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

    Neuronpedia

    INDEX
    Explanations

    requirements and constraints in policy documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rips
    -0.16
    untime
    -0.15
    celik
    -0.14
     Pri
    -0.14
    istr
    -0.14
    quir
    -0.13
    rou
    -0.13
    uti
    -0.13
     gone
    -0.13
    ripe
    -0.13
    POSITIVE LOGITS
    .Throw
    0.15
    tÃŃ
    0.14
    ictim
    0.14
    indre
    0.14
    ukkan
    0.14
    edn
    0.14
    äºŃ
    0.14
    koa
    0.14
     bá»Ļ
    0.14
    CHANT
    0.13
    Act Density 0.026%

    No Known Activations