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

    Neuronpedia

    INDEX
    Explanations

    references to formal publications and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oulder
    -0.17
    zdy
    -0.16
    etri
    -0.16
    ÑĪÑĮ
    -0.14
    ä¹ł
    -0.14
    quipment
    -0.14
    038
    -0.14
    ะ
    -0.14
    Ð¡Ð¡Ðł
    -0.14
    rette
    -0.14
    POSITIVE LOGITS
     Academy
    0.17
     Royal
    0.17
    clair
    0.16
     sym
    0.15
     filter
    0.15
    sym
    0.15
     workshop
    0.14
    cl
    0.14
    Sym
    0.14
     workshops
    0.14
    Act Density 0.022%

    No Known Activations