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

    Neuronpedia

    INDEX
    Explanations

    questions beginning with "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Willis
    -0.15
    auc
    -0.15
    abr
    -0.15
    orch
    -0.15
    uida
    -0.14
    ermen
    -0.14
    olar
    -0.14
    oad
    -0.14
    ennen
    -0.14
     orth
    -0.14
    POSITIVE LOGITS
     Ras
    0.15
    اÙĤÙĦ
    0.15
    Å¡et
    0.14
    AFX
    0.14
    uç
    0.14
    poser
    0.14
    phet
    0.14
    /Runtime
    0.13
    igit
    0.13
     pied
    0.13
    Act Density 0.011%

    No Known Activations