01

Pos logit contributions
terday+0.531
 confir+0.513
pring+0.497
clair+0.495
cale+0.472
Neg logit contributions
rieg-0.485
ambo-0.470
 bloc-0.468
anooga-0.459
 Rove-0.455
Token Mongol
Token ID42188
Feature activation+5.61e+00

Pos logit contributions
rieg+0.237
 bloc+0.229
ambo+0.228
 Rove+0.221
anooga+0.221
Neg logit contributions
terday-0.278
 confir-0.268
clair-0.261
pring-0.260
cale-0.248
Token general
Token ID2276
Feature activation+1.64e-01

Pos logit contributions
rieg+6.035
 bloc+5.873
ambo+5.858
 Rove+5.599
anooga+5.479
Neg logit contributions
terday-8.233
 confir-7.926
clair-7.842
pring-7.662
utics-7.280
Token Mang
Token ID27609
Feature activation+3.91e+00

Pos logit contributions
rieg+0.201
ambo+0.195
 bloc+0.193
anooga+0.189
 Rove+0.188
Neg logit contributions
terday-0.230
 confir-0.222
pring-0.214
clair-0.214
cale-0.204
Tokengh
Token ID456
Feature activation+1.21e+00

Pos logit contributions
rieg+4.995
ambo+4.959
 bloc+4.731
anooga+4.685
 Rove+4.553
Neg logit contributions
terday-5.164
 confir-5.007
pring-4.685
clair-4.652
cale-4.436
Tokenud
Token ID463
Feature activation-5.71e-01

Pos logit contributions
rieg+1.473
ambo+1.432
 bloc+1.380
anooga+1.368
 Rove+1.331
Neg logit contributions
terday-1.717
 confir-1.664
pring-1.584
clair-1.575
cale-1.509
Tokenai
Token ID1872
Feature activation+1.38e+00

Pos logit contributions
terday+0.788
 confir+0.761
pring+0.733
clair+0.730
cale+0.698
Neg logit contributions
rieg-0.717
ambo-0.698
 bloc-0.687
anooga-0.679
 Rove-0.664
Token America
Token ID2253
Feature activation+2.17e-01

Pos logit contributions
rieg+3.086
 bloc+3.001
ambo+2.905
 Rove+2.865
anooga+2.809
Neg logit contributions
terday-4.334
 confir-4.178
pring-4.055
clair-3.995
cale-3.884
Token and
Token ID290
Feature activation+5.70e-01

Pos logit contributions
rieg+0.278
ambo+0.269
 bloc+0.268
anooga+0.262
 Rove+0.260
Neg logit contributions
terday-0.293
 confir-0.287
pring-0.275
clair-0.271
cale-0.260
Token the
Token ID262
Feature activation+1.11e+00

Pos logit contributions
rieg+0.592
ambo+0.568
 bloc+0.568
 Rove+0.552
anooga+0.542
Neg logit contributions
terday-0.909
 confir-0.886
pring-0.858
clair-0.854
cale-0.816
Token Wall
Token ID5007
Feature activation+1.99e+00

Pos logit contributions
rieg+1.230
 bloc+1.205
ambo+1.172
 Rove+1.160
anooga+1.130
Neg logit contributions
terday-1.678
 confir-1.630
pring-1.578
clair-1.571
cale-1.497
Token Street
Token ID3530
Feature activation+1.46e+00

Pos logit contributions
rieg+2.229
ambo+2.141
 bloc+2.131
anooga+2.066
 Rove+2.049
Neg logit contributions
terday-3.018
 confir-2.970
pring-2.804
clair-2.788
cale-2.693
Token cabal
Token ID47548
Feature activation+5.53e+00

Pos logit contributions
rieg+1.578
 bloc+1.519
ambo+1.498
 Rove+1.452
anooga+1.444
Neg logit contributions
terday-2.287
 confir-2.216
pring-2.141
clair-2.128
cale-2.051
Token is
Token ID318
Feature activation+7.78e-01

Pos logit contributions
rieg+6.275
 bloc+6.150
ambo+6.042
 Rove+5.920
anooga+5.753
Neg logit contributions
 confir-7.690
terday-7.598
pring-7.201
clair-7.143
cale-6.844
Token their
Token ID511
Feature activation+4.96e-01

Pos logit contributions
rieg+0.908
ambo+0.880
 bloc+0.876
 Rove+0.869
anooga+0.849
Neg logit contributions
terday-1.116
 confir-1.097
pring-1.061
clair-1.050
cale-0.992
Token complete
Token ID1844
Feature activation-4.28e-01

Pos logit contributions
rieg+0.651
 bloc+0.633
ambo+0.629
 Rove+0.615
anooga+0.610
Neg logit contributions
terday-0.654
 confir-0.631
pring-0.609
clair-0.605
cale-0.576
Token lack
Token ID3092
Feature activation-3.36e-01

Pos logit contributions
terday+0.537
 confir+0.515
pring+0.497
clair+0.492
cale+0.468
Neg logit contributions
rieg-0.592
ambo-0.574
 bloc-0.572
anooga-0.564
 Rove-0.555
Token of
Token ID286
Feature activation+2.86e-01

Pos logit contributions
terday+0.407
 confir+0.396
pring+0.372
clair+0.370
cale+0.350
Neg logit contributions
rieg-0.479
ambo-0.466
 bloc-0.461
anooga-0.454
 Rove-0.449
Token origin
Token ID8159
Feature activation-5.80e-01

Pos logit contributions
rieg+0.216
 bloc+0.211
ambo+0.208
 Rove+0.200
anooga+0.200
Neg logit contributions
terday-0.301
 confir-0.291
clair-0.283
pring-0.280
cale-0.268
Token were
Token ID547
Feature activation+1.49e-01

Pos logit contributions
terday+0.729
 confir+0.701
clair+0.676
pring+0.672
cale+0.637
Neg logit contributions
rieg-0.796
ambo-0.778
 bloc-0.776
anooga-0.751
 Rove-0.746
Token introduced
Token ID5495
Feature activation-7.95e-01

Pos logit contributions
rieg+0.195
 bloc+0.191
ambo+0.188
anooga+0.184
 Rove+0.184
Neg logit contributions
terday-0.196
 confir-0.188
pring-0.183
clair-0.181
cale-0.173
Token when
Token ID618
Feature activation-6.06e-01

Pos logit contributions
terday+1.047
 confir+1.015
clair+0.975
pring+0.974
cale+0.928
Neg logit contributions
rieg-1.041
ambo-1.014
 bloc-1.010
anooga-0.976
 Rove-0.970
Token the
Token ID262
Feature activation-3.92e-01

Pos logit contributions
terday+0.951
 confir+0.921
pring+0.895
clair+0.894
cale+0.857
Neg logit contributions
rieg-0.644
ambo-0.620
 bloc-0.615
anooga-0.601
 Rove-0.590
Token Mongol
Token ID42188
Feature activation+5.40e+00

Pos logit contributions
terday+0.723
 confir+0.704
pring+0.686
clair+0.685
cale+0.661
Neg logit contributions
rieg-0.311
 bloc-0.294
ambo-0.294
anooga-0.281
 Rove-0.276
Token Empire
Token ID8065
Feature activation-6.17e-01

Pos logit contributions
rieg+5.938
 bloc+5.792
ambo+5.672
 Rove+5.335
anooga+5.331
Neg logit contributions
terday-7.955
 confir-7.630
clair-7.580
pring-7.446
cale-7.009
Token expanded
Token ID9902
Feature activation+2.13e-01

Pos logit contributions
terday+0.814
 confir+0.783
pring+0.757
clair+0.751
cale+0.713
Neg logit contributions
rieg-0.815
 bloc-0.790
ambo-0.788
anooga-0.771
 Rove-0.760
Token all
Token ID477
Feature activation+1.33e+00

Pos logit contributions
rieg+0.283
 bloc+0.274
ambo+0.274
anooga+0.263
 Rove+0.262
Neg logit contributions
terday-0.280
 confir-0.270
clair-0.260
pring-0.259
cale-0.245
Token over
Token ID625
Feature activation+8.50e-01

Pos logit contributions
rieg+1.474
ambo+1.416
 bloc+1.404
anooga+1.339
 Rove+1.327
Neg logit contributions
terday-2.026
 confir-1.971
pring-1.904
clair-1.899
cale-1.799
Token Euras
Token ID35769
Feature activation+4.82e-01

Pos logit contributions
rieg+0.892
ambo+0.860
 bloc+0.858
 Rove+0.823
anooga+0.816
Neg logit contributions
terday-1.336
 confir-1.300
clair-1.262
pring-1.254
cale-1.196
Token be
Token ID307
Feature activation+1.49e+00

Pos logit contributions
rieg+1.284
 bloc+1.265
ambo+1.224
 Rove+1.195
anooga+1.181
Neg logit contributions
terday-1.290
 confir-1.271
clair-1.216
pring-1.201
utics-1.137
Token joined
Token ID5399
Feature activation+2.22e-01

Pos logit contributions
rieg+2.013
 bloc+1.986
 Rove+1.931
anooga+1.912
ambo+1.903
Neg logit contributions
terday-1.910
 confir-1.850
clair-1.759
pring-1.719
utics-1.632
Token in
Token ID287
Feature activation+3.34e-01

Pos logit contributions
rieg+0.328
 bloc+0.318
ambo+0.318
anooga+0.312
 Rove+0.309
Neg logit contributions
terday-0.256
 confir-0.249
clair-0.237
pring-0.235
cale-0.222
Token the
Token ID262
Feature activation+3.66e-01

Pos logit contributions
rieg+0.418
 bloc+0.406
ambo+0.402
 Rove+0.392
anooga+0.390
Neg logit contributions
terday-0.463
 confir-0.447
clair-0.434
pring-0.430
cale-0.411
Token next
Token ID1306
Feature activation+1.08e+00

Pos logit contributions
rieg+0.443
 bloc+0.435
ambo+0.425
 Rove+0.423
anooga+0.411
Neg logit contributions
terday-0.521
 confir-0.501
clair-0.487
pring-0.481
cale-0.460
Token big
Token ID1263
Feature activation+5.32e+00

Pos logit contributions
rieg+1.195
 bloc+1.165
ambo+1.137
 Rove+1.122
anooga+1.111
Neg logit contributions
terday-1.650
 confir-1.592
clair-1.550
pring-1.536
cale-1.472
Token marriage
Token ID4845
Feature activation-1.08e-01

Pos logit contributions
 bloc+6.380
rieg+6.205
 Rove+6.011
ambo+5.849
anooga+5.794
Neg logit contributions
terday-7.253
 confir-7.111
clair-6.858
pring-6.722
utics-6.494
Token equality
Token ID10537
Feature activation-9.96e-01

Pos logit contributions
terday+0.143
 confir+0.138
clair+0.132
pring+0.132
cale+0.125
Neg logit contributions
rieg-0.143
 bloc-0.139
ambo-0.138
anooga-0.135
 Rove-0.133
Token case
Token ID1339
Feature activation+3.89e-01

Pos logit contributions
terday+1.317
 confir+1.270
pring+1.224
clair+1.218
cale+1.163
Neg logit contributions
rieg-1.303
ambo-1.264
 bloc-1.252
anooga-1.239
 Rove-1.214
Token.
Token ID13
Feature activation-9.24e-02

Pos logit contributions
rieg+0.584
 bloc+0.570
ambo+0.564
anooga+0.553
 Rove+0.553
Neg logit contributions
terday-0.442
 confir-0.424
clair-0.404
pring-0.400
cale-0.375
Token This
Token ID770
Feature activation+4.29e-01

Pos logit contributions
terday+0.123
 confir+0.121
clair+0.114
pring+0.114
cale+0.108
Neg logit contributions
rieg-0.120
ambo-0.117
 bloc-0.116
 Rove-0.114
anooga-0.113
Token healing
Token ID11516
Feature activation-1.26e+00

Pos logit contributions
rieg+0.213
 bloc+0.208
ambo+0.205
anooga+0.201
 Rove+0.200
Neg logit contributions
terday-0.208
 confir-0.199
clair-0.193
pring-0.191
cale-0.182
Token power
Token ID1176
Feature activation-7.89e-01

Pos logit contributions
terday+1.657
 confir+1.588
clair+1.530
pring+1.513
cale+1.442
Neg logit contributions
rieg-1.673
 bloc-1.619
ambo-1.613
anooga-1.582
 Rove-1.549
Token of
Token ID286
Feature activation+9.13e-02

Pos logit contributions
terday+0.954
 confir+0.912
clair+0.870
pring+0.868
cale+0.824
Neg logit contributions
rieg-1.131
ambo-1.097
 bloc-1.094
anooga-1.080
 Rove-1.060
Token water
Token ID1660
Feature activation+4.85e-01

Pos logit contributions
rieg+0.119
 bloc+0.116
ambo+0.115
anooga+0.112
 Rove+0.112
Neg logit contributions
terday-0.122
 confir-0.116
clair-0.113
pring-0.112
cale-0.107
Token.
Token ID13
Feature activation+5.76e-02

Pos logit contributions
rieg+0.690
 bloc+0.681
ambo+0.677
anooga+0.656
 Rove+0.640
Neg logit contributions
terday-0.587
 confir-0.555
clair-0.535
pring-0.526
cale-0.497
Token Bot
Token ID18579
Feature activation+5.30e+00

Pos logit contributions
rieg+0.073
ambo+0.071
 bloc+0.070
 Rove+0.069
anooga+0.069
Neg logit contributions
terday-0.079
 confir-0.077
clair-0.073
pring-0.073
cale-0.069
Tokenan
Token ID272
Feature activation+2.45e+00

Pos logit contributions
ambo+4.655
rieg+4.653
anooga+4.482
 bloc+4.337
 Rove+4.273
Neg logit contributions
terday-8.890
 confir-8.768
clair-8.317
pring-8.312
cale-7.966
Tokenics
Token ID873
Feature activation-7.20e-01

Pos logit contributions
rieg+2.361
ambo+2.257
 bloc+2.219
anooga+2.154
 Rove+2.118
Neg logit contributions
terday-4.088
 confir-3.996
pring-3.840
clair-3.790
cale-3.691
Token,
Token ID11
Feature activation+5.39e-01

Pos logit contributions
terday+0.905
 confir+0.863
clair+0.830
pring+0.825
cale+0.783
Neg logit contributions
rieg-0.996
ambo-0.970
 bloc-0.965
anooga-0.946
 Rove-0.932
Token on
Token ID319
Feature activation+8.29e-02

Pos logit contributions
rieg+0.680
 bloc+0.665
ambo+0.663
 Rove+0.639
anooga+0.638
Neg logit contributions
terday-0.743
 confir-0.703
clair-0.682
pring-0.679
cale-0.654
Token the
Token ID262
Feature activation+3.38e-01

Pos logit contributions
rieg+0.092
ambo+0.089
 bloc+0.089
anooga+0.087
 Rove+0.085
Neg logit contributions
terday-0.126
 confir-0.121
pring-0.117
clair-0.117
cale-0.112
Token in
Token ID287
Feature activation-8.79e-01

Pos logit contributions
terday+1.056
 confir+1.018
pring+0.973
clair+0.971
cale+0.921
Neg logit contributions
rieg-1.185
ambo-1.153
 bloc-1.145
anooga-1.127
 Rove-1.113
Token Italy
Token ID8031
Feature activation-1.69e+00

Pos logit contributions
terday+1.424
 confir+1.382
pring+1.341
clair+1.336
cale+1.286
Neg logit contributions
rieg-0.889
ambo-0.856
 bloc-0.845
anooga-0.832
 Rove-0.813
Token were
Token ID547
Feature activation+5.54e-01

Pos logit contributions
terday+2.064
 confir+1.985
pring+1.905
clair+1.893
cale+1.798
Neg logit contributions
rieg-2.372
ambo-2.310
 bloc-2.291
anooga-2.261
 Rove-2.229
Token named
Token ID3706
Feature activation-1.55e+00

Pos logit contributions
rieg+0.716
ambo+0.705
 bloc+0.698
 Rove+0.686
anooga+0.680
Neg logit contributions
terday-0.730
 confir-0.693
clair-0.677
pring-0.673
cale-0.641
Token after
Token ID706
Feature activation-2.72e-01

Pos logit contributions
terday+2.365
 confir+2.291
pring+2.219
clair+2.213
cale+2.124
Neg logit contributions
rieg-1.722
ambo-1.665
 bloc-1.643
anooga-1.622
 Rove-1.586
Token Mongol
Token ID42188
Feature activation+5.27e+00

Pos logit contributions
terday+0.434
 confir+0.421
pring+0.409
clair+0.408
cale+0.392
Neg logit contributions
rieg-0.282
ambo-0.272
 bloc-0.269
anooga-0.264
 Rove-0.259
Token rulers
Token ID24925
Feature activation+6.89e-01

Pos logit contributions
rieg+5.517
 bloc+5.436
ambo+5.421
 Rove+5.159
anooga+5.062
Neg logit contributions
terday-7.824
 confir-7.573
clair-7.525
pring-7.363
cale-6.986
Token,
Token ID11
Feature activation-2.17e-01

Pos logit contributions
rieg+0.979
ambo+0.959
 bloc+0.953
 Rove+0.928
anooga+0.926
Neg logit contributions
terday-0.821
 confir-0.791
clair-0.756
pring-0.747
cale-0.710
Token including
Token ID1390
Feature activation+1.22e+00

Pos logit contributions
terday+0.303
 confir+0.291
pring+0.282
clair+0.281
cale+0.269
Neg logit contributions
rieg-0.268
ambo-0.260
 bloc-0.259
anooga-0.253
 Rove-0.250
Token H
Token ID367
Feature activation-9.56e-01

Pos logit contributions
rieg+1.316
ambo+1.276
 bloc+1.269
 Rove+1.232
anooga+1.227
Neg logit contributions
terday-1.870
 confir-1.810
clair-1.768
pring-1.761
cale-1.681
Tokenü
Token ID9116
Feature activation-3.59e-01

Pos logit contributions
terday+1.391
 confir+1.348
pring+1.295
clair+1.290
cale+1.239
Neg logit contributions
rieg-1.133
ambo-1.098
 bloc-1.078
anooga-1.069
 Rove-1.041
Tokenents
Token ID658
Feature activation+3.54e-01

Pos logit contributions
rieg+1.124
ambo+1.081
 bloc+1.072
anooga+1.057
 Rove+1.025
Neg logit contributions
terday-1.725
 confir-1.672
pring-1.620
clair-1.614
cale-1.560
Token SELECT
Token ID33493
Feature activation+1.28e-01

Pos logit contributions
rieg+0.433
 bloc+0.420
ambo+0.419
anooga+0.409
 Rove+0.405
Neg logit contributions
terday-0.493
 confir-0.476
clair-0.460
pring-0.460
cale-0.437
Token *
Token ID1635
Feature activation+5.93e-01

Pos logit contributions
rieg+0.148
 bloc+0.143
ambo+0.142
anooga+0.139
 Rove+0.137
Neg logit contributions
terday-0.188
 confir-0.182
pring-0.177
clair-0.177
cale-0.169
Token FROM
Token ID16034
Feature activation+1.88e+00

Pos logit contributions
rieg+0.864
ambo+0.843
 bloc+0.837
anooga+0.825
 Rove+0.816
Neg logit contributions
terday-0.691
 confir-0.665
pring-0.640
clair-0.637
cale-0.598
Token [
Token ID685
Feature activation+4.99e-01

Pos logit contributions
rieg+2.056
 bloc+1.999
ambo+1.956
anooga+1.922
 Rove+1.897
Neg logit contributions
terday-2.864
 confir-2.750
pring-2.690
clair-2.688
cale-2.576
Token big
Token ID1263
Feature activation+5.25e+00

Pos logit contributions
rieg+0.506
 bloc+0.485
ambo+0.484
anooga+0.472
 Rove+0.461
Neg logit contributions
terday-0.807
 confir-0.779
pring-0.758
clair-0.755
cale-0.727
Tokenquery
Token ID22766
Feature activation-4.93e-01

Pos logit contributions
rieg+5.502
ambo+5.094
 bloc+5.027
 Rove+4.819
owler+4.781
Neg logit contributions
 confir-8.264
terday-8.079
pring-7.405
clair-7.325
cale-7.119
Token -
Token ID532
Feature activation+2.91e+00

Pos logit contributions
terday+0.701
 confir+0.678
pring+0.655
clair+0.652
cale+0.625
Neg logit contributions
rieg-0.596
ambo-0.578
 bloc-0.569
anooga-0.565
 Rove-0.552
Token public
Token ID1171
Feature activation+1.01e+00

Pos logit contributions
rieg+2.814
 bloc+2.769
ambo+2.656
anooga+2.634
 Rove+2.607
Neg logit contributions
terday-4.694
 confir-4.524
pring-4.437
clair-4.422
cale-4.279
Token -
Token ID532
Feature activation+2.44e+00

Pos logit contributions
rieg+1.189
ambo+1.145
 bloc+1.142
anooga+1.126
 Rove+1.101
Neg logit contributions
terday-1.471
 confir-1.422
pring-1.376
clair-1.370
cale-1.314
Token data
Token ID1366
Feature activation+1.10e+00

Pos logit contributions
rieg+3.077
 bloc+3.037
ambo+2.960
anooga+2.951
 Rove+2.889
Neg logit contributions
terday-3.278
 confir-3.125
pring-3.075
clair-3.039
cale-2.902
Token support
Token ID1104
Feature activation+8.50e-01

Pos logit contributions
rieg+1.383
 bloc+1.339
ambo+1.334
 Rove+1.325
anooga+1.293
Neg logit contributions
terday-1.767
 confir-1.717
pring-1.669
clair-1.655
cale-1.589
Token from
Token ID422
Feature activation+9.44e-01

Pos logit contributions
rieg+1.194
 bloc+1.169
ambo+1.163
anooga+1.148
 Rove+1.148
Neg logit contributions
terday-1.019
 confir-0.989
pring-0.947
clair-0.944
cale-0.895
Token former
Token ID1966
Feature activation-5.97e-01

Pos logit contributions
rieg+1.046
 bloc+1.017
ambo+1.010
 Rove+0.992
anooga+0.979
Neg logit contributions
terday-1.427
 confir-1.383
pring-1.344
clair-1.334
cale-1.276
Token Ku
Token ID12554
Feature activation+3.35e+00

Pos logit contributions
terday+0.904
 confir+0.873
pring+0.849
clair+0.845
cale+0.810
Neg logit contributions
rieg-0.665
ambo-0.642
 bloc-0.641
anooga-0.629
 Rove-0.620
Token Klux
Token ID45092
Feature activation+2.51e+00

Pos logit contributions
rieg+3.033
 bloc+2.903
ambo+2.900
anooga+2.795
 Rove+2.782
Neg logit contributions
terday-5.764
 confir-5.624
pring-5.353
clair-5.244
cale-5.157
Token Klan
Token ID31151
Feature activation+5.24e+00

Pos logit contributions
rieg+1.877
 bloc+1.779
ambo+1.772
anooga+1.749
 Rove+1.676
Neg logit contributions
terday-4.718
 confir-4.632
pring-4.480
clair-4.456
cale-4.312
Token leader
Token ID3554
Feature activation+3.84e+00

Pos logit contributions
 bloc+4.862
rieg+4.766
 Rove+4.499
ambo+4.488
anooga+4.443
Neg logit contributions
terday-8.581
pring-8.130
 confir-8.058
clair-8.004
utics-7.994
Token David
Token ID3271
Feature activation+4.87e-01

Pos logit contributions
 bloc+3.290
rieg+3.184
 Rove+3.041
anooga+3.010
ambo+2.996
Neg logit contributions
terday-6.540
 confir-6.501
pring-6.337
clair-6.331
utics-6.198
Token Duke
Token ID11083
Feature activation+1.11e+00

Pos logit contributions
rieg+0.459
 bloc+0.455
anooga+0.440
ambo+0.434
 Rove+0.432
Neg logit contributions
terday-0.824
 confir-0.810
pring-0.774
clair-0.768
cale-0.745
Token.
Token ID13
Feature activation+1.09e+00

Pos logit contributions
rieg+1.667
 bloc+1.640
ambo+1.627
 Rove+1.596
anooga+1.593
Neg logit contributions
terday-1.211
 confir-1.172
pring-1.123
clair-1.114
cale-1.058
Token (
Token ID357
Feature activation+1.56e+00

Pos logit contributions
rieg+1.230
 bloc+1.187
ambo+1.182
 Rove+1.169
anooga+1.137
Neg logit contributions
terday-1.626
 confir-1.605
clair-1.524
pring-1.519
cale-1.455
Token do
Token ID466
Feature activation+8.08e-02

Pos logit contributions
rieg+1.325
 bloc+1.287
ambo+1.282
 Rove+1.212
anooga+1.205
Neg logit contributions
terday-1.393
 confir-1.338
pring-1.301
clair-1.296
cale-1.219
Token and
Token ID290
Feature activation+2.82e-01

Pos logit contributions
rieg+0.117
ambo+0.115
 bloc+0.114
anooga+0.111
 Rove+0.110
Neg logit contributions
terday-0.095
 confir-0.092
clair-0.088
pring-0.087
cale-0.082
Token shared
Token ID4888
Feature activation+8.72e-01

Pos logit contributions
rieg+0.353
 bloc+0.342
ambo+0.341
 Rove+0.330
anooga+0.328
Neg logit contributions
terday-0.390
 confir-0.374
pring-0.363
clair-0.363
cale-0.343
Token with
Token ID351
Feature activation+1.38e+00

Pos logit contributions
rieg+1.097
 bloc+1.067
ambo+1.062
anooga+1.031
 Rove+1.016
Neg logit contributions
terday-1.198
 confir-1.150
clair-1.115
pring-1.104
cale-1.053
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
rieg+1.464
 bloc+1.420
ambo+1.407
 Rove+1.357
anooga+1.343
Neg logit contributions
terday-2.161
 confir-2.093
clair-2.031
pring-2.014
cale-1.923
Token bunch
Token ID7684
Feature activation+5.24e+00

Pos logit contributions
rieg+1.296
 bloc+1.255
ambo+1.245
anooga+1.205
 Rove+1.188
Neg logit contributions
terday-1.912
 confir-1.832
clair-1.781
pring-1.776
cale-1.700
Token of
Token ID286
Feature activation+4.93e-01

Pos logit contributions
rieg+6.657
ambo+6.371
 bloc+6.347
 Rove+6.039
anooga+6.020
Neg logit contributions
terday-7.056
 confir-6.898
clair-6.330
pring-6.311
cale-5.802
Token different
Token ID1180
Feature activation+2.34e+00

Pos logit contributions
rieg+0.488
ambo+0.469
 bloc+0.466
anooga+0.450
 Rove+0.444
Neg logit contributions
terday-0.812
 confir-0.785
clair-0.763
pring-0.762
cale-0.731
Token classes
Token ID6097
Feature activation+2.16e+00

Pos logit contributions
rieg+2.575
 bloc+2.521
ambo+2.465
 Rove+2.367
anooga+2.344
Neg logit contributions
terday-3.564
 confir-3.409
clair-3.353
pring-3.308
cale-3.155
Token.
Token ID13
Feature activation-2.61e-01

Pos logit contributions
rieg+3.098
 bloc+3.050
ambo+3.012
 Rove+2.913
anooga+2.903
Neg logit contributions
terday-2.511
 confir-2.453
clair-2.339
pring-2.303
utics-2.164
Token The
Token ID383
Feature activation-3.16e-01

Pos logit contributions
terday+0.347
 confir+0.338
pring+0.323
clair+0.322
cale+0.307
Neg logit contributions
rieg-0.340
ambo-0.330
 bloc-0.327
anooga-0.321
 Rove-0.318
Token flag
Token ID6056
Feature activation+3.36e+00

Pos logit contributions
rieg+2.475
 bloc+2.469
ambo+2.386
 Rove+2.338
anooga+2.319
Neg logit contributions
terday-3.132
 confir-3.010
clair-2.917
pring-2.911
utics-2.771
Token in
Token ID287
Feature activation+6.86e-01

Pos logit contributions
rieg+4.414
 bloc+4.377
ambo+4.338
 Rove+4.184
anooga+4.129
Neg logit contributions
terday-4.153
 confir-4.134
clair-3.878
pring-3.871
utics-3.662
Token front
Token ID2166
Feature activation+2.86e+00

Pos logit contributions
rieg+0.766
 bloc+0.743
ambo+0.737
 Rove+0.720
anooga+0.716
Neg logit contributions
terday-1.044
 confir-1.012
pring-0.976
clair-0.970
cale-0.930
Token of
Token ID286
Feature activation+6.94e-01

Pos logit contributions
rieg+3.771
 bloc+3.611
ambo+3.582
 Rove+3.531
anooga+3.410
Neg logit contributions
 confir-3.801
terday-3.768
clair-3.435
pring-3.423
utics-3.213
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
rieg+0.815
 bloc+0.793
ambo+0.789
anooga+0.773
 Rove+0.767
Neg logit contributions
terday-1.009
 confir-0.980
pring-0.946
clair-0.942
cale-0.896
Token bull
Token ID6473
Feature activation+5.23e+00

Pos logit contributions
rieg+1.817
 bloc+1.803
ambo+1.752
anooga+1.722
 Rove+1.720
Neg logit contributions
terday-2.281
 confir-2.194
clair-2.123
pring-2.120
cale-2.021
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
rieg+7.440
 bloc+7.301
ambo+7.251
 Rove+7.072
anooga+7.037
Neg logit contributions
 confir-5.785
terday-5.675
pring-5.318
clair-5.193
utics-4.951
Token http
Token ID2638
Feature activation-1.00e+00

Pos logit contributions
rieg+0.160
ambo+0.154
 bloc+0.152
anooga+0.149
 Rove+0.148
Neg logit contributions
terday-0.216
 confir-0.212
pring-0.204
clair-0.203
cale-0.195
Token://
Token ID1378
Feature activation-1.24e-01

Pos logit contributions
terday+1.166
 confir+1.116
pring+1.073
clair+1.066
cale+1.012
Neg logit contributions
rieg-1.476
ambo-1.437
 bloc-1.424
anooga-1.413
 Rove-1.386
Tokence
Token ID344
Feature activation-8.05e-01

Pos logit contributions
terday+0.177
 confir+0.172
pring+0.164
clair+0.163
cale+0.156
Neg logit contributions
rieg-0.150
ambo-0.146
 bloc-0.144
anooga-0.141
 Rove-0.139
Tokenpr
Token ID1050
Feature activation+7.61e-01

Pos logit contributions
terday+1.087
 confir+1.055
pring+1.001
clair+0.998
cale+0.954
Neg logit contributions
rieg-1.043
ambo-1.008
 bloc-0.994
anooga-0.976
 Rove-0.955
Token alliance
Token ID12801
Feature activation+1.80e+00

Pos logit contributions
rieg+0.104
 bloc+0.102
ambo+0.100
anooga+0.097
 Rove+0.096
Neg logit contributions
terday-0.121
 confir-0.117
pring-0.113
clair-0.113
cale-0.107
Token's
Token ID338
Feature activation-9.89e-01

Pos logit contributions
rieg+2.070
 bloc+2.039
ambo+1.974
anooga+1.937
 Rove+1.892
Neg logit contributions
terday-2.669
 confir-2.580
pring-2.530
clair-2.488
cale-2.399
Token role
Token ID2597
Feature activation+4.17e-01

Pos logit contributions
terday+1.161
 confir+1.115
pring+1.070
clair+1.064
cale+1.007
Neg logit contributions
rieg-1.443
ambo-1.404
 bloc-1.398
anooga-1.376
 Rove-1.356
Token as
Token ID355
Feature activation-2.18e-01

Pos logit contributions
rieg+0.505
 bloc+0.492
ambo+0.486
anooga+0.476
 Rove+0.467
Neg logit contributions
terday-0.588
 confir-0.577
clair-0.552
pring-0.552
cale-0.526
Token the
Token ID262
Feature activation+5.20e-02

Pos logit contributions
terday+0.314
 confir+0.305
pring+0.295
clair+0.294
cale+0.280
Neg logit contributions
rieg-0.260
 bloc-0.253
ambo-0.251
anooga-0.245
 Rove-0.241
Token bul
Token ID4807
Feature activation+5.23e+00

Pos logit contributions
rieg+0.062
 bloc+0.061
ambo+0.060
anooga+0.058
 Rove+0.058
Neg logit contributions
terday-0.074
 confir-0.072
pring-0.070
clair-0.070
cale-0.066
Tokenwark
Token ID48542
Feature activation+2.66e+00

Pos logit contributions
rieg+1.786
 bloc+1.689
ambo+1.466
owler+1.200
 Rove+1.183
Neg logit contributions
terday-11.948
 confir-11.598
pring-11.040
clair-11.021
utics-10.779
Token of
Token ID286
Feature activation+1.17e-01

Pos logit contributions
rieg+3.445
 bloc+3.390
ambo+3.301
anooga+3.238
 Rove+3.196
Neg logit contributions
terday-3.466
 confir-3.402
clair-3.248
pring-3.218
cale-3.053
Token Western
Token ID4885
Feature activation+2.40e+00

Pos logit contributions
rieg+0.133
 bloc+0.129
ambo+0.128
anooga+0.124
 Rove+0.122
Neg logit contributions
terday-0.176
 confir-0.171
pring-0.165
clair-0.165
cale-0.158
Token defence
Token ID9366
Feature activation+3.69e-01

Pos logit contributions
 bloc+2.592
rieg+2.570
ambo+2.444
anooga+2.359
 Rove+2.331
Neg logit contributions
terday-3.744
 confir-3.626
pring-3.503
clair-3.488
cale-3.350
Token.
Token ID13
Feature activation-4.98e-02

Pos logit contributions
rieg+0.534
 bloc+0.526
ambo+0.518
anooga+0.508
 Rove+0.496
Neg logit contributions
terday-0.442
 confir-0.424
pring-0.406
clair-0.406
cale-0.382
Token rejected
Token ID8606
Feature activation+9.41e-01

Pos logit contributions
rieg+1.141
 bloc+1.128
ambo+1.124
 Rove+1.079
anooga+1.074
Neg logit contributions
terday-1.153
 confir-1.100
pring-1.068
clair-1.064
utics-0.997
Token by
Token ID416
Feature activation+7.12e-01

Pos logit contributions
rieg+1.224
 bloc+1.221
ambo+1.212
 Rove+1.146
anooga+1.137
Neg logit contributions
terday-1.231
 confir-1.190
pring-1.156
clair-1.148
utics-1.071
Token both
Token ID1111
Feature activation+2.33e+00

Pos logit contributions
rieg+0.776
 bloc+0.753
ambo+0.749
 Rove+0.722
anooga+0.718
Neg logit contributions
terday-1.095
 confir-1.059
pring-1.037
clair-1.033
cale-0.982
Token Burma
Token ID40306
Feature activation+9.66e-01

Pos logit contributions
rieg+2.313
 bloc+2.289
ambo+2.211
 Rove+2.154
anooga+2.039
Neg logit contributions
terday-3.807
 confir-3.638
clair-3.599
pring-3.591
utics-3.413
Token and
Token ID290
Feature activation+3.32e-01

Pos logit contributions
rieg+1.308
ambo+1.267
 bloc+1.264
anooga+1.233
 Rove+1.218
Neg logit contributions
terday-1.243
 confir-1.195
pring-1.155
clair-1.142
cale-1.089
Token neighbouring
Token ID29272
Feature activation+5.21e+00

Pos logit contributions
rieg+0.344
ambo+0.330
 bloc+0.330
anooga+0.317
 Rove+0.317
Neg logit contributions
terday-0.533
 confir-0.514
clair-0.501
pring-0.501
cale-0.479
Token Bangladesh
Token ID19483
Feature activation+2.97e+00

Pos logit contributions
 bloc+4.602
rieg+4.243
 Rove+3.998
ambo+3.969
anooga+3.587
Neg logit contributions
terday-9.149
clair-8.613
 confir-8.583
pring-8.504
utics-8.301
Token.
Token ID13
Feature activation+1.59e-01

Pos logit contributions
rieg+4.341
 bloc+4.299
ambo+4.275
 Rove+4.061
anooga+4.034
Neg logit contributions
terday-3.356
 confir-3.227
clair-3.045
pring-3.019
cale-2.867
Token
Token ID198
Feature activation-2.94e-01

Pos logit contributions
rieg+0.209
ambo+0.203
 bloc+0.201
anooga+0.196
 Rove+0.196
Neg logit contributions
terday-0.210
 confir-0.205
pring-0.195
clair-0.195
cale-0.185
Token
Token ID198
Feature activation-2.68e-01

Pos logit contributions
terday+0.357
 confir+0.346
pring+0.329
clair+0.327
cale+0.310
Neg logit contributions
rieg-0.418
ambo-0.406
 bloc-0.402
anooga-0.397
 Rove-0.391
TokenMS
Token ID5653
Feature activation-2.10e+00

Pos logit contributions
terday+0.355
 confir+0.349
pring+0.329
clair+0.327
cale+0.310
Neg logit contributions
rieg-0.352
ambo-0.343
 bloc-0.335
anooga-0.332
 Rove-0.327
Token circus
Token ID33125
Feature activation+2.25e+00

Pos logit contributions
terday+0.559
 confir+0.539
clair+0.522
pring+0.521
cale+0.498
Neg logit contributions
rieg-0.413
 bloc-0.402
ambo-0.398
 Rove-0.387
anooga-0.385
Token.
Token ID13
Feature activation+3.83e-01

Pos logit contributions
rieg+3.189
 bloc+3.116
ambo+3.104
anooga+3.018
 Rove+2.992
Neg logit contributions
terday-2.717
 confir-2.651
pring-2.492
clair-2.467
cale-2.328
Token Bring
Token ID24347
Feature activation+9.87e-01

Pos logit contributions
rieg+0.488
ambo+0.474
 bloc+0.468
 Rove+0.461
anooga+0.458
Neg logit contributions
terday-0.521
 confir-0.514
pring-0.484
clair-0.481
cale-0.460
Token on
Token ID319
Feature activation+1.27e+00

Pos logit contributions
rieg+1.135
ambo+1.100
 bloc+1.096
anooga+1.069
 Rove+1.057
Neg logit contributions
terday-1.463
 confir-1.411
pring-1.366
clair-1.362
cale-1.306
Token the
Token ID262
Feature activation+5.61e-01

Pos logit contributions
rieg+1.385
ambo+1.348
 bloc+1.344
 Rove+1.312
anooga+1.296
Neg logit contributions
terday-1.937
 confir-1.878
pring-1.821
clair-1.812
cale-1.727
Token clown
Token ID25573
Feature activation+5.18e+00

Pos logit contributions
rieg+0.653
 bloc+0.634
ambo+0.633
anooga+0.614
 Rove+0.613
Neg logit contributions
terday-0.825
 confir-0.793
pring-0.771
clair-0.767
cale-0.732
Tokens
Token ID82
Feature activation+7.51e-02

Pos logit contributions
rieg+6.698
ambo+6.618
 bloc+6.479
anooga+6.271
 Rove+6.263
Neg logit contributions
terday-6.600
 confir-6.364
pring-6.106
clair-6.006
utics-5.708
Token,
Token ID11
Feature activation+4.23e-01

Pos logit contributions
rieg+0.110
ambo+0.108
 bloc+0.107
anooga+0.105
 Rove+0.104
Neg logit contributions
terday-0.087
 confir-0.085
pring-0.080
clair-0.080
cale-0.075
Token the
Token ID262
Feature activation-4.19e-01

Pos logit contributions
rieg+0.528
ambo+0.514
 bloc+0.512
anooga+0.496
 Rove+0.495
Neg logit contributions
terday-0.589
 confir-0.565
pring-0.547
clair-0.542
cale-0.518
Token jug
Token ID45808
Feature activation+1.60e+00

Pos logit contributions
terday+0.629
 confir+0.609
pring+0.590
clair+0.588
cale+0.564
Neg logit contributions
rieg-0.472
ambo-0.457
 bloc-0.454
anooga-0.445
 Rove-0.437
Tokenglers
Token ID33641
Feature activation+1.63e+00

Pos logit contributions
rieg+1.272
ambo+1.224
 bloc+1.190
anooga+1.166
 Rove+1.116
Neg logit contributions
terday-2.956
 confir-2.877
pring-2.799
clair-2.779
cale-2.702
Tokenies
Token ID444
Feature activation-4.55e-01

Pos logit contributions
rieg+0.726
ambo+0.688
 bloc+0.670
anooga+0.658
 Rove+0.630
Neg logit contributions
terday-2.004
 confir-1.960
pring-1.905
clair-1.898
cale-1.842
Token The
Token ID383
Feature activation-3.57e-01

Pos logit contributions
terday+0.665
 confir+0.644
clair+0.621
pring+0.618
cale+0.590
Neg logit contributions
rieg-0.531
ambo-0.517
 bloc-0.513
 Rove-0.497
anooga-0.496
Token Good
Token ID4599
Feature activation-1.16e-02

Pos logit contributions
terday+0.487
 confir+0.474
clair+0.454
pring+0.453
cale+0.430
Neg logit contributions
rieg-0.453
ambo-0.441
 bloc-0.438
anooga-0.431
 Rove-0.424
Token Wife
Token ID34188
Feature activation+9.09e-02

Pos logit contributions
terday+0.015
 confir+0.015
clair+0.014
pring+0.014
cale+0.013
Neg logit contributions
rieg-0.015
ambo-0.015
 bloc-0.015
anooga-0.014
 Rove-0.014
Token CBS
Token ID11133
Feature activation-1.15e+00

Pos logit contributions
rieg+0.102
ambo+0.099
 bloc+0.099
anooga+0.096
 Rove+0.096
Neg logit contributions
terday-0.137
 confir-0.134
clair-0.128
pring-0.127
cale-0.122
Token Tat
Token ID29070
Feature activation+5.14e+00

Pos logit contributions
terday+1.730
 confir+1.685
pring+1.618
clair+1.615
cale+1.547
Neg logit contributions
rieg-1.300
ambo-1.254
 bloc-1.241
anooga-1.220
 Rove-1.203
Tokeniana
Token ID7484
Feature activation-1.53e+00

Pos logit contributions
rieg+3.840
ambo+3.795
anooga+3.620
 bloc+3.595
 Rove+3.475
Neg logit contributions
 confir-9.563
terday-9.468
pring-8.732
clair-8.719
cale-8.508
Token Mas
Token ID11066
Feature activation+8.47e-01

Pos logit contributions
terday+2.335
 confir+2.272
clair+2.188
pring+2.186
cale+2.093
Neg logit contributions
rieg-1.703
ambo-1.639
 bloc-1.634
anooga-1.599
 Rove-1.572
Tokenl
Token ID75
Feature activation+1.99e+00

Pos logit contributions
rieg+0.891
ambo+0.873
 bloc+0.855
anooga+0.831
 Rove+0.809
Neg logit contributions
terday-1.332
 confir-1.302
pring-1.230
clair-1.224
utics-1.179
Tokenany
Token ID1092
Feature activation-3.46e-01

Pos logit contributions
ambo+1.382
rieg+1.314
 bloc+1.285
anooga+1.194
owler+1.146
Neg logit contributions
terday-3.824
 confir-3.725
clair-3.581
pring-3.566
cale-3.538
Token Or
Token ID1471
Feature activation+7.32e-01

Pos logit contributions
terday+0.514
 confir+0.500
clair+0.478
pring+0.478
cale+0.456
Neg logit contributions
rieg-0.399
ambo-0.387
 bloc-0.385
anooga-0.373
 Rove-0.373
Token Islands
Token ID12010
Feature activation+4.21e-01

Pos logit contributions
rieg+2.789
ambo+2.767
 bloc+2.761
anooga+2.650
 Rove+2.640
Neg logit contributions
terday-1.953
 confir-1.825
pring-1.745
clair-1.737
cale-1.649
Token 14
Token ID1478
Feature activation-1.83e+00

Pos logit contributions
rieg+0.513
 bloc+0.502
ambo+0.499
 Rove+0.481
anooga+0.477
Neg logit contributions
terday-0.594
 confir-0.579
clair-0.551
pring-0.550
cale-0.523
Token.
Token ID13
Feature activation-5.93e-02

Pos logit contributions
terday+1.847
 confir+1.764
pring+1.689
clair+1.668
cale+1.571
Neg logit contributions
rieg-2.955
ambo-2.880
 bloc-2.846
anooga-2.835
 Rove-2.786
Token6
Token ID21
Feature activation+7.49e-01

Pos logit contributions
terday+0.071
 confir+0.069
clair+0.065
pring+0.065
cale+0.062
Neg logit contributions
rieg-0.085
ambo-0.083
 bloc-0.082
anooga-0.081
 Rove-0.080
Token 8
Token ID807
Feature activation+2.38e-01

Pos logit contributions
rieg+0.910
ambo+0.895
 bloc+0.889
anooga+0.862
 Rove+0.855
Neg logit contributions
terday-1.063
 confir-1.031
clair-0.980
pring-0.978
cale-0.929
Token Bots
Token ID40946
Feature activation+5.13e+00

Pos logit contributions
rieg+0.228
ambo+0.220
 bloc+0.219
 Rove+0.210
anooga+0.209
Neg logit contributions
terday-0.399
 confir-0.390
clair-0.376
pring-0.374
cale-0.359
Tokenwana
Token ID49484
Feature activation+1.15e+00

Pos logit contributions
ambo+0.598
rieg+0.529
 bloc+0.511
wana+0.244
anooga+0.237
Neg logit contributions
terday-12.719
 confir-12.560
pring-12.127
clair-12.102
utics-11.733
Token 14
Token ID1478
Feature activation-1.82e+00

Pos logit contributions
rieg+1.421
 bloc+1.396
ambo+1.381
 Rove+1.344
anooga+1.311
Neg logit contributions
terday-1.598
 confir-1.565
clair-1.477
pring-1.475
cale-1.401
Token.
Token ID13
Feature activation+5.27e-02

Pos logit contributions
terday+1.741
 confir+1.658
pring+1.587
clair+1.566
cale+1.466
Neg logit contributions
rieg-3.021
ambo-2.951
 bloc-2.916
anooga-2.904
 Rove-2.857
Token9
Token ID24
Feature activation+4.15e-01

Pos logit contributions
rieg+0.075
ambo+0.074
 bloc+0.072
anooga+0.071
 Rove+0.071
Neg logit contributions
terday-0.064
 confir-0.062
clair-0.058
pring-0.058
cale-0.055
Token 9
Token ID860
Feature activation-1.00e-01

Pos logit contributions
rieg+0.512
ambo+0.500
 bloc+0.497
 Rove+0.482
anooga+0.480
Neg logit contributions
terday-0.584
 confir-0.571
clair-0.537
pring-0.531
cale-0.508
Token the
Token ID262
Feature activation-4.66e-01

Pos logit contributions
terday+0.303
 confir+0.292
clair+0.281
pring+0.279
cale+0.268
Neg logit contributions
rieg-0.246
ambo-0.240
 bloc-0.240
anooga-0.234
 Rove-0.231
Token PAX
Token ID49742
Feature activation-2.02e+00

Pos logit contributions
terday+0.626
 confir+0.601
pring+0.576
clair+0.576
cale+0.549
Neg logit contributions
rieg-0.601
ambo-0.584
 bloc-0.582
anooga-0.572
 Rove-0.565
Token East
Token ID3687
Feature activation+1.33e+00

Pos logit contributions
terday+2.923
 confir+2.829
pring+2.738
clair+2.724
cale+2.616
Neg logit contributions
rieg-2.380
ambo-2.302
 bloc-2.272
anooga-2.252
 Rove-2.200
Token app
Token ID598
Feature activation-2.99e-01

Pos logit contributions
rieg+1.542
 bloc+1.507
ambo+1.495
anooga+1.459
 Rove+1.429
Neg logit contributions
terday-1.967
 confir-1.890
pring-1.810
clair-1.805
utics-1.727
Token (
Token ID357
Feature activation+5.88e-02

Pos logit contributions
terday+0.375
 confir+0.360
pring+0.345
clair+0.343
cale+0.326
Neg logit contributions
rieg-0.413
ambo-0.402
 bloc-0.399
anooga-0.394
 Rove-0.386
TokeniOS
Token ID35742
Feature activation-5.61e+00

Pos logit contributions
rieg+0.072
ambo+0.071
 bloc+0.069
anooga+0.069
 Rove+0.067
Neg logit contributions
terday-0.082
 confir-0.080
pring-0.076
clair-0.075
cale-0.072
Token,
Token ID11
Feature activation+2.56e-01

Pos logit contributions
terday+6.413
 confir+6.153
pring+6.010
clair+5.996
cale+5.544
Neg logit contributions
rieg-7.848
anooga-7.706
ambo-7.675
 bloc-7.533
 Rove-7.446
Token Android
Token ID5565
Feature activation-2.27e+00

Pos logit contributions
rieg+0.230
ambo+0.221
 bloc+0.219
anooga+0.212
 Rove+0.209
Neg logit contributions
terday-0.443
 confir-0.431
pring-0.416
clair-0.415
cale-0.402
Token),
Token ID828
Feature activation+9.49e-01

Pos logit contributions
terday+2.538
 confir+2.430
pring+2.340
clair+2.320
cale+2.197
Neg logit contributions
rieg-3.423
ambo-3.333
 bloc-3.291
anooga-3.290
 Rove-3.217
Token get
Token ID651
Feature activation+5.65e-01

Pos logit contributions
rieg+1.148
 bloc+1.127
ambo+1.120
anooga+1.095
 Rove+1.085
Neg logit contributions
terday-1.340
 confir-1.287
pring-1.238
clair-1.233
cale-1.178
Token it
Token ID340
Feature activation+2.49e-01

Pos logit contributions
rieg+0.673
ambo+0.657
 bloc+0.654
anooga+0.639
 Rove+0.630
Neg logit contributions
terday-0.812
 confir-0.780
clair-0.753
pring-0.752
cale-0.717
Token.
Token ID13
Feature activation+3.78e-01

Pos logit contributions
rieg+0.934
 bloc+0.910
ambo+0.908
anooga+0.892
 Rove+0.872
Neg logit contributions
terday-0.709
 confir-0.675
clair-0.648
pring-0.639
cale-0.610
Token Exercise
Token ID32900
Feature activation-8.85e-01

Pos logit contributions
rieg+0.494
ambo+0.478
 bloc+0.477
 Rove+0.467
anooga+0.465
Neg logit contributions
terday-0.500
 confir-0.489
clair-0.463
pring-0.460
cale-0.439
Token also
Token ID635
Feature activation+1.45e+00

Pos logit contributions
terday+1.194
 confir+1.143
pring+1.104
clair+1.102
cale+1.052
Neg logit contributions
rieg-1.143
ambo-1.110
 bloc-1.102
anooga-1.087
 Rove-1.064
Token improves
Token ID19575
Feature activation-1.03e+00

Pos logit contributions
rieg+1.649
 bloc+1.639
ambo+1.618
 Rove+1.567
anooga+1.516
Neg logit contributions
terday-2.093
 confir-2.007
clair-1.980
pring-1.972
cale-1.873
Token insulin
Token ID14588
Feature activation-4.27e+00

Pos logit contributions
terday+1.368
 confir+1.313
pring+1.270
clair+1.267
cale+1.208
Neg logit contributions
rieg-1.333
ambo-1.294
 bloc-1.290
anooga-1.270
 Rove-1.248
Token sensitivity
Token ID14233
Feature activation-5.49e+00

Pos logit contributions
terday+3.602
 confir+3.447
pring+3.226
clair+3.223
cale+3.002
Neg logit contributions
rieg-7.445
ambo-7.346
anooga-7.230
 bloc-7.214
 Rove-7.092
Token.
Token ID13
Feature activation-4.60e-01

Pos logit contributions
terday+6.073
 confir+5.837
pring+5.639
clair+5.524
cale+5.255
Neg logit contributions
rieg-8.143
ambo-7.935
anooga-7.859
 bloc-7.764
 Rove-7.698
Token
Token ID198
Feature activation+2.45e-01

Pos logit contributions
terday+0.592
 confir+0.573
clair+0.546
pring+0.545
cale+0.518
Neg logit contributions
rieg-0.619
ambo-0.601
 bloc-0.598
anooga-0.586
 Rove-0.584
Token
Token ID198
Feature activation+7.92e-02

Pos logit contributions
rieg+0.342
ambo+0.332
 bloc+0.329
anooga+0.323
 Rove+0.320
Neg logit contributions
terday-0.305
 confir-0.301
pring-0.280
clair-0.279
cale-0.264
TokenCal
Token ID9771
Feature activation-1.50e+00

Pos logit contributions
rieg+0.101
ambo+0.098
 bloc+0.096
anooga+0.095
 Rove+0.094
Neg logit contributions
terday-0.109
 confir-0.107
pring-0.099
clair-0.099
cale-0.095
Tokenoric
Token ID8146
Feature activation-2.11e+00

Pos logit contributions
terday+2.087
 confir+2.020
pring+1.939
clair+1.926
cale+1.842
Neg logit contributions
rieg-1.879
ambo-1.824
 bloc-1.799
anooga-1.779
 Rove-1.749
Token as
Token ID355
Feature activation-1.58e+00

Pos logit contributions
terday+2.271
 confir+2.185
pring+2.092
clair+2.091
cale+1.982
Neg logit contributions
rieg-2.474
ambo-2.413
 bloc-2.394
anooga-2.353
 Rove-2.312
Token well
Token ID880
Feature activation-6.77e-01

Pos logit contributions
terday+1.694
 confir+1.619
pring+1.546
clair+1.536
cale+1.449
Neg logit contributions
rieg-2.462
ambo-2.401
 bloc-2.379
anooga-2.361
 Rove-2.320
Token as
Token ID355
Feature activation-1.18e+00

Pos logit contributions
terday+0.781
 confir+0.748
pring+0.713
clair+0.711
cale+0.670
Neg logit contributions
rieg-1.004
ambo-0.979
 bloc-0.974
anooga-0.959
 Rove-0.944
Token response
Token ID2882
Feature activation-3.07e+00

Pos logit contributions
terday+1.655
 confir+1.599
pring+1.545
clair+1.537
cale+1.472
Neg logit contributions
rieg-1.455
ambo-1.409
 bloc-1.393
anooga-1.379
 Rove-1.349
Token and
Token ID290
Feature activation-6.10e-01

Pos logit contributions
terday+3.536
 confir+3.397
pring+3.256
clair+3.228
cale+3.062
Neg logit contributions
rieg-4.519
ambo-4.400
 bloc-4.348
anooga-4.319
 Rove-4.246
Token remission
Token ID47829
Feature activation-5.45e+00

Pos logit contributions
terday+0.791
 confir+0.755
clair+0.733
pring+0.730
cale+0.694
Neg logit contributions
rieg-0.814
 bloc-0.791
ambo-0.790
anooga-0.775
 Rove-0.762
Token rates
Token ID3965
Feature activation-2.20e+00

Pos logit contributions
terday+6.344
 confir+6.176
pring+5.942
clair+5.799
cale+5.563
Neg logit contributions
rieg-7.704
ambo-7.512
anooga-7.450
 bloc-7.298
 Rove-7.252
Token at
Token ID379
Feature activation+4.49e-01

Pos logit contributions
terday+2.601
 confir+2.488
clair+2.380
pring+2.378
cale+2.247
Neg logit contributions
rieg-3.203
ambo-3.127
 bloc-3.105
anooga-3.061
 Rove-3.012
Token week
Token ID1285
Feature activation+5.47e-01

Pos logit contributions
rieg+0.551
 bloc+0.536
ambo+0.531
anooga+0.522
 Rove+0.512
Neg logit contributions
terday-0.625
 confir-0.606
pring-0.586
clair-0.585
cale-0.557
Token four
Token ID1440
Feature activation+1.83e+00

Pos logit contributions
rieg+0.630
 bloc+0.615
ambo+0.610
anooga+0.589
 Rove+0.579
Neg logit contributions
terday-0.804
 confir-0.773
clair-0.754
pring-0.745
cale-0.712
Token.
Token ID13
Feature activation-8.41e-01

Pos logit contributions
rieg+2.499
 bloc+2.480
ambo+2.461
anooga+2.390
 Rove+2.341
Neg logit contributions
terday-2.251
 confir-2.145
clair-2.050
pring-1.998
cale-1.922
Tokenusal
Token ID6775
Feature activation-2.35e+00

Pos logit contributions
terday+2.884
 confir+2.789
pring+2.695
clair+2.673
cale+2.559
Neg logit contributions
rieg-2.724
ambo-2.639
 bloc-2.610
anooga-2.596
 Rove-2.534
Token rules
Token ID3173
Feature activation-1.42e+00

Pos logit contributions
terday+3.148
 confir+3.034
pring+2.941
clair+2.910
cale+2.778
Neg logit contributions
rieg-3.055
ambo-2.947
 bloc-2.945
anooga-2.892
 Rove-2.840
Token mean
Token ID1612
Feature activation-1.90e+00

Pos logit contributions
terday+1.767
 confir+1.702
pring+1.632
clair+1.631
cale+1.535
Neg logit contributions
rieg-1.978
ambo-1.929
 bloc-1.921
anooga-1.875
 Rove-1.857
Token judges
Token ID10266
Feature activation-1.21e+00

Pos logit contributions
terday+2.661
 confir+2.580
pring+2.484
clair+2.472
cale+2.376
Neg logit contributions
rieg-2.319
ambo-2.242
anooga-2.199
 bloc-2.197
 Rove-2.129
Token often
Token ID1690
Feature activation-3.71e-01

Pos logit contributions
terday+1.457
 confir+1.397
pring+1.337
clair+1.329
cale+1.256
Neg logit contributions
rieg-1.737
ambo-1.686
 bloc-1.679
anooga-1.652
 Rove-1.629
Token pres
Token ID906
Feature activation-5.43e+00

Pos logit contributions
terday+0.461
 confir+0.440
pring+0.427
clair+0.421
cale+0.397
Neg logit contributions
rieg-0.519
 bloc-0.507
ambo-0.502
 Rove-0.488
anooga-0.487
Tokenide
Token ID485
Feature activation-2.14e+00

Pos logit contributions
terday+6.771
pring+6.437
 confir+6.350
clair+6.286
cale+6.158
Neg logit contributions
rieg-7.152
anooga-7.084
ambo-6.886
 bloc-6.810
 Rove-6.697
Token over
Token ID625
Feature activation+6.90e-01

Pos logit contributions
terday+3.136
 confir+3.028
pring+2.935
clair+2.919
cale+2.804
Neg logit contributions
rieg-2.481
ambo-2.400
 bloc-2.363
anooga-2.346
 Rove-2.292
Token cases
Token ID2663
Feature activation-1.67e+00

Pos logit contributions
rieg+0.823
 bloc+0.809
ambo+0.800
 Rove+0.781
anooga+0.777
Neg logit contributions
terday-0.996
 confir-0.952
pring-0.922
clair-0.921
cale-0.871
Token involving
Token ID7411
Feature activation+9.16e-01

Pos logit contributions
terday+2.332
 confir+2.248
pring+2.166
clair+2.160
cale+2.062
Neg logit contributions
rieg-2.075
ambo-2.010
 bloc-1.997
anooga-1.965
 Rove-1.934
Token major
Token ID1688
Feature activation+2.51e+00

Pos logit contributions
rieg+1.040
 bloc+1.023
ambo+1.007
 Rove+0.989
anooga+0.974
Neg logit contributions
terday-1.374
 confir-1.322
clair-1.281
pring-1.276
cale-1.210
Token,
Token ID11
Feature activation-2.98e-01

Pos logit contributions
rieg+1.067
ambo+1.046
 bloc+1.043
anooga+1.021
 Rove+1.012
Neg logit contributions
terday-0.827
 confir-0.801
clair-0.762
pring-0.760
cale-0.708
Token they
Token ID484
Feature activation-2.83e-01

Pos logit contributions
terday+0.341
 confir+0.327
pring+0.313
clair+0.310
cale+0.294
Neg logit contributions
rieg-0.443
ambo-0.431
 bloc-0.430
anooga-0.424
 Rove-0.418
Token
Token ID447
Feature activation-2.52e-01

Pos logit contributions
terday+0.237
 confir+0.222
clair+0.210
pring+0.209
cale+0.193
Neg logit contributions
rieg-0.508
ambo-0.495
 bloc-0.492
anooga-0.489
 Rove-0.481
Token
Token ID247
Feature activation-2.10e+00

Pos logit contributions
terday+0.362
 confir+0.350
clair+0.337
pring+0.334
cale+0.322
Neg logit contributions
rieg-0.303
ambo-0.292
 bloc-0.288
anooga-0.284
 Rove-0.281
Tokenre
Token ID260
Feature activation-2.75e+00

Pos logit contributions
terday+2.571
 confir+2.464
pring+2.367
clair+2.367
cale+2.237
Neg logit contributions
rieg-2.965
ambo-2.866
 bloc-2.842
anooga-2.811
 Rove-2.778
Token irre
Token ID11331
Feature activation-5.39e+00

Pos logit contributions
terday+3.670
 confir+3.543
pring+3.418
clair+3.398
cale+3.248
Neg logit contributions
rieg-3.550
ambo-3.443
 bloc-3.397
anooga-3.377
 Rove-3.299
Tokenve
Token ID303
Feature activation-1.25e+00

Pos logit contributions
terday+3.912
 confir+3.624
pring+3.461
clair+3.424
cale+3.118
Neg logit contributions
rieg-10.179
ambo-9.955
anooga-9.874
 bloc-9.873
 Rove-9.674
Tokenrent
Token ID1156
Feature activation+1.44e-01

Pos logit contributions
terday+2.151
 confir+2.089
pring+2.029
clair+2.019
cale+1.950
Neg logit contributions
rieg-1.156
ambo-1.101
 bloc-1.092
anooga-1.063
 Rove-1.040
Token,
Token ID11
Feature activation-2.86e-01

Pos logit contributions
rieg+0.219
ambo+0.215
 bloc+0.214
anooga+0.209
 Rove+0.207
Neg logit contributions
terday-0.159
 confir-0.152
pring-0.145
clair-0.145
cale-0.136
Token they
Token ID484
Feature activation-2.35e-01

Pos logit contributions
terday+0.332
 confir+0.317
pring+0.304
clair+0.301
cale+0.286
Neg logit contributions
rieg-0.421
ambo-0.410
 bloc-0.409
anooga-0.403
 Rove-0.398
Token
Token ID447
Feature activation-3.60e-01

Pos logit contributions
terday+0.190
 confir+0.177
clair+0.168
pring+0.167
cale+0.154
Neg logit contributions
rieg-0.428
ambo-0.417
 bloc-0.415
anooga-0.413
 Rove-0.406
Token than
Token ID621
Feature activation-8.43e-01

Pos logit contributions
terday+0.379
 confir+0.359
clair+0.352
pring+0.350
cale+0.329
Neg logit contributions
rieg-0.444
 bloc-0.434
ambo-0.431
anooga-0.422
 Rove-0.421
Token three
Token ID1115
Feature activation+2.10e+00

Pos logit contributions
terday+1.206
 confir+1.160
pring+1.128
clair+1.126
cale+1.063
Neg logit contributions
rieg-1.016
 bloc-0.984
ambo-0.982
 Rove-0.952
anooga-0.952
Token weeks
Token ID2745
Feature activation-9.15e-01

Pos logit contributions
 bloc+2.442
rieg+2.414
ambo+2.342
 Rove+2.307
anooga+2.281
Neg logit contributions
terday-2.988
 confir-2.877
clair-2.856
pring-2.772
utics-2.619
Token,"
Token ID553
Feature activation-1.71e+00

Pos logit contributions
terday+1.037
 confir+1.009
clair+0.958
pring+0.952
cale+0.878
Neg logit contributions
rieg-1.363
ambo-1.337
 bloc-1.331
anooga-1.292
 Rove-1.290
Token says
Token ID1139
Feature activation-2.67e+00

Pos logit contributions
terday+2.356
 confir+2.275
pring+2.198
clair+2.186
cale+2.092
Neg logit contributions
rieg-2.137
ambo-2.072
 bloc-2.049
anooga-2.028
 Rove-1.985
Token Es
Token ID8678
Feature activation-5.35e+00

Pos logit contributions
terday+4.013
 confir+3.885
pring+3.751
clair+3.735
cale+3.613
Neg logit contributions
rieg-2.992
ambo-2.899
anooga-2.835
 bloc-2.823
 Rove-2.731
Tokena
Token ID64
Feature activation-4.73e-01

Pos logit contributions
terday+5.721
 confir+5.394
clair+5.269
pring+5.126
cale+4.934
Neg logit contributions
rieg-8.099
ambo-7.975
anooga-7.935
 bloc-7.770
 Rove-7.701
Token mission
Token ID4365
Feature activation-2.52e+00

Pos logit contributions
terday+0.681
 confir+0.658
pring+0.642
clair+0.635
cale+0.609
Neg logit contributions
rieg-0.559
 bloc-0.542
ambo-0.540
anooga-0.526
 Rove-0.522
Token manager
Token ID4706
Feature activation+4.28e-01

Pos logit contributions
terday+3.509
 confir+3.404
clair+3.274
pring+3.266
cale+3.128
Neg logit contributions
rieg-3.100
ambo-3.015
anooga-2.935
 bloc-2.931
 Rove-2.873
Token Dr
Token ID1583
Feature activation-1.08e+00

Pos logit contributions
rieg+0.467
 bloc+0.451
ambo+0.449
 Rove+0.439
anooga+0.434
Neg logit contributions
terday-0.656
 confir-0.641
clair-0.618
pring-0.616
cale-0.587
Token Rune
Token ID28228
Feature activation-1.63e+00

Pos logit contributions
terday+1.646
 confir+1.601
pring+1.547
clair+1.540
cale+1.475
Neg logit contributions
rieg-1.185
ambo-1.145
 bloc-1.131
anooga-1.114
 Rove-1.097
Token it
Token ID340
Feature activation-1.96e-01

Pos logit contributions
terday+1.073
 confir+1.041
pring+1.005
clair+1.003
cale+0.956
Neg logit contributions
rieg-0.957
ambo-0.932
 bloc-0.923
anooga-0.905
 Rove-0.897
Token
Token ID447
Feature activation-8.11e-01

Pos logit contributions
terday+0.275
 confir+0.265
pring+0.257
clair+0.255
cale+0.245
Neg logit contributions
rieg-0.238
ambo-0.233
 bloc-0.230
anooga-0.227
 Rove-0.222
Token
Token ID247
Feature activation-2.08e+00

Pos logit contributions
terday+1.402
 confir+1.365
pring+1.324
clair+1.322
cale+1.277
Neg logit contributions
rieg-0.732
ambo-0.700
 bloc-0.689
anooga-0.680
 Rove-0.662
Tokens
Token ID82
Feature activation-2.44e+00

Pos logit contributions
terday+2.739
 confir+2.642
pring+2.541
clair+2.533
cale+2.413
Neg logit contributions
rieg-2.749
ambo-2.672
 bloc-2.636
anooga-2.612
 Rove-2.558
Token an
Token ID281
Feature activation-2.99e-02

Pos logit contributions
terday+3.407
 confir+3.290
pring+3.178
clair+3.164
cale+3.029
Neg logit contributions
rieg-3.021
ambo-2.931
 bloc-2.898
anooga-2.868
 Rove-2.805
Token obligation
Token ID12990
Feature activation-5.29e+00

Pos logit contributions
terday+0.038
 confir+0.037
pring+0.036
clair+0.035
cale+0.034
Neg logit contributions
rieg-0.040
ambo-0.039
 bloc-0.039
anooga-0.038
 Rove-0.038
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
terday+5.806
 confir+5.505
pring+5.335
clair+5.247
cale+4.980
Neg logit contributions
rieg-7.970
ambo-7.757
anooga-7.666
 bloc-7.618
 Rove-7.496
Token
Token ID447
Feature activation-1.31e+00

Pos logit contributions
terday+1.484
 confir+1.429
pring+1.372
clair+1.364
cale+1.302
Neg logit contributions
rieg-1.586
ambo-1.546
 bloc-1.534
anooga-1.513
 Rove-1.487
Token
Token ID251
Feature activation+8.06e-01

Pos logit contributions
terday+1.889
 confir+1.824
pring+1.761
clair+1.759
cale+1.687
Neg logit contributions
rieg-1.560
ambo-1.509
 bloc-1.492
anooga-1.476
 Rove-1.449
Token said
Token ID531
Feature activation-1.54e+00

Pos logit contributions
rieg+1.109
ambo+1.090
 bloc+1.079
anooga+1.057
 Rove+1.043
Neg logit contributions
terday-0.993
 confir-0.960
clair-0.915
pring-0.911
cale-0.861
Token Morton
Token ID35766
Feature activation-1.30e+00

Pos logit contributions
terday+2.296
 confir+2.223
pring+2.152
clair+2.144
cale+2.057
Neg logit contributions
rieg-1.752
ambo-1.695
 bloc-1.677
anooga-1.652
 Rove-1.620
Token you
Token ID345
Feature activation-1.13e+00

Pos logit contributions
terday+0.138
 confir+0.135
pring+0.131
clair+0.130
cale+0.123
Neg logit contributions
rieg-0.114
 bloc-0.110
ambo-0.109
 Rove-0.107
anooga-0.106
Token've
Token ID1053
Feature activation-1.95e-01

Pos logit contributions
terday+1.311
 confir+1.261
pring+1.211
clair+1.201
cale+1.132
Neg logit contributions
rieg-1.674
ambo-1.629
 bloc-1.620
anooga-1.592
 Rove-1.576
Token now
Token ID783
Feature activation+1.12e+00

Pos logit contributions
terday+0.234
 confir+0.225
pring+0.217
clair+0.216
cale+0.203
Neg logit contributions
rieg-0.279
 bloc-0.273
ambo-0.272
 Rove-0.265
anooga-0.265
Token got
Token ID1392
Feature activation+1.15e+00

Pos logit contributions
rieg+1.569
 bloc+1.551
ambo+1.532
 Rove+1.497
anooga+1.474
Neg logit contributions
terday-1.356
 confir-1.294
pring-1.264
clair-1.253
utics-1.190
Token Lord
Token ID4453
Feature activation-6.36e-01

Pos logit contributions
rieg+1.346
 bloc+1.316
ambo+1.287
 Rove+1.274
anooga+1.259
Neg logit contributions
terday-1.676
 confir-1.628
pring-1.584
clair-1.576
utics-1.485
Token Hes
Token ID44773
Feature activation-5.28e+00

Pos logit contributions
terday+0.689
 confir+0.672
pring+0.635
clair+0.634
cale+0.589
Neg logit contributions
rieg-0.979
 bloc-0.951
ambo-0.948
anooga-0.939
 Rove-0.932
Tokenelt
Token ID2120
Feature activation-3.78e-01

Pos logit contributions
terday+5.067
clair+4.677
pring+4.549
cale+4.480
 confir+4.335
Neg logit contributions
rieg-8.513
ambo-8.396
anooga-8.332
 bloc-8.327
 Rove-8.323
Tokenine
Token ID500
Feature activation-1.91e+00

Pos logit contributions
terday+0.456
 confir+0.442
pring+0.420
clair+0.415
cale+0.394
Neg logit contributions
rieg-0.541
ambo-0.526
 bloc-0.520
anooga-0.512
 Rove-0.506
Token saying
Token ID2282
Feature activation-2.01e-01

Pos logit contributions
terday+2.589
 confir+2.499
pring+2.410
clair+2.396
cale+2.294
Neg logit contributions
rieg-2.425
ambo-2.353
anooga-2.318
 bloc-2.311
 Rove-2.245
Token that
Token ID326
Feature activation-3.26e-01

Pos logit contributions
terday+0.275
 confir+0.268
pring+0.260
clair+0.258
cale+0.244
Neg logit contributions
rieg-0.253
 bloc-0.245
ambo-0.244
anooga-0.237
 Rove-0.237
Token he
Token ID339
Feature activation+2.58e-01

Pos logit contributions
terday+0.454
 confir+0.443
pring+0.428
clair+0.426
cale+0.403
Neg logit contributions
rieg-0.405
 bloc-0.393
ambo-0.388
anooga-0.378
 Rove-0.378
Token.
Token ID13
Feature activation+1.92e-02

Pos logit contributions
terday+2.394
 confir+2.288
pring+2.187
clair+2.172
cale+2.049
Neg logit contributions
rieg-3.469
ambo-3.384
 bloc-3.352
anooga-3.327
 Rove-3.270
Token
Token ID198
Feature activation+1.48e-01

Pos logit contributions
rieg+0.027
ambo+0.027
 bloc+0.026
anooga+0.026
 Rove+0.026
Neg logit contributions
terday-0.023
 confir-0.022
pring-0.021
clair-0.021
cale-0.020
Token
Token ID198
Feature activation+1.63e-01

Pos logit contributions
rieg+0.207
ambo+0.201
 bloc+0.199
anooga+0.196
 Rove+0.194
Neg logit contributions
terday-0.182
 confir-0.179
pring-0.168
clair-0.167
cale-0.158
TokenIncreases
Token ID28544
Feature activation-7.50e-02

Pos logit contributions
rieg+0.177
ambo+0.170
 bloc+0.166
anooga+0.164
 Rove+0.163
Neg logit contributions
terday-0.253
 confir-0.248
pring-0.235
clair-0.234
cale-0.225
Token insulin
Token ID14588
Feature activation-2.84e+00

Pos logit contributions
terday+0.097
 confir+0.093
clair+0.090
pring+0.090
cale+0.085
Neg logit contributions
rieg-0.100
 bloc-0.098
ambo-0.097
anooga-0.095
 Rove-0.095
Token sensitivity
Token ID14233
Feature activation-5.27e+00

Pos logit contributions
terday+2.674
 confir+2.554
pring+2.422
clair+2.407
cale+2.247
Neg logit contributions
rieg-4.748
ambo-4.652
 bloc-4.597
anooga-4.580
 Rove-4.499
Token.
Token ID13
Feature activation+1.42e-02

Pos logit contributions
terday+5.116
 confir+4.873
pring+4.699
clair+4.597
cale+4.355
Neg logit contributions
rieg-8.490
ambo-8.313
anooga-8.187
 bloc-8.116
 Rove-8.061
Token
Token ID198
Feature activation+3.39e-01

Pos logit contributions
rieg+0.020
ambo+0.020
 bloc+0.019
anooga+0.019
 Rove+0.019
Neg logit contributions
terday-0.017
 confir-0.016
pring-0.016
clair-0.016
cale-0.015
Token
Token ID198
Feature activation+3.67e-01

Pos logit contributions
rieg+0.471
ambo+0.457
 bloc+0.453
anooga+0.444
 Rove+0.441
Neg logit contributions
terday-0.423
 confir-0.418
pring-0.388
clair-0.387
cale-0.366
TokenIncreases
Token ID28544
Feature activation+2.90e-01

Pos logit contributions
rieg+0.418
ambo+0.403
 bloc+0.394
anooga+0.389
 Rove+0.387
Neg logit contributions
terday-0.551
 confir-0.541
pring-0.510
clair-0.507
cale-0.488
Token lip
Token ID10645
Feature activation+6.74e-01

Pos logit contributions
rieg+0.387
 bloc+0.380
ambo+0.375
anooga+0.369
 Rove+0.368
Neg logit contributions
terday-0.373
 confir-0.355
clair-0.345
pring-0.345
cale-0.328
Token slack
Token ID30740
Feature activation+1.60e+00

Pos logit contributions
rieg+0.313
 bloc+0.304
ambo+0.300
 Rove+0.296
anooga+0.294
Neg logit contributions
terday-0.376
 confir-0.360
pring-0.350
clair-0.349
cale-0.331
Token.
Token ID13
Feature activation+8.08e-01

Pos logit contributions
rieg+2.353
 bloc+2.282
ambo+2.274
 Rove+2.216
anooga+2.214
Neg logit contributions
terday-1.834
 confir-1.789
clair-1.670
pring-1.654
cale-1.555
Token The
Token ID383
Feature activation+3.08e-01

Pos logit contributions
rieg+1.008
ambo+0.975
 bloc+0.974
 Rove+0.969
anooga+0.934
Neg logit contributions
terday-1.111
 confir-1.108
clair-1.039
pring-1.037
cale-0.981
Token Center
Token ID3337
Feature activation+1.70e+00

Pos logit contributions
rieg+0.371
 bloc+0.361
ambo+0.357
 Rove+0.351
anooga+0.348
Neg logit contributions
terday-0.440
 confir-0.424
pring-0.412
clair-0.411
cale-0.390
Token for
Token ID329
Feature activation+1.14e+00

Pos logit contributions
rieg+2.429
 bloc+2.357
ambo+2.351
anooga+2.299
 Rove+2.299
Neg logit contributions
terday-2.021
 confir-1.944
pring-1.868
clair-1.835
cale-1.764
Token Respons
Token ID20549
Feature activation-5.25e+00

Pos logit contributions
rieg+1.187
ambo+1.147
 bloc+1.136
 Rove+1.120
anooga+1.091
Neg logit contributions
terday-1.815
 confir-1.763
clair-1.690
pring-1.690
cale-1.606
Tokenive
Token ID425
Feature activation-1.67e-01

Pos logit contributions
terday+4.244
cale+3.741
clair+3.729
pring+3.715
ury+3.686
Neg logit contributions
rieg-8.981
anooga-8.945
ambo-8.919
 bloc-8.726
 Rove-8.583
Token Politics
Token ID17554
Feature activation-6.58e-03

Pos logit contributions
terday+0.213
 confir+0.207
pring+0.198
clair+0.197
cale+0.187
Neg logit contributions
rieg-0.226
ambo-0.219
 bloc-0.218
anooga-0.215
 Rove-0.212
Token has
Token ID468
Feature activation-4.47e-02

Pos logit contributions
terday+0.008
 confir+0.008
pring+0.008
clair+0.008
cale+0.007
Neg logit contributions
rieg-0.009
ambo-0.009
 bloc-0.009
anooga-0.008
 Rove-0.008
Token the
Token ID262
Feature activation-6.34e-01

Pos logit contributions
terday+0.057
 confir+0.054
clair+0.053
pring+0.053
cale+0.050
Neg logit contributions
rieg-0.060
ambo-0.059
 bloc-0.059
 Rove-0.058
anooga-0.057
Token full
Token ID1336
Feature activation-1.20e-01

Pos logit contributions
terday+0.884
 confir+0.853
pring+0.825
clair+0.822
cale+0.785
Neg logit contributions
rieg-0.786
ambo-0.760
 bloc-0.757
anooga-0.742
 Rove-0.737
Token is
Token ID318
Feature activation-8.76e-01

Pos logit contributions
terday+2.122
 confir+2.052
pring+1.977
clair+1.966
cale+1.880
Neg logit contributions
rieg-1.999
ambo-1.940
 bloc-1.918
anooga-1.897
 Rove-1.857
Token that
Token ID326
Feature activation-9.61e-01

Pos logit contributions
terday+1.183
 confir+1.138
pring+1.108
clair+1.093
cale+1.042
Neg logit contributions
rieg-1.127
ambo-1.099
 bloc-1.087
anooga-1.065
 Rove-1.044
Token we
Token ID356
Feature activation-1.93e+00

Pos logit contributions
terday+1.299
 confir+1.253
pring+1.212
clair+1.206
cale+1.148
Neg logit contributions
rieg-1.233
ambo-1.198
 bloc-1.188
anooga-1.161
 Rove-1.147
Token must
Token ID1276
Feature activation-1.97e+00

Pos logit contributions
terday+2.323
 confir+2.241
pring+2.149
clair+2.139
cale+2.024
Neg logit contributions
rieg-2.752
ambo-2.681
 bloc-2.652
anooga-2.616
 Rove-2.578
Token be
Token ID307
Feature activation+2.21e-01

Pos logit contributions
terday+2.576
 confir+2.492
pring+2.407
clair+2.384
cale+2.266
Neg logit contributions
rieg-2.620
ambo-2.543
 bloc-2.519
anooga-2.471
 Rove-2.432
Token responsive
Token ID21802
Feature activation-5.21e+00

Pos logit contributions
rieg+0.295
ambo+0.288
 bloc+0.288
anooga+0.277
 Rove+0.277
Neg logit contributions
terday-0.284
 confir-0.275
pring-0.264
clair-0.260
cale-0.246
Token the
Token ID262
Feature activation-1.28e+00

Pos logit contributions
terday+5.364
 confir+5.025
pring+4.854
clair+4.770
cale+4.576
Neg logit contributions
rieg-8.142
ambo-7.971
anooga-7.875
 bloc-7.831
 Rove-7.719
Token changing
Token ID5609
Feature activation-3.39e-01

Pos logit contributions
terday+1.693
 confir+1.640
pring+1.579
clair+1.572
cale+1.499
Neg logit contributions
rieg-1.680
ambo-1.629
 bloc-1.616
anooga-1.586
 Rove-1.561
Token environment
Token ID2858
Feature activation+1.81e-01

Pos logit contributions
terday+0.455
 confir+0.442
clair+0.427
pring+0.426
cale+0.403
Neg logit contributions
rieg-0.436
 bloc-0.423
ambo-0.420
anooga-0.408
 Rove-0.405
Token.
Token ID13
Feature activation+1.41e-01

Pos logit contributions
rieg+0.252
 bloc+0.244
ambo+0.243
 Rove+0.235
anooga+0.235
Neg logit contributions
terday-0.225
 confir-0.219
clair-0.210
pring-0.209
cale-0.197
Token
Token ID198
Feature activation+2.26e-01

Pos logit contributions
rieg+0.178
ambo+0.172
 bloc+0.170
 Rove+0.167
anooga+0.166
Neg logit contributions
terday-0.192
 confir-0.190
pring-0.179
clair-0.179
cale-0.170
Token r
Token ID374
Feature activation-7.60e-01

Pos logit contributions
terday+2.375
 confir+2.285
pring+2.195
clair+2.186
cale+2.077
Neg logit contributions
rieg-2.652
ambo-2.580
 bloc-2.556
anooga-2.528
 Rove-2.483
Tokenims
Token ID12078
Feature activation-1.14e+00

Pos logit contributions
terday+1.140
 confir+1.103
clair+1.047
pring+1.044
cale+1.005
Neg logit contributions
rieg-0.883
ambo-0.861
 bloc-0.835
anooga-0.813
 Rove-0.804
Token,
Token ID11
Feature activation-7.33e-01

Pos logit contributions
terday+1.440
 confir+1.391
clair+1.330
pring+1.319
cale+1.252
Neg logit contributions
rieg-1.551
ambo-1.514
 bloc-1.505
anooga-1.468
 Rove-1.454
Token laced
Token ID49699
Feature activation-1.57e+00

Pos logit contributions
terday+1.014
 confir+0.979
clair+0.943
pring+0.940
cale+0.896
Neg logit contributions
rieg-0.917
ambo-0.889
 bloc-0.887
anooga-0.867
 Rove-0.858
Token to
Token ID284
Feature activation-6.55e-01

Pos logit contributions
terday+2.162
 confir+2.087
pring+2.012
clair+2.009
cale+1.918
Neg logit contributions
rieg-1.958
ambo-1.898
 bloc-1.882
anooga-1.853
 Rove-1.821
Token Suz
Token ID22691
Feature activation-5.21e+00

Pos logit contributions
terday+0.930
 confir+0.897
clair+0.868
pring+0.865
cale+0.822
Neg logit contributions
rieg-0.794
ambo-0.767
 bloc-0.763
anooga-0.748
 Rove-0.743
Tokenue
Token ID518
Feature activation-2.55e+00

Pos logit contributions
terday+7.064
pring+6.715
 confir+6.685
clair+6.625
cale+6.416
Neg logit contributions
rieg-6.246
ambo-6.092
anooga-6.034
 bloc-6.023
 Rove-5.851
Token road
Token ID2975
Feature activation-6.61e-01

Pos logit contributions
terday+3.572
 confir+3.454
pring+3.333
clair+3.316
cale+3.176
Neg logit contributions
rieg-3.131
ambo-3.033
 bloc-3.000
anooga-2.964
 Rove-2.905
Token hubs
Token ID38459
Feature activation-1.51e+00

Pos logit contributions
terday+0.832
 confir+0.798
clair+0.766
pring+0.762
cale+0.725
Neg logit contributions
rieg-0.915
ambo-0.884
 bloc-0.883
anooga-0.864
 Rove-0.852
Token with
Token ID351
Feature activation-9.08e-02

Pos logit contributions
terday+1.817
 confir+1.749
clair+1.665
pring+1.658
cale+1.569
Neg logit contributions
rieg-2.165
ambo-2.111
 bloc-2.096
anooga-2.061
 Rove-2.034
Token an
Token ID281
Feature activation+3.28e-01

Pos logit contributions
terday+0.130
 confir+0.126
clair+0.122
pring+0.121
cale+0.115
Neg logit contributions
rieg-0.109
 bloc-0.106
ambo-0.105
 Rove-0.102
anooga-0.102
Token-
Token ID12
Feature activation-3.50e-01

Pos logit contributions
rieg+0.455
 bloc+0.444
ambo+0.436
anooga+0.426
 Rove+0.422
Neg logit contributions
terday-0.560
 confir-0.537
pring-0.522
clair-0.521
cale-0.497
Tokenaged
Token ID1886
Feature activation-5.61e-01

Pos logit contributions
terday+0.478
 confir+0.462
pring+0.445
clair+0.442
cale+0.422
Neg logit contributions
rieg-0.444
ambo-0.431
 bloc-0.426
anooga-0.421
 Rove-0.413
Token Italians
Token ID41720
Feature activation-6.99e-01

Pos logit contributions
terday+0.833
 confir+0.805
pring+0.780
clair+0.779
cale+0.744
Neg logit contributions
rieg-0.648
ambo-0.625
 bloc-0.623
anooga-0.604
 Rove-0.600
Token had
Token ID550
Feature activation+1.45e-01

Pos logit contributions
terday+0.904
 confir+0.866
pring+0.837
clair+0.829
cale+0.788
Neg logit contributions
rieg-0.940
ambo-0.916
 bloc-0.911
anooga-0.889
 Rove-0.882
Token been
Token ID587
Feature activation+3.04e-02

Pos logit contributions
rieg+0.199
 bloc+0.196
ambo+0.194
 Rove+0.189
anooga+0.189
Neg logit contributions
terday-0.184
 confir-0.173
pring-0.170
clair-0.168
cale-0.159
Token cons
Token ID762
Feature activation-5.17e+00

Pos logit contributions
rieg+0.040
ambo+0.039
 bloc+0.038
anooga+0.037
 Rove+0.037
Neg logit contributions
terday-0.041
 confir-0.039
pring-0.038
clair-0.037
cale-0.036
Tokencript
Token ID6519
Feature activation-1.12e+00

Pos logit contributions
terday+3.853
 confir+3.564
pring+3.548
clair+3.490
cale+3.204
Neg logit contributions
rieg-9.287
anooga-9.139
 bloc-8.983
ambo-8.971
 Rove-8.885
Tokened
Token ID276
Feature activation+3.31e-01

Pos logit contributions
terday+1.595
 confir+1.541
pring+1.491
clair+1.483
cale+1.423
Neg logit contributions
rieg-1.355
ambo-1.313
 bloc-1.298
anooga-1.281
 Rove-1.254
Token into
Token ID656
Feature activation-4.60e-01

Pos logit contributions
rieg+0.446
ambo+0.435
 bloc+0.434
anooga+0.418
 Rove+0.416
Neg logit contributions
terday-0.426
 confir-0.414
pring-0.396
clair-0.395
cale-0.375
Token forced
Token ID4137
Feature activation+2.07e-01

Pos logit contributions
terday+0.697
 confir+0.675
pring+0.654
clair+0.651
cale+0.625
Neg logit contributions
rieg-0.516
ambo-0.497
 bloc-0.492
anooga-0.484
 Rove-0.475
Token labour
Token ID10515
Feature activation-1.73e+00

Pos logit contributions
rieg+0.290
 bloc+0.284
ambo+0.278
anooga+0.273
 Rove+0.273
Neg logit contributions
terday-0.259
 confir-0.248
pring-0.241
clair-0.236
cale-0.224
Tokenuart
Token ID19986
Feature activation+9.56e-01

Pos logit contributions
rieg+0.814
ambo+0.797
 bloc+0.768
 Rove+0.746
anooga+0.745
Neg logit contributions
terday-1.174
 confir-1.150
pring-1.090
clair-1.067
cale-1.051
Token H
Token ID367
Feature activation-9.17e-01

Pos logit contributions
rieg+1.060
ambo+1.055
 bloc+1.035
 Rove+1.025
anooga+0.996
Neg logit contributions
terday-1.431
 confir-1.413
clair-1.331
pring-1.326
cale-1.275
Tokenogg
Token ID10332
Feature activation+6.02e-01

Pos logit contributions
terday+1.501
 confir+1.457
pring+1.418
clair+1.412
cale+1.361
Neg logit contributions
rieg-0.907
ambo-0.871
 bloc-0.859
anooga-0.849
 Rove-0.825
Token,
Token ID11
Feature activation-2.20e-01

Pos logit contributions
rieg+0.791
ambo+0.774
 bloc+0.762
anooga+0.749
 Rove+0.734
Neg logit contributions
terday-0.795
 confir-0.756
pring-0.728
clair-0.723
cale-0.696
Token Tommy
Token ID19919
Feature activation-1.36e+00

Pos logit contributions
terday+0.334
 confir+0.321
pring+0.313
clair+0.312
cale+0.299
Neg logit contributions
rieg-0.243
ambo-0.236
 bloc-0.235
anooga-0.228
 Rove-0.226
Token Seymour
Token ID42843
Feature activation-5.17e+00

Pos logit contributions
terday+1.959
 confir+1.895
pring+1.827
clair+1.818
cale+1.743
Neg logit contributions
rieg-1.629
ambo-1.578
 bloc-1.560
anooga-1.539
 Rove-1.511
Token and
Token ID290
Feature activation-6.54e-01

Pos logit contributions
terday+5.402
 confir+5.150
pring+5.052
clair+5.007
cale+4.748
Neg logit contributions
rieg-7.895
ambo-7.640
anooga-7.605
 bloc-7.542
 Rove-7.493
Token Lee
Token ID5741
Feature activation-1.45e+00

Pos logit contributions
terday+1.016
 confir+0.984
pring+0.955
clair+0.952
cale+0.909
Neg logit contributions
rieg-0.703
ambo-0.680
 bloc-0.678
anooga-0.660
 Rove-0.655
Token Jones
Token ID5437
Feature activation-2.57e+00

Pos logit contributions
terday+2.154
 confir+2.089
pring+2.010
clair+2.002
cale+1.916
Neg logit contributions
rieg-1.665
ambo-1.615
 bloc-1.599
anooga-1.571
 Rove-1.549
Token make
Token ID787
Feature activation-1.93e-01

Pos logit contributions
terday+3.215
 confir+3.092
pring+2.975
clair+2.959
cale+2.816
Neg logit contributions
rieg-3.533
ambo-3.435
 bloc-3.402
anooga-3.368
 Rove-3.304
Token up
Token ID510
Feature activation+1.18e-01

Pos logit contributions
terday+0.303
 confir+0.296
pring+0.287
clair+0.286
cale+0.274
Neg logit contributions
rieg-0.202
 bloc-0.196
ambo-0.195
anooga-0.190
 Rove-0.187
Token touch
Token ID3638
Feature activation-2.60e+00

Pos logit contributions
terday+0.706
 confir+0.678
pring+0.656
clair+0.652
cale+0.625
Neg logit contributions
rieg-0.632
ambo-0.612
 bloc-0.610
anooga-0.600
 Rove-0.590
Token of
Token ID286
Feature activation-9.39e-01

Pos logit contributions
terday+2.828
 confir+2.717
pring+2.624
clair+2.611
cale+2.449
Neg logit contributions
rieg-3.925
ambo-3.844
anooga-3.776
 bloc-3.774
 Rove-3.685
Token cl
Token ID537
Feature activation+1.22e+00

Pos logit contributions
terday+1.279
 confir+1.230
pring+1.188
clair+1.183
cale+1.129
Neg logit contributions
rieg-1.195
ambo-1.158
 bloc-1.152
anooga-1.133
 Rove-1.119
Tokenove
Token ID659
Feature activation-1.17e+00

Pos logit contributions
rieg+1.010
ambo+0.980
 bloc+0.935
anooga+0.907
 Rove+0.884
Neg logit contributions
terday-2.221
 confir-2.181
clair-2.075
pring-2.073
cale-2.006
Token (
Token ID357
Feature activation-1.64e-01

Pos logit contributions
terday+1.397
 confir+1.334
pring+1.274
clair+1.267
cale+1.208
Neg logit contributions
rieg-1.683
ambo-1.638
 bloc-1.634
anooga-1.603
 Rove-1.581
Tokenpres
Token ID18302
Feature activation-5.14e+00

Pos logit contributions
terday+0.227
 confir+0.221
pring+0.208
clair+0.205
cale+0.198
Neg logit contributions
rieg-0.206
ambo-0.201
 bloc-0.196
anooga-0.194
 Rove-0.191
Tokenumably
Token ID31303
Feature activation-6.35e-01

Pos logit contributions
terday+4.782
 confir+4.478
pring+4.436
clair+4.309
cale+4.145
Neg logit contributions
rieg-8.526
 bloc-8.304
anooga-8.298
ambo-8.290
 Rove-8.104
Token from
Token ID422
Feature activation-2.93e-01

Pos logit contributions
terday+0.844
 confir+0.807
pring+0.779
clair+0.779
cale+0.741
Neg logit contributions
rieg-0.824
ambo-0.803
 bloc-0.800
 Rove-0.782
anooga-0.782
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
terday+0.438
 confir+0.422
pring+0.408
clair+0.408
cale+0.389
Neg logit contributions
rieg-0.332
ambo-0.323
 bloc-0.320
anooga-0.313
 Rove-0.311
Token sa
Token ID473
Feature activation-1.57e+00

Pos logit contributions
terday+0.370
 confir+0.353
pring+0.342
clair+0.342
cale+0.326
Neg logit contributions
rieg-0.318
ambo-0.310
 bloc-0.309
 Rove-0.300
anooga-0.300
Tokenison
Token ID1653
Feature activation-1.06e+00

Pos logit contributions
terday+2.065
 confir+1.995
pring+1.899
clair+1.882
cale+1.810
Neg logit contributions
rieg-2.091
ambo-2.041
 bloc-2.001
anooga-1.976
 Rove-1.940
Token,
Token ID11
Feature activation+6.89e-01

Pos logit contributions
terday+0.168
 confir+0.162
clair+0.155
pring+0.154
cale+0.147
Neg logit contributions
rieg-0.187
 bloc-0.183
ambo-0.183
 Rove-0.179
anooga-0.178
Token and
Token ID290
Feature activation-1.98e-01

Pos logit contributions
rieg+0.887
 bloc+0.871
ambo+0.870
 Rove+0.852
anooga+0.840
Neg logit contributions
terday-0.913
 confir-0.874
clair-0.847
pring-0.845
cale-0.797
Token they
Token ID484
Feature activation+5.34e-01

Pos logit contributions
terday+0.272
 confir+0.261
clair+0.253
pring+0.253
cale+0.241
Neg logit contributions
rieg-0.248
 bloc-0.242
ambo-0.242
 Rove-0.236
anooga-0.233
Token are
Token ID389
Feature activation+4.39e-01

Pos logit contributions
rieg+0.797
ambo+0.778
 bloc+0.768
anooga+0.751
 Rove+0.747
Neg logit contributions
terday-0.606
 confir-0.569
clair-0.556
pring-0.547
cale-0.523
Token.
Token ID13
Feature activation-2.43e-01

Pos logit contributions
rieg+0.535
ambo+0.521
 bloc+0.518
anooga+0.503
 Rove+0.501
Neg logit contributions
terday-0.620
 confir-0.592
clair-0.576
pring-0.573
cale-0.549
Token Writ
Token ID12257
Feature activation-5.09e+00

Pos logit contributions
terday+0.316
 confir+0.308
clair+0.293
pring+0.292
cale+0.278
Neg logit contributions
rieg-0.324
ambo-0.314
 bloc-0.311
anooga-0.305
 Rove-0.304
Tokenes
Token ID274
Feature activation-1.06e+00

Pos logit contributions
terday+5.763
 confir+5.466
pring+5.272
clair+5.153
cale+4.974
Neg logit contributions
rieg-7.364
ambo-7.208
anooga-7.074
 bloc-7.046
 Rove-6.873
Token Bridges
Token ID41839
Feature activation+9.49e-02

Pos logit contributions
terday+1.628
 confir+1.580
pring+1.530
clair+1.528
cale+1.463
Neg logit contributions
rieg-1.155
ambo-1.114
 bloc-1.104
anooga-1.078
 Rove-1.068
TokenOut
Token ID7975
Feature activation+2.39e-01

Pos logit contributions
rieg+0.135
ambo+0.132
 bloc+0.131
anooga+0.127
 Rove+0.127
Neg logit contributions
terday-0.114
 confir-0.111
clair-0.105
pring-0.103
cale-0.100
TokenOfficial
Token ID28529
Feature activation-1.11e+00

Pos logit contributions
rieg+0.309
ambo+0.299
 bloc+0.297
anooga+0.292
 Rove+0.287
Neg logit contributions
terday-0.324
 confir-0.311
pring-0.298
clair-0.296
cale-0.284
Token:
Token ID25
Feature activation+5.54e-01

Pos logit contributions
terday+1.245
 confir+1.190
pring+1.137
clair+1.133
cale+1.080
Neg logit contributions
rieg-1.668
ambo-1.628
 bloc-1.616
anooga-1.596
 Rove-1.572
Token lower
Token ID2793
Feature activation+4.47e-01

Pos logit contributions
terday+1.656
 confir+1.601
clair+1.546
pring+1.545
cale+1.470
Neg logit contributions
rieg-1.479
 bloc-1.433
ambo-1.430
anooga-1.394
 Rove-1.379
Token the
Token ID262
Feature activation-8.46e-01

Pos logit contributions
rieg+0.499
 bloc+0.484
ambo+0.480
anooga+0.468
 Rove+0.464
Neg logit contributions
terday-0.673
 confir-0.652
clair-0.631
pring-0.626
cale-0.600
Token wife
Token ID3656
Feature activation+9.91e-02

Pos logit contributions
terday+1.088
 confir+1.045
clair+1.008
pring+1.001
cale+0.951
Neg logit contributions
rieg-1.141
 bloc-1.111
ambo-1.105
anooga-1.081
 Rove-1.069
Token's
Token ID338
Feature activation-1.54e+00

Pos logit contributions
rieg+0.116
ambo+0.112
 bloc+0.112
anooga+0.109
 Rove+0.107
Neg logit contributions
terday-0.146
 confir-0.140
clair-0.135
pring-0.135
cale-0.129
Token life
Token ID1204
Feature activation-2.28e+00

Pos logit contributions
terday+1.961
 confir+1.884
clair+1.816
pring+1.805
cale+1.712
Neg logit contributions
rieg-2.107
ambo-2.046
 bloc-2.044
anooga-2.004
 Rove-1.975
Token expectancy
Token ID29098
Feature activation-5.03e+00

Pos logit contributions
terday+1.922
 confir+1.817
pring+1.717
clair+1.695
cale+1.574
Neg logit contributions
rieg-4.065
ambo-3.981
 bloc-3.943
anooga-3.919
 Rove-3.862
Token.
Token ID13
Feature activation-9.13e-01

Pos logit contributions
terday+5.325
 confir+5.019
pring+4.931
clair+4.773
cale+4.621
Neg logit contributions
rieg-7.708
ambo-7.520
anooga-7.396
 bloc-7.317
 Rove-7.225
Token This
Token ID770
Feature activation-6.37e-01

Pos logit contributions
terday+1.204
 confir+1.168
pring+1.116
clair+1.114
cale+1.062
Neg logit contributions
rieg-1.201
ambo-1.164
 bloc-1.153
anooga-1.135
 Rove-1.124
Token is
Token ID318
Feature activation-1.61e-01

Pos logit contributions
terday+0.843
 confir+0.808
clair+0.783
pring+0.782
cale+0.741
Neg logit contributions
rieg-0.833
 bloc-0.810
ambo-0.808
anooga-0.787
 Rove-0.782
Token the
Token ID262
Feature activation-1.18e+00

Pos logit contributions
terday+0.220
 confir+0.209
clair+0.204
pring+0.204
cale+0.193
Neg logit contributions
rieg-0.203
 bloc-0.199
ambo-0.197
 Rove-0.193
anooga-0.191
Token case
Token ID1339
Feature activation-6.33e-01

Pos logit contributions
terday+1.399
 confir+1.333
pring+1.282
clair+1.280
cale+1.210
Neg logit contributions
rieg-1.707
 bloc-1.659
ambo-1.656
anooga-1.620
 Rove-1.612
TokenB
Token ID33
Feature activation+1.22e+00

Pos logit contributions
terday+0.009
 confir+0.009
pring+0.008
clair+0.008
cale+0.008
Neg logit contributions
rieg-0.009
ambo-0.009
anooga-0.009
 bloc-0.009
 Rove-0.009
Tokenart
Token ID433
Feature activation+2.74e-01

Pos logit contributions
rieg+1.371
ambo+1.327
 bloc+1.293
anooga+1.285
 Rove+1.246
Neg logit contributions
terday-1.837
 confir-1.784
pring-1.716
clair-1.710
cale-1.642
Token's
Token ID338
Feature activation-1.47e+00

Pos logit contributions
rieg+0.362
ambo+0.352
 bloc+0.346
anooga+0.344
 Rove+0.338
Neg logit contributions
terday-0.358
 confir-0.346
pring-0.336
clair-0.330
cale-0.316
Token owner
Token ID4870
Feature activation-1.66e+00

Pos logit contributions
terday+2.045
 confir+1.974
pring+1.920
clair+1.909
cale+1.822
Neg logit contributions
rieg-1.821
ambo-1.763
 bloc-1.757
anooga-1.726
 Rove-1.699
Token,
Token ID11
Feature activation-6.95e-01

Pos logit contributions
terday+2.169
 confir+2.091
pring+2.018
clair+2.009
cale+1.915
Neg logit contributions
rieg-2.188
ambo-2.127
 bloc-2.109
anooga-2.081
 Rove-2.048
Token Ellis
Token ID21299
Feature activation-5.02e+00

Pos logit contributions
terday+1.062
 confir+1.028
pring+0.998
clair+0.994
cale+0.953
Neg logit contributions
rieg-0.767
ambo-0.742
 bloc-0.737
anooga-0.721
 Rove-0.711
Token Hut
Token ID32767
Feature activation+5.90e-01

Pos logit contributions
terday+7.402
 confir+7.022
pring+6.979
clair+6.914
cale+6.659
Neg logit contributions
rieg-5.627
ambo-5.408
 bloc-5.328
anooga-5.320
 Rove-5.041
Tokenson
Token ID1559
Feature activation-1.53e+00

Pos logit contributions
rieg+0.752
ambo+0.738
 bloc+0.720
anooga+0.715
 Rove+0.696
Neg logit contributions
terday-0.801
 confir-0.781
pring-0.735
clair-0.732
cale-0.701
Token,
Token ID11
Feature activation-8.49e-01

Pos logit contributions
terday+1.728
 confir+1.656
pring+1.586
clair+1.576
cale+1.491
Neg logit contributions
rieg-2.297
ambo-2.238
 bloc-2.216
anooga-2.199
 Rove-2.160
Token told
Token ID1297
Feature activation-7.72e-01

Pos logit contributions
terday+1.023
 confir+0.981
pring+0.945
clair+0.943
cale+0.896
Neg logit contributions
rieg-1.202
ambo-1.176
 bloc-1.169
anooga-1.147
 Rove-1.133
Token the
Token ID262
Feature activation-7.23e-01

Pos logit contributions
terday+1.151
 confir+1.116
pring+1.082
clair+1.079
cale+1.032
Neg logit contributions
rieg-0.875
ambo-0.855
 bloc-0.845
anooga-0.824
 Rove-0.815
Token a
Token ID257
Feature activation+6.74e-01

Pos logit contributions
rieg+1.018
 bloc+1.000
ambo+0.992
 Rove+0.960
anooga+0.946
Neg logit contributions
terday-1.372
 confir-1.320
pring-1.287
clair-1.279
cale-1.221
Token skin
Token ID4168
Feature activation-7.39e-01

Pos logit contributions
rieg+0.865
ambo+0.839
 bloc+0.835
anooga+0.820
 Rove+0.806
Neg logit contributions
terday-0.905
 confir-0.871
pring-0.840
clair-0.837
cale-0.798
Token condition
Token ID4006
Feature activation-3.75e+00

Pos logit contributions
terday+0.964
 confir+0.928
pring+0.891
clair+0.888
cale+0.848
Neg logit contributions
rieg-0.984
ambo-0.951
 bloc-0.948
anooga-0.930
 Rove-0.914
Token,
Token ID11
Feature activation-1.18e+00

Pos logit contributions
terday+4.601
 confir+4.424
pring+4.262
clair+4.224
cale+4.039
Neg logit contributions
rieg-5.233
ambo-5.093
 bloc-5.024
anooga-5.003
 Rove-4.880
Token an
Token ID281
Feature activation-9.08e-01

Pos logit contributions
terday+1.593
 confir+1.529
pring+1.481
clair+1.471
cale+1.404
Neg logit contributions
rieg-1.523
ambo-1.479
 bloc-1.470
anooga-1.444
 Rove-1.430
Token autos
Token ID44619
Feature activation-5.01e+00

Pos logit contributions
terday+1.185
 confir+1.143
pring+1.105
clair+1.096
cale+1.044
Neg logit contributions
rieg-1.208
ambo-1.171
 bloc-1.162
anooga-1.144
 Rove-1.130
Tokenomal
Token ID18048
Feature activation-1.61e+00

Pos logit contributions
terday+6.798
 confir+6.481
pring+6.481
clair+6.331
cale+6.161
Neg logit contributions
rieg-6.152
ambo-5.906
anooga-5.900
 bloc-5.882
 Rove-5.730
Token dominant
Token ID11410
Feature activation-3.68e-01

Pos logit contributions
terday+2.004
 confir+1.926
pring+1.856
clair+1.840
cale+1.750
Neg logit contributions
rieg-2.225
ambo-2.165
 bloc-2.148
anooga-2.115
 Rove-2.089
Token palm
Token ID18057
Feature activation-8.35e-01

Pos logit contributions
terday+0.510
 confir+0.492
pring+0.475
clair+0.473
cale+0.448
Neg logit contributions
rieg-0.460
 bloc-0.447
ambo-0.445
anooga-0.433
 Rove-0.431
Tokenopl
Token ID20106
Feature activation-6.70e-01

Pos logit contributions
terday+1.089
 confir+1.050
pring+1.008
clair+1.005
cale+0.958
Neg logit contributions
rieg-1.108
ambo-1.077
 bloc-1.067
anooga-1.051
 Rove-1.034
Tokenant
Token ID415
Feature activation+3.03e-01

Pos logit contributions
terday+1.044
 confir+1.014
pring+0.982
clair+0.977
cale+0.940
Neg logit contributions
rieg-0.717
ambo-0.692
 bloc-0.683
anooga-0.673
 Rove-0.657
Token it
Token ID340
Feature activation+9.11e-01

Pos logit contributions
rieg+2.105
ambo+2.053
 bloc+2.050
anooga+2.014
 Rove+1.999
Neg logit contributions
terday-1.436
 confir-1.383
clair-1.324
pring-1.302
cale-1.234
Token is
Token ID318
Feature activation-4.15e-01

Pos logit contributions
rieg+1.139
ambo+1.107
 bloc+1.100
anooga+1.086
 Rove+1.067
Neg logit contributions
terday-1.245
 confir-1.205
clair-1.159
pring-1.157
cale-1.111
Token,
Token ID11
Feature activation-5.74e-01

Pos logit contributions
terday+0.464
 confir+0.448
clair+0.426
pring+0.425
cale+0.400
Neg logit contributions
rieg-0.624
ambo-0.608
 bloc-0.606
anooga-0.595
 Rove-0.588
Token without
Token ID1231
Feature activation-1.32e+00

Pos logit contributions
terday+0.808
 confir+0.782
pring+0.754
clair+0.752
cale+0.719
Neg logit contributions
rieg-0.702
ambo-0.680
 bloc-0.676
anooga-0.663
 Rove-0.653
Token further
Token ID2252
Feature activation-3.74e-01

Pos logit contributions
terday+1.949
 confir+1.889
pring+1.827
clair+1.817
cale+1.745
Neg logit contributions
rieg-1.532
ambo-1.482
 bloc-1.462
anooga-1.450
 Rove-1.413
Token ado
Token ID50129
Feature activation-4.99e+00

Pos logit contributions
terday+0.577
 confir+0.551
pring+0.538
clair+0.536
cale+0.512
Neg logit contributions
rieg-0.411
ambo-0.396
 bloc-0.393
anooga-0.384
 Rove-0.380
Token:
Token ID25
Feature activation-4.47e-01

Pos logit contributions
terday+4.911
 confir+4.628
pring+4.522
clair+4.390
cale+4.191
Neg logit contributions
rieg-7.908
ambo-7.754
anooga-7.647
 bloc-7.570
 Rove-7.470
Token one
Token ID530
Feature activation+1.23e+00

Pos logit contributions
terday+0.588
 confir+0.567
pring+0.546
clair+0.543
cale+0.518
Neg logit contributions
rieg-0.590
ambo-0.573
 bloc-0.567
anooga-0.560
 Rove-0.551
Token man
Token ID582
Feature activation+2.23e+00

Pos logit contributions
rieg+1.651
 bloc+1.610
ambo+1.596
anooga+1.569
 Rove+1.561
Neg logit contributions
terday-1.579
 confir-1.530
clair-1.473
pring-1.461
cale-1.392
Token
Token ID447
Feature activation+7.34e-02

Pos logit contributions
rieg+2.706
ambo+2.626
 bloc+2.611
anooga+2.521
 Rove+2.503
Neg logit contributions
terday-3.133
 confir-3.007
clair-2.918
pring-2.909
cale-2.781
Token
Token ID247
Feature activation-1.78e+00

Pos logit contributions
rieg+0.088
ambo+0.085
 bloc+0.084
anooga+0.083
 Rove+0.082
Neg logit contributions
terday-0.105
 confir-0.102
clair-0.098
pring-0.097
cale-0.094
Token close
Token ID1969
Feature activation+1.27e+00

Pos logit contributions
rieg+1.655
 bloc+1.603
ambo+1.593
 Rove+1.557
anooga+1.553
Neg logit contributions
terday-1.957
 confir-1.813
clair-1.784
pring-1.761
cale-1.688
Token Bit
Token ID4722
Feature activation+1.80e+00

Pos logit contributions
rieg+1.381
 bloc+1.333
ambo+1.326
 Rove+1.294
anooga+1.277
Neg logit contributions
terday-1.940
 confir-1.855
clair-1.825
pring-1.795
cale-1.739
Tokenmap
Token ID8899
Feature activation+2.79e+00

Pos logit contributions
rieg+1.511
ambo+1.465
 bloc+1.427
anooga+1.391
 Rove+1.352
Neg logit contributions
terday-3.239
 confir-3.119
clair-3.031
pring-3.029
cale-2.912
Token $
Token ID720
Feature activation+1.68e+00

Pos logit contributions
rieg+3.088
 bloc+3.021
ambo+3.016
 Rove+2.928
anooga+2.897
Neg logit contributions
terday-4.129
 confir-3.947
clair-3.878
pring-3.859
cale-3.655
Tokenb
Token ID65
Feature activation+3.23e+00

Pos logit contributions
rieg+2.019
ambo+1.967
 bloc+1.907
anooga+1.890
 Rove+1.858
Neg logit contributions
terday-2.379
 confir-2.326
pring-2.173
clair-2.159
cale-2.062
Tokenmp
Token ID3149
Feature activation+4.07e+00

Pos logit contributions
rieg+2.893
ambo+2.873
 bloc+2.660
owler+2.560
anooga+2.528
Neg logit contributions
 confir-5.645
terday-5.572
pring-5.145
clair-5.087
utics-4.918
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
rieg+5.633
ambo+5.551
 bloc+5.472
anooga+5.354
 Rove+5.351
Neg logit contributions
terday-4.806
 confir-4.657
clair-4.350
pring-4.267
utics-3.975
TokenSave
Token ID16928
Feature activation+1.53e+00

Pos logit contributions
rieg+1.835
ambo+1.777
 bloc+1.735
anooga+1.725
 Rove+1.706
Neg logit contributions
terday-2.050
 confir-1.988
pring-1.864
clair-1.857
cale-1.784
Token($
Token ID16763
Feature activation+2.46e+00

Pos logit contributions
rieg+1.798
ambo+1.742
 bloc+1.718
anooga+1.695
 Rove+1.666
Neg logit contributions
terday-2.206
 confir-2.167
clair-2.052
pring-2.040
cale-1.956
TokenOut
Token ID7975
Feature activation+1.88e+00

Pos logit contributions
rieg+2.781
ambo+2.707
 bloc+2.595
anooga+2.594
 Rove+2.569
Neg logit contributions
terday-3.632
 confir-3.563
pring-3.304
clair-3.303
cale-3.159
TokenFile
Token ID8979
Feature activation+5.24e-01

Pos logit contributions
rieg+2.333
ambo+2.240
 bloc+2.238
anooga+2.165
 Rove+2.155
Neg logit contributions
terday-2.611
 confir-2.568
clair-2.368
pring-2.342
utics-2.255
Token by
Token ID416
Feature activation+1.01e+00

Pos logit contributions
rieg+2.284
 bloc+2.259
ambo+2.229
 Rove+2.147
anooga+2.134
Neg logit contributions
terday-2.040
 confir-1.982
clair-1.884
pring-1.872
utics-1.775
Token pro
Token ID386
Feature activation+5.41e-01

Pos logit contributions
rieg+1.078
 bloc+1.040
ambo+1.033
anooga+1.001
 Rove+1.000
Neg logit contributions
terday-1.571
 confir-1.526
pring-1.493
clair-1.482
cale-1.413
Token-
Token ID12
Feature activation+6.68e-01

Pos logit contributions
rieg+0.785
ambo+0.764
 bloc+0.758
anooga+0.748
 Rove+0.737
Neg logit contributions
terday-0.640
 confir-0.617
pring-0.589
clair-0.585
cale-0.554
TokenK
Token ID42
Feature activation+2.24e+00

Pos logit contributions
rieg+0.801
ambo+0.778
 bloc+0.771
anooga+0.753
 Rove+0.743
Neg logit contributions
terday-0.961
 confir-0.933
pring-0.903
clair-0.890
cale-0.849
Tokeniev
Token ID11203
Feature activation+1.40e+00

Pos logit contributions
rieg+3.010
ambo+2.916
 bloc+2.869
anooga+2.811
 Rove+2.759
Neg logit contributions
terday-2.916
 confir-2.823
pring-2.722
clair-2.688
cale-2.575
Token fascists
Token ID48594
Feature activation+3.86e+00

Pos logit contributions
rieg+1.197
 bloc+1.162
ambo+1.136
anooga+1.085
 Rove+1.078
Neg logit contributions
terday-2.476
 confir-2.408
pring-2.354
clair-2.348
cale-2.255
Token working
Token ID1762
Feature activation+1.96e+00

Pos logit contributions
rieg+5.344
 bloc+5.238
ambo+5.144
 Rove+5.023
anooga+4.919
Neg logit contributions
terday-4.600
 confir-4.505
clair-4.242
pring-4.214
utics-4.030
Token with
Token ID351
Feature activation+1.35e+00

Pos logit contributions
rieg+2.556
 bloc+2.512
ambo+2.475
 Rove+2.390
anooga+2.379
Neg logit contributions
terday-2.598
 confir-2.529
pring-2.406
clair-2.403
cale-2.262
Token Black
Token ID2619
Feature activation+2.17e+00

Pos logit contributions
rieg+1.465
 bloc+1.418
ambo+1.405
 Rove+1.367
anooga+1.360
Neg logit contributions
terday-2.077
 confir-2.014
pring-1.968
clair-1.946
cale-1.858
Tokenwater
Token ID7050
Feature activation+1.52e+00

Pos logit contributions
rieg+2.630
 bloc+2.614
ambo+2.568
 Rove+2.482
anooga+2.445
Neg logit contributions
terday-3.053
 confir-2.971
pring-2.856
clair-2.854
cale-2.720
Token mercenaries
Token ID37569
Feature activation+3.14e+00

Pos logit contributions
rieg+2.078
 bloc+2.037
ambo+2.013
 Rove+1.956
anooga+1.929
Neg logit contributions
terday-1.914
 confir-1.850
clair-1.779
pring-1.762
cale-1.658
Token and
Token ID290
Feature activation+4.91e-01

Pos logit contributions
terday+2.102
 confir+2.024
pring+1.959
clair+1.947
cale+1.859
Neg logit contributions
rieg-2.041
ambo-1.985
 bloc-1.948
anooga-1.945
 Rove-1.900
Token his
Token ID465
Feature activation+1.28e+00

Pos logit contributions
rieg+0.549
ambo+0.525
 bloc+0.525
anooga+0.513
 Rove+0.507
Neg logit contributions
terday-0.746
 confir-0.726
pring-0.703
clair-0.696
cale-0.669
Token allies
Token ID7681
Feature activation+3.19e+00

Pos logit contributions
rieg+1.388
 bloc+1.369
ambo+1.331
 Rove+1.303
anooga+1.282
Neg logit contributions
terday-1.975
 confir-1.902
pring-1.848
clair-1.835
cale-1.756
Token of
Token ID286
Feature activation+1.56e-01

Pos logit contributions
rieg+4.043
 bloc+4.025
ambo+3.943
 Rove+3.883
anooga+3.711
Neg logit contributions
terday-4.072
 confir-3.958
clair-3.811
pring-3.745
utics-3.597
Token the
Token ID262
Feature activation+7.32e-01

Pos logit contributions
rieg+0.174
ambo+0.167
 bloc+0.166
anooga+0.163
 Rove+0.160
Neg logit contributions
terday-0.236
 confir-0.229
pring-0.222
clair-0.221
cale-0.212
Token Mil
Token ID4460
Feature activation+3.49e+00

Pos logit contributions
rieg+0.831
 bloc+0.807
ambo+0.796
anooga+0.777
 Rove+0.773
Neg logit contributions
terday-1.093
 confir-1.065
pring-1.025
clair-1.025
cale-0.981
Tokenitant
Token ID23737
Feature activation+3.31e+00

Pos logit contributions
rieg+3.130
ambo+3.012
 bloc+2.899
anooga+2.772
 Rove+2.663
Neg logit contributions
 confir-6.071
terday-5.976
pring-5.558
clair-5.502
cale-5.328
Token faction
Token ID17710
Feature activation+4.32e+00

Pos logit contributions
rieg+2.643
 bloc+2.610
ambo+2.425
anooga+2.350
 Rove+2.333
Neg logit contributions
terday-5.944
 confir-5.795
clair-5.673
pring-5.611
cale-5.438
Token on
Token ID319
Feature activation+1.03e+00

Pos logit contributions
 bloc+5.499
rieg+5.435
ambo+5.292
 Rove+5.177
anooga+4.938
Neg logit contributions
terday-5.383
 confir-5.211
clair-5.056
pring-4.977
utics-4.784
Token the
Token ID262
Feature activation+7.90e-01

Pos logit contributions
rieg+1.140
 bloc+1.107
ambo+1.099
anooga+1.064
 Rove+1.058
Neg logit contributions
terday-1.554
 confir-1.509
pring-1.464
clair-1.458
cale-1.390
Token one
Token ID530
Feature activation+2.76e+00

Pos logit contributions
rieg+1.003
 bloc+0.981
ambo+0.970
anooga+0.945
 Rove+0.938
Neg logit contributions
terday-1.072
 confir-1.036
clair-1.000
pring-0.995
cale-0.943
Token &
Token ID1222
Feature activation+4.61e-01

Pos logit contributions
rieg+2.215
ambo+2.167
 bloc+2.129
 Rove+2.084
anooga+2.070
Neg logit contributions
terday-2.428
 confir-2.349
clair-2.246
pring-2.236
cale-2.133
Token Danny
Token ID15105
Feature activation+1.98e+00

Pos logit contributions
rieg+0.514
ambo+0.498
 bloc+0.492
 Rove+0.483
anooga+0.477
Neg logit contributions
terday-0.702
 confir-0.684
clair-0.655
pring-0.653
cale-0.624
Token Fight
Token ID10480
Feature activation+2.42e+00

Pos logit contributions
rieg+2.434
ambo+2.370
 bloc+2.328
 Rove+2.312
anooga+2.266
Neg logit contributions
terday-2.761
 confir-2.693
clair-2.552
pring-2.536
cale-2.414
Token With
Token ID2080
Feature activation+1.87e+00

Pos logit contributions
rieg+3.007
ambo+2.904
 bloc+2.897
 Rove+2.861
anooga+2.822
Neg logit contributions
terday-3.311
 confir-3.244
clair-3.105
pring-3.061
cale-2.928
Token Each
Token ID5501
Feature activation+1.93e+00

Pos logit contributions
rieg+2.061
ambo+1.994
 bloc+1.991
 Rove+1.982
anooga+1.925
Neg logit contributions
terday-2.834
 confir-2.772
clair-2.633
pring-2.600
cale-2.495
Tokenother
Token ID847
Feature activation+3.44e+00

Pos logit contributions
rieg+2.019
ambo+1.950
 bloc+1.924
anooga+1.888
 Rove+1.869
Neg logit contributions
terday-3.064
 confir-2.977
clair-2.865
pring-2.854
cale-2.717
Token 200
Token ID939
Feature activation+8.34e-01

Pos logit contributions
rieg+4.312
ambo+4.199
 bloc+4.147
 Rove+4.075
anooga+4.015
Neg logit contributions
terday-4.632
 confir-4.516
clair-4.358
pring-4.231
cale-4.033
Token80
Token ID1795
Feature activation+1.27e+00

Pos logit contributions
rieg+1.239
ambo+1.218
 bloc+1.210
 Rove+1.167
anooga+1.160
Neg logit contributions
terday-0.944
 confir-0.924
clair-0.868
pring-0.857
cale-0.804
Token205
Token ID21261
Feature activation-1.27e+00

Pos logit contributions
rieg+1.760
 bloc+1.674
ambo+1.665
 Rove+1.638
anooga+1.592
Neg logit contributions
 confir-1.635
terday-1.620
clair-1.475
pring-1.422
cale-1.371
Token O
Token ID440
Feature activation+4.20e-01

Pos logit contributions
terday+1.436
 confir+1.356
pring+1.322
clair+1.306
cale+1.247
Neg logit contributions
rieg-1.896
ambo-1.852
anooga-1.836
 bloc-1.828
 Rove-1.770
Token&
Token ID5
Feature activation+8.20e-01

Pos logit contributions
rieg+0.601
ambo+0.584
 bloc+0.574
 Rove+0.561
anooga+0.559
Neg logit contributions
terday-0.514
 confir-0.509
pring-0.464
clair-0.464
cale-0.437
Token win
Token ID1592
Feature activation+1.47e-01

Pos logit contributions
terday+1.075
 confir+1.023
pring+0.993
clair+0.977
cale+0.945
Neg logit contributions
rieg-1.016
ambo-0.994
 bloc-0.993
 Rove-0.950
anooga-0.940
Token for
Token ID329
Feature activation+6.78e-01

Pos logit contributions
rieg+0.190
ambo+0.186
 bloc+0.184
anooga+0.180
 Rove+0.178
Neg logit contributions
terday-0.196
 confir-0.189
pring-0.181
clair-0.181
cale-0.172
Token Out
Token ID3806
Feature activation+8.11e-01

Pos logit contributions
rieg+0.676
ambo+0.659
 bloc+0.648
anooga+0.632
 Rove+0.623
Neg logit contributions
terday-1.106
 confir-1.072
pring-1.040
clair-1.039
cale-0.993
Tokenstanding
Token ID5646
Feature activation+1.12e+00

Pos logit contributions
rieg+0.767
ambo+0.738
 bloc+0.724
anooga+0.708
 Rove+0.691
Neg logit contributions
terday-1.381
 confir-1.357
clair-1.278
pring-1.275
cale-1.226
Token Supporting
Token ID44188
Feature activation+2.31e+00

Pos logit contributions
rieg+1.201
ambo+1.178
 bloc+1.152
anooga+1.134
 Rove+1.116
Neg logit contributions
terday-1.741
 confir-1.693
clair-1.633
pring-1.631
cale-1.550
Token Actor
Token ID27274
Feature activation+3.44e+00

Pos logit contributions
rieg+2.410
ambo+2.357
 bloc+2.344
anooga+2.264
 Rove+2.256
Neg logit contributions
terday-3.654
 confir-3.530
clair-3.400
pring-3.361
cale-3.240
Token in
Token ID287
Feature activation+8.76e-01

Pos logit contributions
rieg+3.792
ambo+3.741
 bloc+3.722
 Rove+3.521
anooga+3.513
Neg logit contributions
terday-5.087
 confir-4.876
clair-4.713
pring-4.623
cale-4.458
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
rieg+1.024
ambo+0.996
 bloc+0.985
anooga+0.982
 Rove+0.957
Neg logit contributions
terday-1.279
 confir-1.238
pring-1.186
clair-1.186
cale-1.131
Token Comedy
Token ID22329
Feature activation+2.21e+00

Pos logit contributions
rieg+1.646
ambo+1.605
 bloc+1.595
anooga+1.571
 Rove+1.555
Neg logit contributions
terday-1.574
 confir-1.512
clair-1.439
pring-1.430
cale-1.358
Token,
Token ID11
Feature activation+2.88e-01

Pos logit contributions
rieg+2.592
ambo+2.542
 bloc+2.525
anooga+2.452
 Rove+2.441
Neg logit contributions
terday-3.170
 confir-3.047
pring-2.933
clair-2.922
cale-2.782
Token for
Token ID329
Feature activation+3.38e-01

Pos logit contributions
rieg+0.371
ambo+0.364
 bloc+0.360
anooga+0.351
 Rove+0.350
Neg logit contributions
terday-0.388
 confir-0.371
pring-0.358
clair-0.356
cale-0.340
Token.
Token ID13
Feature activation-6.44e-02

Pos logit contributions
terday+1.685
 confir+1.636
pring+1.557
clair+1.556
cale+1.470
Neg logit contributions
rieg-2.055
ambo-1.992
 bloc-1.990
anooga-1.945
 Rove-1.926
Token But
Token ID887
Feature activation+2.32e+00

Pos logit contributions
terday+0.088
 confir+0.086
pring+0.082
clair+0.082
cale+0.078
Neg logit contributions
rieg-0.081
ambo-0.079
 bloc-0.078
anooga-0.077
 Rove-0.076
Token even
Token ID772
Feature activation+1.98e+00

Pos logit contributions
rieg+2.810
 bloc+2.796
ambo+2.715
 Rove+2.710
anooga+2.615
Neg logit contributions
terday-3.125
 confir-3.105
pring-3.014
clair-2.972
utics-2.818
Token though
Token ID996
Feature activation+1.22e+00

Pos logit contributions
rieg+2.513
 bloc+2.478
ambo+2.432
 Rove+2.409
anooga+2.328
Neg logit contributions
terday-2.627
 confir-2.581
pring-2.520
clair-2.486
utics-2.338
Token Republicans
Token ID4734
Feature activation+3.74e-01

Pos logit contributions
rieg+1.427
 bloc+1.391
ambo+1.368
 Rove+1.352
anooga+1.315
Neg logit contributions
terday-1.736
 confir-1.696
pring-1.668
clair-1.642
cale-1.562
Token took
Token ID1718
Feature activation+4.49e-02

Pos logit contributions
rieg+0.533
 bloc+0.521
ambo+0.517
 Rove+0.506
anooga+0.502
Neg logit contributions
terday-0.447
 confir-0.431
pring-0.414
clair-0.413
utics-0.387
Token 10
Token ID838
Feature activation-7.92e-01

Pos logit contributions
rieg+0.054
ambo+0.052
 bloc+0.052
anooga+0.051
 Rove+0.051
Neg logit contributions
terday-0.064
 confir-0.062
clair-0.060
pring-0.060
cale-0.057
Token days
Token ID1528
Feature activation-1.75e+00

Pos logit contributions
terday+1.108
 confir+1.076
pring+1.039
clair+1.036
cale+0.987
Neg logit contributions
rieg-0.976
 bloc-0.942
ambo-0.940
anooga-0.918
 Rove-0.907
Token off
Token ID572
Feature activation+2.45e-01

Pos logit contributions
terday+2.368
 confir+2.306
clair+2.218
pring+2.209
cale+2.093
Neg logit contributions
rieg-2.221
ambo-2.147
 bloc-2.142
anooga-2.081
 Rove-2.073
Token,
Token ID11
Feature activation-2.23e-01

Pos logit contributions
rieg+0.337
 bloc+0.326
ambo+0.324
 Rove+0.316
anooga+0.315
Neg logit contributions
terday-0.304
 confir-0.297
clair-0.286
pring-0.285
cale-0.268
Token the
Token ID262
Feature activation-6.24e-01

Pos logit contributions
terday+0.306
 confir+0.297
pring+0.289
clair+0.286
cale+0.272
Neg logit contributions
rieg-0.279
 bloc-0.271
ambo-0.271
anooga-0.263
 Rove-0.263
Token
Token ID198
Feature activation+1.05e-02

Pos logit contributions
terday+0.737
 confir+0.707
pring+0.680
clair+0.676
cale+0.641
Neg logit contributions
rieg-0.888
ambo-0.864
 bloc-0.854
anooga-0.848
 Rove-0.832
Token
Token ID198
Feature activation+1.63e-02

Pos logit contributions
rieg+0.015
ambo+0.014
 bloc+0.014
anooga+0.014
 Rove+0.014
Neg logit contributions
terday-0.013
 confir-0.013
pring-0.012
clair-0.012
cale-0.011
Token……
Token ID7398
Feature activation+1.56e+00

Pos logit contributions
rieg+0.024
ambo+0.023
 bloc+0.023
anooga+0.023
 Rove+0.022
Neg logit contributions
terday-0.019
 confir-0.019
pring-0.018
clair-0.017
cale-0.017
Token..
Token ID492
Feature activation+1.13e+00

Pos logit contributions
rieg+2.409
ambo+2.337
 bloc+2.327
anooga+2.306
 Rove+2.258
Neg logit contributions
terday-1.676
 confir-1.615
pring-1.526
clair-1.520
cale-1.440
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
rieg+1.541
ambo+1.490
 bloc+1.470
anooga+1.437
 Rove+1.436
Neg logit contributions
 confir-1.451
terday-1.448
pring-1.328
clair-1.322
cale-1.254
Token
Token ID198
Feature activation+1.82e-01

Pos logit contributions
rieg+0.217
ambo+0.210
 bloc+0.208
anooga+0.204
 Rove+0.202
Neg logit contributions
terday-0.195
 confir-0.193
pring-0.179
clair-0.178
cale-0.169
TokenDear
Token ID20266
Feature activation-1.88e+00

Pos logit contributions
rieg+0.279
ambo+0.271
anooga+0.265
 bloc+0.264
 Rove+0.259
Neg logit contributions
terday-0.202
 confir-0.196
pring-0.183
clair-0.180
cale-0.172
Token George
Token ID4502
Feature activation-1.73e-01

Pos logit contributions
terday+2.787
 confir+2.699
pring+2.613
clair+2.601
cale+2.497
Neg logit contributions
rieg-2.164
ambo-2.090
 bloc-2.067
anooga-2.040
 Rove-2.000
Token,
Token ID11
Feature activation+8.06e-01

Pos logit contributions
terday+0.193
 confir+0.185
pring+0.177
clair+0.176
cale+0.166
Neg logit contributions
rieg-0.261
ambo-0.254
 bloc-0.252
anooga-0.250
 Rove-0.246
Token
Token ID198
Feature activation+1.78e-02

Pos logit contributions
rieg+1.089
ambo+1.057
 bloc+1.048
anooga+1.023
 Rove+1.022
Neg logit contributions
terday-1.029
 confir-1.017
pring-0.952
clair-0.946
cale-0.896
Token
Token ID198
Feature activation+2.11e-02

Pos logit contributions
rieg+0.025
ambo+0.024
 bloc+0.024
anooga+0.023
 Rove+0.023
Neg logit contributions
terday-0.022
 confir-0.022
pring-0.020
clair-0.020
cale-0.019
Token and
Token ID290
Feature activation-8.77e-01

Pos logit contributions
terday+1.980
 confir+1.902
pring+1.805
clair+1.803
cale+1.696
Neg logit contributions
rieg-2.641
ambo-2.576
 bloc-2.561
anooga-2.525
 Rove-2.482
Token bring
Token ID2222
Feature activation+1.93e-01

Pos logit contributions
terday+1.140
 confir+1.092
pring+1.055
clair+1.050
cale+0.998
Neg logit contributions
rieg-1.168
ambo-1.134
 bloc-1.130
anooga-1.109
 Rove-1.096
Token around
Token ID1088
Feature activation+1.50e+00

Pos logit contributions
rieg+0.223
ambo+0.215
 bloc+0.214
anooga+0.209
 Rove+0.206
Neg logit contributions
terday-0.285
 confir-0.276
clair-0.268
pring-0.268
cale-0.254
Token 100
Token ID1802
Feature activation-7.93e-01

Pos logit contributions
rieg+1.719
 bloc+1.691
ambo+1.666
 Rove+1.617
anooga+1.596
Neg logit contributions
terday-2.195
 confir-2.116
pring-2.054
clair-2.052
cale-1.926
Token jobs
Token ID3946
Feature activation-5.10e-01

Pos logit contributions
terday+1.149
 confir+1.113
pring+1.075
clair+1.073
cale+1.022
Neg logit contributions
rieg-0.940
ambo-0.907
 bloc-0.905
anooga-0.888
 Rove-0.869
Token to
Token ID284
Feature activation+1.88e-01

Pos logit contributions
terday+0.580
 confir+0.557
clair+0.533
pring+0.525
cale+0.497
Neg logit contributions
rieg-0.761
 bloc-0.745
ambo-0.743
anooga-0.734
 Rove-0.718
Token the
Token ID262
Feature activation+1.76e-02

Pos logit contributions
rieg+0.205
ambo+0.198
 bloc+0.197
anooga+0.194
 Rove+0.190
Neg logit contributions
terday-0.288
 confir-0.280
clair-0.271
pring-0.270
cale-0.258
Token surrounding
Token ID7346
Feature activation+3.11e+00

Pos logit contributions
rieg+0.019
ambo+0.018
 bloc+0.018
anooga+0.018
 Rove+0.018
Neg logit contributions
terday-0.027
 confir-0.026
clair-0.026
pring-0.026
cale-0.024
Token communities
Token ID5348
Feature activation+5.78e-01

Pos logit contributions
 bloc+2.856
rieg+2.825
ambo+2.734
anooga+2.682
 Rove+2.643
Neg logit contributions
terday-5.208
 confir-5.056
clair-4.942
pring-4.856
cale-4.664
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
rieg+0.867
 bloc+0.852
ambo+0.848
anooga+0.831
 Rove+0.819
Neg logit contributions
terday-0.648
 confir-0.620
clair-0.583
pring-0.574
cale-0.545
Token
Token ID198
Feature activation+2.85e-01

Pos logit contributions
rieg+0.179
ambo+0.173
 bloc+0.172
anooga+0.170
 Rove+0.167
Neg logit contributions
terday-0.183
 confir-0.178
clair-0.170
pring-0.169
cale-0.162
Token Democrat
Token ID9755
Feature activation+3.38e-01

Pos logit contributions
terday+0.182
 confir+0.175
pring+0.170
clair+0.168
cale+0.161
Neg logit contributions
rieg-0.158
 bloc-0.154
ambo-0.153
anooga-0.150
 Rove-0.148
Token who
Token ID508
Feature activation+6.50e-01

Pos logit contributions
rieg+0.489
 bloc+0.477
ambo+0.476
anooga+0.469
 Rove+0.462
Neg logit contributions
terday-0.396
 confir-0.379
pring-0.363
clair-0.362
cale-0.343
Token announced
Token ID3414
Feature activation+4.80e-01

Pos logit contributions
rieg+0.816
 bloc+0.804
ambo+0.794
 Rove+0.774
anooga+0.772
Neg logit contributions
terday-0.880
 confir-0.855
pring-0.832
clair-0.819
cale-0.791
Token his
Token ID465
Feature activation+4.95e-02

Pos logit contributions
rieg+0.577
 bloc+0.571
ambo+0.559
 Rove+0.551
anooga+0.539
Neg logit contributions
terday-0.674
 confir-0.656
pring-0.634
clair-0.633
cale-0.606
Token support
Token ID1104
Feature activation+1.03e-01

Pos logit contributions
rieg+0.069
 bloc+0.068
ambo+0.066
 Rove+0.065
anooga+0.065
Neg logit contributions
terday-0.062
 confir-0.059
clair-0.057
pring-0.056
cale-0.053
Token for
Token ID329
Feature activation+7.96e-01

Pos logit contributions
rieg+0.136
 bloc+0.134
ambo+0.132
anooga+0.130
 Rove+0.129
Neg logit contributions
terday-0.131
 confir-0.129
clair-0.123
pring-0.123
cale-0.116
Token the
Token ID262
Feature activation+2.19e-01

Pos logit contributions
rieg+0.893
 bloc+0.867
ambo+0.863
 Rove+0.842
anooga+0.835
Neg logit contributions
terday-1.200
 confir-1.154
pring-1.128
clair-1.122
cale-1.067
Token bill
Token ID2855
Feature activation+1.82e-01

Pos logit contributions
rieg+0.292
 bloc+0.285
ambo+0.282
anooga+0.276
 Rove+0.275
Neg logit contributions
terday-0.285
 confir-0.272
pring-0.265
clair-0.263
cale-0.249
Token Monday
Token ID3321
Feature activation-2.22e-01

Pos logit contributions
rieg+0.243
 bloc+0.236
ambo+0.235
anooga+0.230
 Rove+0.228
Neg logit contributions
terday-0.234
 confir-0.229
pring-0.220
clair-0.219
cale-0.208
Token,
Token ID11
Feature activation+4.62e-01

Pos logit contributions
terday+0.272
 confir+0.265
pring+0.254
clair+0.252
cale+0.240
Neg logit contributions
rieg-0.308
 bloc-0.301
ambo-0.301
anooga-0.294
 Rove-0.291
Token came
Token ID1625
Feature activation+1.48e+00

Pos logit contributions
rieg+0.639
 bloc+0.630
ambo+0.625
anooga+0.613
 Rove+0.609
Neg logit contributions
terday-0.571
 confir-0.546
pring-0.528
clair-0.524
cale-0.501
Token catching
Token ID16508
Feature activation+1.95e+00

Pos logit contributions
terday+0.225
 confir+0.220
pring+0.211
clair+0.210
cale+0.199
Neg logit contributions
rieg-0.201
 bloc-0.198
ambo-0.194
anooga-0.190
 Rove-0.189
Token up
Token ID510
Feature activation+9.78e-01

Pos logit contributions
rieg+2.008
 bloc+1.935
ambo+1.860
 Rove+1.824
anooga+1.785
Neg logit contributions
terday-3.138
 confir-3.049
clair-2.999
pring-2.954
cale-2.833
Token to
Token ID284
Feature activation-1.89e-02

Pos logit contributions
rieg+1.195
 bloc+1.160
ambo+1.145
anooga+1.124
 Rove+1.104
Neg logit contributions
terday-1.381
 confir-1.343
clair-1.296
pring-1.277
cale-1.214
Token an
Token ID281
Feature activation+1.15e+00

Pos logit contributions
terday+0.029
 confir+0.028
pring+0.027
clair+0.027
cale+0.026
Neg logit contributions
rieg-0.021
 bloc-0.020
ambo-0.020
anooga-0.020
 Rove-0.019
Token established
Token ID4920
Feature activation+5.72e-01

Pos logit contributions
rieg+1.520
 bloc+1.477
ambo+1.456
anooga+1.427
 Rove+1.418
Neg logit contributions
terday-1.491
 confir-1.458
pring-1.405
clair-1.384
cale-1.304
Token fact
Token ID1109
Feature activation-3.37e-03

Pos logit contributions
rieg+0.705
 bloc+0.694
ambo+0.672
anooga+0.662
 Rove+0.654
Neg logit contributions
terday-0.800
 confir-0.783
pring-0.749
clair-0.746
cale-0.706
Token on
Token ID319
Feature activation+2.12e-01

Pos logit contributions
terday+0.004
 confir+0.004
pring+0.004
clair+0.004
cale+0.004
Neg logit contributions
rieg-0.005
ambo-0.005
 bloc-0.005
anooga-0.005
 Rove-0.004
Token the
Token ID262
Feature activation-9.73e-02

Pos logit contributions
rieg+0.241
 bloc+0.235
ambo+0.233
anooga+0.228
 Rove+0.226
Neg logit contributions
terday-0.313
 confir-0.306
clair-0.294
pring-0.294
cale-0.279
Token ground
Token ID2323
Feature activation+1.74e+00

Pos logit contributions
terday+0.139
 confir+0.135
clair+0.130
pring+0.129
cale+0.123
Neg logit contributions
rieg-0.117
 bloc-0.114
ambo-0.112
anooga-0.111
 Rove-0.109
Token:
Token ID25
Feature activation-2.46e-01

Pos logit contributions
rieg+2.582
 bloc+2.524
ambo+2.482
anooga+2.440
 Rove+2.405
Neg logit contributions
terday-1.966
 confir-1.931
clair-1.810
pring-1.792
cale-1.688
Token Cities
Token ID20830
Feature activation+5.30e-01

Pos logit contributions
terday+0.359
 confir+0.347
pring+0.337
clair+0.334
cale+0.320
Neg logit contributions
rieg-0.289
ambo-0.279
 bloc-0.279
anooga-0.272
 Rove-0.268
Token[
Token ID58
Feature activation-2.66e-01

Pos logit contributions
rieg+1.078
ambo+1.044
 bloc+1.038
anooga+1.018
 Rove+1.011
Neg logit contributions
terday-1.165
 confir-1.144
clair-1.089
pring-1.086
cale-1.035
Tokennn
Token ID20471
Feature activation+3.73e-01

Pos logit contributions
terday+0.368
 confir+0.356
pring+0.342
clair+0.341
cale+0.326
Neg logit contributions
rieg-0.331
ambo-0.321
 bloc-0.318
anooga-0.313
 Rove-0.308
Token[
Token ID58
Feature activation-1.84e-01

Pos logit contributions
rieg+0.478
ambo+0.465
 bloc+0.459
anooga+0.453
 Rove+0.447
Neg logit contributions
terday-0.499
 confir-0.487
pring-0.464
clair-0.464
cale-0.440
TokenKeys
Token ID40729
Feature activation-1.67e+00

Pos logit contributions
terday+0.266
 confir+0.258
pring+0.248
clair+0.247
cale+0.237
Neg logit contributions
rieg-0.218
ambo-0.212
 bloc-0.209
anooga-0.206
 Rove-0.202
Token[
Token ID58
Feature activation-1.36e-02

Pos logit contributions
terday+2.194
 confir+2.123
pring+2.036
clair+2.028
cale+1.933
Neg logit contributions
rieg-2.209
ambo-2.144
 bloc-2.120
anooga-2.096
 Rove-2.059
Tokensearch
Token ID12947
Feature activation-5.15e-01

Pos logit contributions
terday+0.017
 confir+0.016
pring+0.016
clair+0.016
cale+0.015
Neg logit contributions
rieg-0.019
ambo-0.018
 bloc-0.018
anooga-0.018
 Rove-0.018
TokenSpace
Token ID14106
Feature activation+1.70e-02

Pos logit contributions
terday+0.546
 confir+0.523
pring+0.498
clair+0.495
cale+0.466
Neg logit contributions
rieg-0.809
ambo-0.789
 bloc-0.782
anooga-0.776
 Rove-0.763
Token][
Token ID7131
Feature activation+1.71e+00

Pos logit contributions
rieg+0.021
ambo+0.021
 bloc+0.021
anooga+0.020
 Rove+0.020
Neg logit contributions
terday-0.023
 confir-0.023
pring-0.022
clair-0.022
cale-0.021
Token[
Token ID58
Feature activation+2.49e-01

Pos logit contributions
rieg+2.131
ambo+2.076
 bloc+2.045
anooga+2.005
 Rove+1.974
Neg logit contributions
terday-2.333
 confir-2.293
clair-2.163
pring-2.158
cale-2.058
Tokeni
Token ID72
Feature activation+5.75e-01

Pos logit contributions
rieg+0.305
ambo+0.297
 bloc+0.293
anooga+0.288
 Rove+0.283
Neg logit contributions
terday-0.348
 confir-0.339
pring-0.323
clair-0.322
cale-0.307
Token]]
Token ID11907
Feature activation+3.44e+00

Pos logit contributions
rieg+0.662
ambo+0.643
 bloc+0.638
anooga+0.622
 Rove+0.610
Neg logit contributions
terday-0.843
 confir-0.824
pring-0.792
clair-0.791
cale-0.755
Token conferences
Token ID19993
Feature activation-5.87e-01

Pos logit contributions
terday+0.042
 confir+0.040
pring+0.039
clair+0.039
cale+0.037
Neg logit contributions
rieg-0.034
ambo-0.033
 bloc-0.033
anooga-0.033
 Rove-0.032
Token over
Token ID625
Feature activation+8.87e-01

Pos logit contributions
terday+0.750
 confir+0.729
clair+0.694
pring+0.693
cale+0.656
Neg logit contributions
rieg-0.793
ambo-0.772
 bloc-0.768
anooga-0.751
 Rove-0.747
Token a
Token ID257
Feature activation+5.39e-01

Pos logit contributions
rieg+0.996
 bloc+0.969
ambo+0.961
 Rove+0.939
anooga+0.933
Neg logit contributions
terday-1.327
 confir-1.281
pring-1.249
clair-1.237
cale-1.182
Token three
Token ID1115
Feature activation+1.56e+00

Pos logit contributions
rieg+0.653
 bloc+0.648
ambo+0.629
 Rove+0.619
anooga+0.616
Neg logit contributions
terday-0.767
 confir-0.731
clair-0.709
pring-0.706
cale-0.667
Token-
Token ID12
Feature activation-1.25e-01

Pos logit contributions
rieg+2.122
 bloc+2.092
ambo+2.046
anooga+2.037
 Rove+2.007
Neg logit contributions
terday-1.950
 confir-1.899
clair-1.811
pring-1.787
cale-1.687
Tokenyear
Token ID1941
Feature activation-2.87e+00

Pos logit contributions
terday+0.140
 confir+0.136
pring+0.127
clair+0.127
cale+0.119
Neg logit contributions
rieg-0.188
ambo-0.182
 bloc-0.182
anooga-0.180
 Rove-0.177
Token period
Token ID2278
Feature activation-6.26e-01

Pos logit contributions
terday+3.415
 confir+3.282
pring+3.157
clair+3.132
cale+2.990
Neg logit contributions
rieg-4.105
ambo-4.006
 bloc-3.936
anooga-3.929
 Rove-3.839
Token,
Token ID11
Feature activation-6.27e-01

Pos logit contributions
terday+0.796
 confir+0.771
clair+0.739
pring+0.737
cale+0.696
Neg logit contributions
rieg-0.845
 bloc-0.826
ambo-0.824
 Rove-0.802
anooga-0.796
Token travelling
Token ID16574
Feature activation+2.11e-01

Pos logit contributions
terday+0.848
 confir+0.815
pring+0.790
clair+0.785
cale+0.751
Neg logit contributions
rieg-0.801
ambo-0.780
 bloc-0.775
anooga-0.759
 Rove-0.752
Token to
Token ID284
Feature activation-5.94e-01

Pos logit contributions
rieg+0.284
 bloc+0.276
ambo+0.275
 Rove+0.265
anooga+0.265
Neg logit contributions
terday-0.270
 confir-0.264
clair-0.254
pring-0.253
cale-0.236
Token California
Token ID3442
Feature activation-9.88e-01

Pos logit contributions
terday+0.873
 confir+0.843
pring+0.820
clair+0.814
cale+0.779
Neg logit contributions
rieg-0.690
ambo-0.669
 bloc-0.667
anooga-0.650
 Rove-0.644
Token the
Token ID262
Feature activation-7.13e-01

Pos logit contributions
terday+0.067
 confir+0.065
pring+0.062
clair+0.062
cale+0.060
Neg logit contributions
rieg-0.065
ambo-0.063
 bloc-0.063
anooga-0.061
 Rove-0.061
Token camera
Token ID4676
Feature activation+2.43e+00

Pos logit contributions
terday+1.029
 confir+0.993
pring+0.962
clair+0.959
cale+0.919
Neg logit contributions
rieg-0.848
ambo-0.822
 bloc-0.814
anooga-0.802
 Rove-0.786
Token will
Token ID481
Feature activation-1.12e-01

Pos logit contributions
rieg+2.830
 bloc+2.786
ambo+2.756
 Rove+2.656
anooga+2.641
Neg logit contributions
terday-3.554
 confir-3.381
clair-3.288
pring-3.264
cale-3.144
Token pan
Token ID3425
Feature activation+1.89e+00

Pos logit contributions
terday+0.152
 confir+0.146
pring+0.140
clair+0.140
cale+0.134
Neg logit contributions
rieg-0.144
ambo-0.141
 bloc-0.140
 Rove-0.135
anooga-0.134
Token over
Token ID625
Feature activation+9.75e-01

Pos logit contributions
rieg+2.220
ambo+2.160
 bloc+2.127
 Rove+2.054
anooga+2.047
Neg logit contributions
terday-2.745
 confir-2.666
clair-2.554
pring-2.546
cale-2.432
Token or
Token ID393
Feature activation-4.68e-02

Pos logit contributions
rieg+1.198
ambo+1.165
 bloc+1.163
 Rove+1.136
anooga+1.119
Neg logit contributions
terday-1.352
 confir-1.305
clair-1.264
pring-1.249
cale-1.201
Token Lem
Token ID20607
Feature activation+2.20e-01

Pos logit contributions
terday+0.067
 confir+0.064
pring+0.062
clair+0.062
cale+0.059
Neg logit contributions
rieg-0.057
ambo-0.055
 bloc-0.055
anooga-0.053
 Rove-0.053
Tokenony
Token ID1647
Feature activation+1.18e-01

Pos logit contributions
rieg+0.211
ambo+0.204
 bloc+0.198
anooga+0.195
 Rove+0.190
Neg logit contributions
terday-0.368
 confir-0.360
pring-0.345
clair-0.345
cale-0.333
Token will
Token ID481
Feature activation+6.01e-01

Pos logit contributions
rieg+0.155
ambo+0.151
 bloc+0.150
anooga+0.146
 Rove+0.145
Neg logit contributions
terday-0.156
 confir-0.149
pring-0.144
clair-0.143
cale-0.137
Token walk
Token ID2513
Feature activation-2.79e-01

Pos logit contributions
rieg+0.767
 bloc+0.751
ambo+0.749
 Rove+0.715
anooga+0.708
Neg logit contributions
terday-0.818
 confir-0.777
clair-0.751
pring-0.748
cale-0.718
Token into
Token ID656
Feature activation+2.59e-01

Pos logit contributions
terday+0.415
 confir+0.402
clair+0.390
pring+0.388
cale+0.370
Neg logit contributions
rieg-0.319
ambo-0.309
 bloc-0.306
 Rove-0.296
anooga-0.296
Token the
Token ID262
Feature activation+1.60e-01

Pos logit contributions
terday+0.177
 confir+0.171
pring+0.164
clair+0.164
cale+0.156
Neg logit contributions
rieg-0.130
ambo-0.126
 bloc-0.126
anooga-0.122
 Rove-0.122
Token U
Token ID471
Feature activation-1.55e+00

Pos logit contributions
rieg+0.176
 bloc+0.172
ambo+0.169
anooga+0.165
 Rove+0.165
Neg logit contributions
terday-0.247
 confir-0.239
pring-0.230
clair-0.229
cale-0.218
Token.
Token ID13
Feature activation+6.33e-01

Pos logit contributions
terday+1.492
 confir+1.419
pring+1.347
clair+1.337
cale+1.252
Neg logit contributions
rieg-2.597
ambo-2.538
 bloc-2.516
anooga-2.498
 Rove-2.458
TokenN
Token ID45
Feature activation+3.04e-01

Pos logit contributions
rieg+0.888
 bloc+0.866
ambo+0.860
anooga+0.846
 Rove+0.832
Neg logit contributions
terday-0.781
 confir-0.747
pring-0.713
clair-0.712
cale-0.672
Token.
Token ID13
Feature activation+2.96e-01

Pos logit contributions
rieg+0.491
ambo+0.479
 bloc+0.476
anooga+0.472
 Rove+0.462
Neg logit contributions
terday-0.309
 confir-0.294
pring-0.280
clair-0.278
cale-0.260
Token Scientific
Token ID22060
Feature activation-1.56e+00

Pos logit contributions
rieg+0.333
 bloc+0.325
ambo+0.323
anooga+0.312
 Rove+0.305
Neg logit contributions
terday-0.447
 confir-0.430
pring-0.420
clair-0.415
cale-0.398
Token Committee
Token ID4606
Feature activation-1.05e+00

Pos logit contributions
terday+2.395
 confir+2.312
pring+2.247
clair+2.227
cale+2.143
Neg logit contributions
rieg-1.720
ambo-1.665
 bloc-1.651
anooga-1.629
 Rove-1.583
Token on
Token ID319
Feature activation+7.06e-01

Pos logit contributions
terday+1.437
 confir+1.384
pring+1.345
clair+1.335
cale+1.276
Neg logit contributions
rieg-1.318
ambo-1.277
 bloc-1.271
anooga-1.247
 Rove-1.225
Token the
Token ID262
Feature activation+3.34e-01

Pos logit contributions
rieg+0.810
ambo+0.796
 bloc+0.796
anooga+0.773
 Rove+0.769
Neg logit contributions
terday-1.036
 confir-1.006
pring-0.969
clair-0.961
cale-0.913
Token Effects
Token ID17417
Feature activation-2.46e+00

Pos logit contributions
rieg+0.415
 bloc+0.407
ambo+0.399
anooga+0.391
 Rove+0.391
Neg logit contributions
terday-0.466
 confir-0.448
pring-0.434
clair-0.433
cale-0.404
Token of
Token ID286
Feature activation-1.96e-01

Pos logit contributions
terday+2.690
 confir+2.596
pring+2.504
clair+2.462
cale+2.366
Neg logit contributions
rieg-3.711
ambo-3.621
 bloc-3.571
anooga-3.549
 Rove-3.484
Tokeneg
Token ID1533
Feature activation-6.77e-01

Pos logit contributions
rieg+0.234
ambo+0.229
 bloc+0.224
anooga+0.220
 Rove+0.216
Neg logit contributions
terday-0.248
 confir-0.241
pring-0.226
clair-0.223
cale-0.215
Tokenle
Token ID293
Feature activation-2.11e-01

Pos logit contributions
terday+0.907
 confir+0.875
pring+0.831
clair+0.825
cale+0.796
Neg logit contributions
rieg-0.886
ambo-0.860
 bloc-0.846
anooga-0.833
 Rove-0.817
Token,
Token ID11
Feature activation-3.94e-01

Pos logit contributions
terday+0.242
 confir+0.234
pring+0.220
clair+0.219
cale+0.209
Neg logit contributions
rieg-0.313
ambo-0.306
 bloc-0.303
anooga-0.297
 Rove-0.294
Token Colorado
Token ID7492
Feature activation-1.06e+00

Pos logit contributions
terday+0.573
 confir+0.553
clair+0.535
pring+0.534
cale+0.513
Neg logit contributions
rieg-0.463
ambo-0.450
 bloc-0.448
anooga-0.439
 Rove-0.430
Token Hemp
Token ID50060
Feature activation-1.14e-01

Pos logit contributions
terday+1.445
 confir+1.393
pring+1.342
clair+1.339
cale+1.280
Neg logit contributions
rieg-1.352
ambo-1.312
 bloc-1.301
anooga-1.284
 Rove-1.258
Token Company
Token ID5834
Feature activation-9.17e-01

Pos logit contributions
terday+0.163
 confir+0.158
pring+0.152
clair+0.151
cale+0.145
Neg logit contributions
rieg-0.136
ambo-0.132
 bloc-0.131
anooga-0.130
 Rove-0.126
Token.
Token ID13
Feature activation-5.47e-01

Pos logit contributions
terday+1.310
 confir+1.261
pring+1.220
clair+1.219
cale+1.167
Neg logit contributions
rieg-1.104
ambo-1.070
 bloc-1.066
anooga-1.046
 Rove-1.027
Token
Token ID564
Feature activation-1.11e+00

Pos logit contributions
terday+0.723
 confir+0.704
clair+0.670
pring+0.670
cale+0.639
Neg logit contributions
rieg-0.717
ambo-0.697
 bloc-0.690
anooga-0.680
 Rove-0.671
Token
Token ID250
Feature activation+7.75e-01

Pos logit contributions
terday+1.901
 confir+1.848
pring+1.797
clair+1.790
cale+1.729
Neg logit contributions
rieg-1.018
ambo-0.975
 bloc-0.960
anooga-0.947
 Rove-0.919
TokenThe
Token ID464
Feature activation-5.45e-01

Pos logit contributions
rieg+1.037
ambo+1.011
 bloc+0.994
anooga+0.984
 Rove+0.968
Neg logit contributions
terday-1.005
 confir-0.987
pring-0.923
clair-0.920
cale-0.873
Token timing
Token ID10576
Feature activation+2.04e-01

Pos logit contributions
terday+0.774
 confir+0.747
clair+0.722
pring+0.722
cale+0.686
Neg logit contributions
rieg-0.664
ambo-0.644
 bloc-0.642
anooga-0.628
 Rove-0.617
Tokens
Token ID82
Feature activation-2.35e+00

Pos logit contributions
terday+3.341
 confir+3.220
pring+3.109
clair+3.088
cale+2.952
Neg logit contributions
rieg-3.258
ambo-3.162
 bloc-3.129
anooga-3.103
 Rove-3.036
Token an
Token ID281
Feature activation+4.99e-01

Pos logit contributions
terday+3.203
 confir+3.092
pring+2.984
clair+2.969
cale+2.840
Neg logit contributions
rieg-2.972
ambo-2.881
 bloc-2.848
anooga-2.822
 Rove-2.761
Token ambitious
Token ID14742
Feature activation+2.40e-01

Pos logit contributions
rieg+0.637
ambo+0.621
 bloc+0.610
 Rove+0.587
anooga+0.585
Neg logit contributions
terday-0.679
 confir-0.651
pring-0.636
clair-0.628
cale-0.604
Token rock
Token ID3881
Feature activation+2.26e-01

Pos logit contributions
rieg+0.305
 bloc+0.298
ambo+0.295
anooga+0.284
 Rove+0.282
Neg logit contributions
terday-0.327
 confir-0.316
pring-0.307
clair-0.304
cale-0.289
Token op
Token ID1034
Feature activation-7.31e-01

Pos logit contributions
rieg+0.289
ambo+0.280
 bloc+0.280
anooga+0.272
 Rove+0.266
Neg logit contributions
terday-0.308
 confir-0.297
pring-0.287
clair-0.285
cale-0.272
Tokenus
Token ID385
Feature activation-3.56e+00

Pos logit contributions
terday+0.947
 confir+0.909
pring+0.878
clair+0.871
cale+0.832
Neg logit contributions
rieg-0.979
ambo-0.952
 bloc-0.942
anooga-0.930
 Rove-0.912
Token written
Token ID3194
Feature activation-3.08e+00

Pos logit contributions
terday+4.455
 confir+4.290
pring+4.140
clair+4.112
cale+3.920
Neg logit contributions
rieg-4.836
ambo-4.698
anooga-4.659
 bloc-4.638
 Rove-4.550
Token by
Token ID416
Feature activation+6.05e-02

Pos logit contributions
terday+4.077
 confir+3.919
pring+3.788
clair+3.761
cale+3.603
Neg logit contributions
rieg-4.004
ambo-3.885
 bloc-3.836
anooga-3.823
 Rove-3.741
Token and
Token ID290
Feature activation-5.10e-01

Pos logit contributions
rieg+0.071
ambo+0.068
 bloc+0.068
anooga+0.066
 Rove+0.065
Neg logit contributions
terday-0.089
 confir-0.086
pring-0.083
clair-0.083
cale-0.079
Token for
Token ID329
Feature activation+6.37e-01

Pos logit contributions
terday+0.661
 confir+0.633
pring+0.611
clair+0.607
cale+0.577
Neg logit contributions
rieg-0.684
ambo-0.666
 bloc-0.660
anooga-0.648
 Rove-0.638
Token a
Token ID257
Feature activation+8.16e-01

Pos logit contributions
rieg+0.718
ambo+0.697
 bloc+0.692
anooga+0.666
 Rove+0.664
Neg logit contributions
terday-0.958
 confir-0.930
pring-0.900
clair-0.893
cale-0.852
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
rieg+1.637
ambo+1.579
 bloc+1.576
anooga+1.539
 Rove+1.493
Neg logit contributions
terday-2.055
 confir-2.010
clair-1.895
pring-1.889
cale-1.835
Token Walton
Token ID34468
Feature activation-4.58e-01

Pos logit contributions
rieg+1.397
ambo+1.359
 bloc+1.345
anooga+1.324
 Rove+1.307
Neg logit contributions
terday-1.363
 confir-1.320
pring-1.260
clair-1.252
cale-1.195
Token was
Token ID373
Feature activation-4.47e-01

Pos logit contributions
terday+0.587
 confir+0.563
pring+0.542
clair+0.539
cale+0.515
Neg logit contributions
rieg-0.618
ambo-0.604
 bloc-0.599
anooga-0.589
 Rove-0.582
Token taken
Token ID2077
Feature activation-3.18e+00

Pos logit contributions
terday+0.607
 confir+0.582
clair+0.562
pring+0.562
cale+0.535
Neg logit contributions
rieg-0.569
ambo-0.554
 bloc-0.552
anooga-0.540
 Rove-0.536
Token into
Token ID656
Feature activation-1.61e+00

Pos logit contributions
terday+4.166
 confir+4.013
pring+3.870
clair+3.836
cale+3.668
Neg logit contributions
rieg-4.202
ambo-4.066
 bloc-4.010
anooga-3.997
 Rove-3.903
Token custody
Token ID10804
Feature activation-3.59e+00

Pos logit contributions
terday+1.747
 confir+1.663
pring+1.597
clair+1.580
cale+1.491
Neg logit contributions
rieg-2.492
ambo-2.432
 bloc-2.424
anooga-2.390
 Rove-2.360
Token based
Token ID1912
Feature activation-7.45e-02

Pos logit contributions
terday+4.580
 confir+4.372
pring+4.224
clair+4.186
cale+4.005
Neg logit contributions
rieg-4.872
ambo-4.727
anooga-4.661
 bloc-4.648
 Rove-4.528
Token upon
Token ID2402
Feature activation-1.06e+00

Pos logit contributions
terday+0.106
 confir+0.103
pring+0.099
clair+0.099
cale+0.095
Neg logit contributions
rieg-0.090
 bloc-0.087
ambo-0.087
anooga-0.084
 Rove-0.083
Token probable
Token ID17939
Feature activation-3.43e+00

Pos logit contributions
terday+1.476
 confir+1.423
pring+1.381
clair+1.374
cale+1.311
Neg logit contributions
rieg-1.318
ambo-1.277
 bloc-1.277
anooga-1.241
 Rove-1.238
Token cause
Token ID2728
Feature activation-2.73e+00

Pos logit contributions
terday+3.603
 confir+3.442
pring+3.290
clair+3.248
cale+3.076
Neg logit contributions
rieg-5.374
ambo-5.254
 bloc-5.169
anooga-5.159
 Rove-5.065
Token,
Token ID11
Feature activation-4.79e-01

Pos logit contributions
terday+3.195
 confir+3.056
pring+2.950
clair+2.928
cale+2.778
Neg logit contributions
rieg-3.995
ambo-3.881
 bloc-3.869
anooga-3.812
 Rove-3.759
Token is
Token ID318
Feature activation-4.06e-01

Pos logit contributions
terday+0.087
 confir+0.083
pring+0.081
clair+0.080
cale+0.077
Neg logit contributions
rieg-0.072
 bloc-0.070
ambo-0.070
anooga-0.068
 Rove-0.068
Token a
Token ID257
Feature activation-8.26e-01

Pos logit contributions
terday+0.573
 confir+0.553
pring+0.532
clair+0.531
cale+0.507
Neg logit contributions
rieg-0.496
ambo-0.481
 bloc-0.477
anooga-0.471
 Rove-0.464
Token series
Token ID2168
Feature activation-2.15e+00

Pos logit contributions
terday+1.189
 confir+1.148
pring+1.109
clair+1.107
cale+1.060
Neg logit contributions
rieg-0.987
ambo-0.953
 bloc-0.949
anooga-0.930
 Rove-0.916
Token about
Token ID546
Feature activation-8.22e-01

Pos logit contributions
terday+2.719
 confir+2.619
pring+2.523
clair+2.506
cale+2.391
Neg logit contributions
rieg-2.935
ambo-2.853
 bloc-2.819
anooga-2.798
 Rove-2.740
Token health
Token ID1535
Feature activation-3.06e+00

Pos logit contributions
terday+1.175
 confir+1.135
pring+1.097
clair+1.092
cale+1.045
Neg logit contributions
rieg-0.989
ambo-0.957
 bloc-0.951
anooga-0.934
 Rove-0.919
Token care
Token ID1337
Feature activation-3.32e+00

Pos logit contributions
terday+3.542
 confir+3.402
pring+3.262
clair+3.240
cale+3.072
Neg logit contributions
rieg-4.496
ambo-4.376
 bloc-4.326
anooga-4.293
 Rove-4.223
Token from
Token ID422
Feature activation-2.76e-01

Pos logit contributions
terday+4.194
 confir+4.049
pring+3.891
clair+3.866
cale+3.702
Neg logit contributions
rieg-4.498
ambo-4.365
 bloc-4.305
anooga-4.283
 Rove-4.194
Token a
Token ID257
Feature activation-6.69e-02

Pos logit contributions
terday+0.410
 confir+0.399
pring+0.383
clair+0.383
cale+0.365
Neg logit contributions
rieg-0.316
ambo-0.306
 bloc-0.304
anooga-0.298
 Rove-0.295
Token nurse
Token ID15849
Feature activation-3.38e+00

Pos logit contributions
terday+0.094
 confir+0.090
pring+0.087
clair+0.087
cale+0.083
Neg logit contributions
rieg-0.082
 bloc-0.080
ambo-0.080
anooga-0.078
 Rove-0.077
Token
Token ID447
Feature activation-7.38e-01

Pos logit contributions
terday+4.499
 confir+4.355
pring+4.218
clair+4.194
cale+4.003
Neg logit contributions
rieg-4.319
ambo-4.200
 bloc-4.126
anooga-4.112
 Rove-4.014
Token
Token ID247
Feature activation-2.68e+00

Pos logit contributions
terday+1.250
 confir+1.213
pring+1.177
clair+1.177
cale+1.137
Neg logit contributions
rieg-0.692
ambo-0.665
 bloc-0.654
anooga-0.648
 Rove-0.632
Tokenusal
Token ID6775
Feature activation-2.35e+00

Pos logit contributions
terday+2.884
 confir+2.789
pring+2.695
clair+2.673
cale+2.559
Neg logit contributions
rieg-2.724
ambo-2.639
 bloc-2.610
anooga-2.596
 Rove-2.534
Token rules
Token ID3173
Feature activation-1.42e+00

Pos logit contributions
terday+3.148
 confir+3.034
pring+2.941
clair+2.910
cale+2.778
Neg logit contributions
rieg-3.055
ambo-2.947
 bloc-2.945
anooga-2.892
 Rove-2.840
Token mean
Token ID1612
Feature activation-1.90e+00

Pos logit contributions
terday+1.767
 confir+1.702
pring+1.632
clair+1.631
cale+1.535
Neg logit contributions
rieg-1.978
ambo-1.929
 bloc-1.921
anooga-1.875
 Rove-1.857
Token judges
Token ID10266
Feature activation-1.21e+00

Pos logit contributions
terday+2.661
 confir+2.580
pring+2.484
clair+2.472
cale+2.376
Neg logit contributions
rieg-2.319
ambo-2.242
anooga-2.199
 bloc-2.197
 Rove-2.129
Token often
Token ID1690
Feature activation-3.71e-01

Pos logit contributions
terday+1.457
 confir+1.397
pring+1.337
clair+1.329
cale+1.256
Neg logit contributions
rieg-1.737
ambo-1.686
 bloc-1.679
anooga-1.652
 Rove-1.629
Token pres
Token ID906
Feature activation-5.43e+00

Pos logit contributions
terday+0.461
 confir+0.440
pring+0.427
clair+0.421
cale+0.397
Neg logit contributions
rieg-0.519
 bloc-0.507
ambo-0.502
 Rove-0.488
anooga-0.487
Tokenide
Token ID485
Feature activation-2.14e+00

Pos logit contributions
terday+6.771
pring+6.437
 confir+6.350
clair+6.286
cale+6.158
Neg logit contributions
rieg-7.152
anooga-7.084
ambo-6.886
 bloc-6.810
 Rove-6.697
Token over
Token ID625
Feature activation+6.90e-01

Pos logit contributions
terday+3.136
 confir+3.028
pring+2.935
clair+2.919
cale+2.804
Neg logit contributions
rieg-2.481
ambo-2.400
 bloc-2.363
anooga-2.346
 Rove-2.292
Token cases
Token ID2663
Feature activation-1.67e+00

Pos logit contributions
rieg+0.823
 bloc+0.809
ambo+0.800
 Rove+0.781
anooga+0.777
Neg logit contributions
terday-0.996
 confir-0.952
pring-0.922
clair-0.921
cale-0.871
Token involving
Token ID7411
Feature activation+9.16e-01

Pos logit contributions
terday+2.332
 confir+2.248
pring+2.166
clair+2.160
cale+2.062
Neg logit contributions
rieg-2.075
ambo-2.010
 bloc-1.997
anooga-1.965
 Rove-1.934
Token major
Token ID1688
Feature activation+2.51e+00

Pos logit contributions
rieg+1.040
 bloc+1.023
ambo+1.007
 Rove+0.989
anooga+0.974
Neg logit contributions
terday-1.374
 confir-1.322
clair-1.281
pring-1.276
cale-1.210
Token very
Token ID845
Feature activation-1.25e+00

Pos logit contributions
terday+0.541
 confir+0.522
pring+0.508
clair+0.505
cale+0.482
Neg logit contributions
rieg-0.423
 bloc-0.409
ambo-0.405
anooga-0.394
 Rove-0.393
Token small
Token ID1402
Feature activation-8.03e-01

Pos logit contributions
terday+1.797
 confir+1.735
pring+1.682
clair+1.677
cale+1.602
Neg logit contributions
rieg-1.487
 bloc-1.435
ambo-1.435
anooga-1.404
 Rove-1.383
Token.
Token ID13
Feature activation+4.09e-01

Pos logit contributions
terday+1.228
 confir+1.185
pring+1.151
clair+1.151
cale+1.097
Neg logit contributions
rieg-0.889
 bloc-0.861
ambo-0.860
anooga-0.832
 Rove-0.817
Token US
Token ID1294
Feature activation-2.01e+00

Pos logit contributions
rieg+0.508
ambo+0.494
 bloc+0.494
anooga+0.478
 Rove+0.474
Neg logit contributions
terday-0.566
 confir-0.541
pring-0.528
clair-0.525
cale-0.496
Token Naval
Token ID20818
Feature activation-2.83e-01

Pos logit contributions
terday+2.992
 confir+2.893
pring+2.805
clair+2.793
cale+2.677
Neg logit contributions
rieg-2.295
ambo-2.216
 bloc-2.193
anooga-2.160
 Rove-2.115
Token React
Token ID21492
Feature activation-3.31e+00

Pos logit contributions
terday+0.414
 confir+0.395
pring+0.385
clair+0.385
cale+0.364
Neg logit contributions
rieg-0.333
 bloc-0.324
ambo-0.322
 Rove-0.312
anooga-0.308
Tokenors
Token ID669
Feature activation-4.23e-01

Pos logit contributions
terday+2.773
 confir+2.606
pring+2.460
clair+2.432
cale+2.268
Neg logit contributions
rieg-5.899
ambo-5.784
 bloc-5.721
anooga-5.682
 Rove-5.617
Token
Token ID447
Feature activation-3.88e-02

Pos logit contributions
terday+0.555
 confir+0.532
clair+0.523
pring+0.517
cale+0.483
Neg logit contributions
rieg-0.550
 bloc-0.540
ambo-0.536
 Rove-0.519
anooga-0.518
Token
Token ID247
Feature activation-1.72e+00

Pos logit contributions
terday+0.065
 confir+0.063
clair+0.061
pring+0.061
cale+0.059
Neg logit contributions
rieg-0.037
ambo-0.036
 bloc-0.035
anooga-0.035
 Rove-0.034
Token average
Token ID2811
Feature activation-7.75e-01

Pos logit contributions
terday+2.224
 confir+2.127
pring+2.056
clair+2.054
cale+1.943
Neg logit contributions
rieg-2.328
ambo-2.258
 bloc-2.238
anooga-2.206
 Rove-2.170
Token annual
Token ID5079
Feature activation-1.47e+00

Pos logit contributions
terday+1.070
 confir+1.020
pring+0.997
clair+0.994
cale+0.938
Neg logit contributions
rieg-0.976
 bloc-0.948
ambo-0.943
anooga-0.914
 Rove-0.913