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

    Neuronpedia

    INDEX
    Explanations

    dialogue and direct quotes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ruhm
    -0.60
    SharedDtor
    -0.58
     populer
    -0.56
     Decken
    -0.56
    drawiam
    -0.55
    voici
    -0.55
    wyd
    -0.55
     aanbod
    -0.54
     виправивши
    -0.54
    Tembelea
    -0.53
    POSITIVE LOGITS
    Diwedd
    0.61
     teammates
    0.57
    oprecip
    0.56
     deflected
    0.56
    QMetaType
    0.55
    mmate
    0.54
     superstitious
    0.54
     propOrder
    0.54
     lof
    0.53
     NUKAT
    0.53
    Act Density 0.110%

    No Known Activations