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

    Neuronpedia

    INDEX
    Explanations

    numerical references to body measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ẠI
    -0.60
     EnglishChoose
    -0.58
    Ỉ
    -0.56
    posterous
    -0.56
    ometrica
    -0.56
    eryllium
    -0.56
    tiny
    -0.54
     runner
    -0.54
    WriteLiteral
    -0.54
    consulté
    -0.54
    POSITIVE LOGITS
     than
    1.76
    than
    1.28
     THAN
    1.19
    Than
    1.18
     niż
    1.06
     Than
    1.04
    THAN
    1.00
     clearer
    0.98
     hơn
    0.94
     firmer
    0.92
    Act Density 0.664%

    No Known Activations