INDEX
Explanations
words related to time endings like "weekend" and "end."
instances of the word "END" in various contexts
New Auto-Interp
Negative Logits
hill
-0.63
Britann
-0.62
gau
-0.60
incub
-0.59
Irish
-0.56
stubborn
-0.56
Su
-0.56
popul
-0.55
playbook
-0.54
hard
-0.54
POSITIVE LOGITS
END
4.30
ENDED
2.35
enders
1.88
ends
1.87
ending
1.78
end
1.76
ender
1.75
END
1.64
ENT
1.56
ENC
1.53
Activations Density 0.017%