INDEX
Explanations
phrases indicating the impact or influence of corporations on the environment and society
New Auto-Interp
Negative Logits
anki
-0.18
aint
-0.15
ais
-0.15
Ïĩο
-0.15
illow
-0.15
Jad
-0.14
iner
-0.14
vana
-0.14
orz
-0.14
opia
-0.14
POSITIVE LOGITS
erap
0.19
raman
0.15
åĬŁ
0.15
RAP
0.15
eskort
0.15
пон
0.15
Īëĭ¤
0.14
lut
0.14
ÑĢап
0.14
à¥ĥत
0.14
Activations Density 0.163%