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

    Neuronpedia

    INDEX
    Explanations

    references to conditional or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .lu
    -0.19
    uckle
    -0.17
    828
    -0.15
     Jae
    -0.14
    duk
    -0.14
    éĻ£
    -0.14
    lu
    -0.14
     Turnbull
    -0.14
    apiro
    -0.14
    馬
    -0.13
    POSITIVE LOGITS
     Farr
    0.17
     Mori
    0.16
    ngr
    0.15
    оÑĢож
    0.15
    overrides
    0.15
    Configurer
    0.15
    nex
    0.14
    _firestore
    0.14
    unction
    0.14
    æĭ¼
    0.14
    Act Density 0.002%

    No Known Activations