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

    Neuronpedia

    INDEX
    Explanations

    terms related to data privacy and account management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    зопас
    -0.61
    getahuan
    -0.60
    іга
    -0.60
     uſed
    -0.57
     ProtoMessage
    -0.57
    partiet
    -0.56
     lefs
    -0.55
    ificance
    -0.55
     ivelany
    -0.54
     Inscrivez
    -0.54
    POSITIVE LOGITS
    msgTypes
    0.66
     surla
    0.63
    basicConfig
    0.54
     autorytatywna
    0.54
    ution
    0.53
    ation
    0.53
    tainment
    0.52
    JECTION
    0.52
    ination
    0.52
     مشين
    0.49
    Act Density 1.444%

    No Known Activations