INDEX
Explanations
references to physical gestures or actions, particularly those involving raising hands
New Auto-Interp
Negative Logits
èį·
-0.15
esin
-0.15
ronic
-0.15
æ²¢
-0.15
lesi
-0.14
spokes
-0.14
room
-0.14
hound
-0.13
Substance
-0.13
ä½ĵ
-0.13
POSITIVE LOGITS
isté
0.15
fur
0.14
uled
0.14
ETHER
0.14
antom
0.14
_pcm
0.14
inç
0.14
æĬĢèĥ½
0.14
Hao
0.14
atori
0.14
Activations Density 0.070%