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

    Neuronpedia

    INDEX
    Explanations

    references to approval, guidance, and support in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovic
    -0.17
    mq
    -0.16
    onden
    -0.15
    ingle
    -0.15
    ião
    -0.14
    _firestore
    -0.14
    ond
    -0.14
    cratch
    -0.14
    gün
    -0.14
    ipar
    -0.14
    POSITIVE LOGITS
    immel
    0.16
    325
    0.15
    .defer
    0.14
    _EXPECT
    0.14
    keley
    0.14
    oped
    0.14
    defer
    0.14
    ker
    0.14
     Evel
    0.13
    aker
    0.13
    Act Density 0.083%

    No Known Activations