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

    Neuronpedia

    INDEX
    Explanations

    negation phrases indicating reluctance or unwillingness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     not
    -0.17
    ruh
    -0.16
    agra
    -0.15
    oi
    -0.15
    kiye
    -0.15
    anel
    -0.14
     really
    -0.14
    292
    -0.14
    uela
    -0.14
    ylko
    -0.14
    POSITIVE LOGITS
    æħİ
    0.17
     Pornhub
    0.16
    achat
    0.15
    activex
    0.15
    ,readonly
    0.15
    maf
    0.14
    670
    0.14
    aller
    0.14
     bát
    0.14
    æĬľ
    0.14
    Act Density 0.075%

    No Known Activations