INDEX
Explanations
references to memes and their cultural impact
New Auto-Interp
Head Attr Weights
0:0.15
1:0.04
2:0.04
3:0.02
4:0.30
5:0.11
6:0.05
7:0.05
8:0.04
9:0.02
10:0.11
11:0.04
Negative Logits
�
-1.52
�
-1.49
龍�
-1.46
�
-1.46
�
-1.45
作
-1.45
schild
-1.45
サーティワン
-1.44
habitable
-1.43
enario
-1.36
POSITIVE LOGITS
retweet
1.59
irony
1.45
ironic
1.43
achev
1.43
Pastebin
1.39
hysterical
1.36
Screenshot
1.35
tho
1.35
sic
1.34
urned
1.33
Activations Density 0.555%