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

    Neuronpedia

    INDEX
    Explanations

    key terms and identifiers commonly associated with academic or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lez
    -0.16
    fty
    -0.16
    VAS
    -0.15
     Canal
    -0.15
    ledon
    -0.15
     Moral
    -0.15
    .mu
    -0.15
     Punch
    -0.14
     Dud
    -0.14
     Fist
    -0.14
    POSITIVE LOGITS
    frauen
    0.16
    anted
    0.16
    ernet
    0.15
    anja
    0.14
    mant
    0.14
    pedia
    0.14
    Inspectable
    0.14
    _COPY
    0.14
    vat
    0.14
     manten
    0.14
    Act Density 0.002%

    No Known Activations