INDEX
Explanations
references to societal or historical controversies and discussions
New Auto-Interp
Negative Logits
ibName
-0.15
oter
-0.15
psz
-0.15
šen
-0.14
ipeg
-0.13
alytics
-0.13
Swinger
-0.13
iskey
-0.13
'gc
-0.13
indicator
-0.13
POSITIVE LOGITS
drawing
0.38
drew
0.37
receives
0.35
receive
0.33
draws
0.33
å¼ķ
0.33
attracts
0.33
draw
0.32
drawing
0.32
received
0.32
Activations Density 0.475%