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

    Neuronpedia

    INDEX
    Explanations

    references to specific model names or designations in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aison
    -0.18
    idian
    -0.16
    dan
    -0.15
     peÅŁ
    -0.15
    inox
    -0.15
    oler
    -0.14
    Exit
    -0.14
    ongs
    -0.14
    roup
    -0.14
    大åħ¨
    -0.14
    POSITIVE LOGITS
    oop
    0.15
    mmc
    0.15
    opoulos
    0.14
    frey
    0.14
    Porn
    0.14
    ffer
    0.14
    urve
    0.13
    akespeare
    0.13
    isson
    0.13
    .sym
    0.13
    Act Density 0.034%

    No Known Activations