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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities that are being quoted or cited

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gone
    -0.16
    angu
    -0.15
    andom
    -0.15
    orrent
    -0.14
    acco
    -0.14
    aur
    -0.14
     cis
    -0.14
    chw
    -0.14
    à¤ķरण
    -0.14
    ideshow
    -0.14
    POSITIVE LOGITS
    dden
    0.17
    گار
    0.17
    elts
    0.16
    yonel
    0.15
    quist
    0.13
    ikan
    0.13
     Pub
    0.13
     excess
    0.13
    ellan
    0.13
    _constant
    0.13
    Act Density 0.013%

    No Known Activations