Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the concept of "whole" or "entire" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bekasi
    -0.73
    iliano
    -0.73
     Shapiro
    -0.72
     Pittman
    -0.69
     Tapatalk
    -0.68
    例文帳に追加
    -0.68
     apricots
    -0.66
    StreetMap
    -0.65
     Aniston
    -0.65
    żeli
    -0.63
    POSITIVE LOGITS
    Whole
    1.80
    whole
    1.76
     whole
    1.76
     Whole
    1.75
     WHOLE
    1.63
     entire
    1.18
     whol
    1.13
     wholes
    1.12
     Ganze
    1.00
     ganzes
    0.99
    Act Density 0.039%

    No Known Activations