INDEX
Explanations
references to people and their influence or impact within various contexts
New Auto-Interp
Negative Logits
done
-0.17
Done
-0.17
done
-0.17
doing
-0.15
again
-0.15
-done
-0.15
Doing
-0.15
done
-0.14
astes
-0.14
Hayward
-0.14
POSITIVE LOGITS
so
0.20
æīĢ
0.19
poss
0.17
minate
0.17
æīĢ
0.17
bring
0.16
proport
0.16
ark
0.16
esp
0.15
eng
0.15
Activations Density 0.274%