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

    Neuronpedia

    INDEX
    Explanations

    references to regulatory and policy-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾Ħ
    -0.15
    anders
    -0.15
    rox
    -0.14
    apyrus
    -0.14
    isky
    -0.14
    idine
    -0.13
    ascus
    -0.13
     ziy
    -0.13
     بÙĦغ
    -0.12
     Obrázky
    -0.12
    POSITIVE LOGITS
     by
    0.95
     oleh
    0.66
     By
    0.62
    _by
    0.56
     تÙĪسط
    0.56
    by
    0.53
    By
    0.52
    .by
    0.48
     bợi
    0.48
    -by
    0.44
    Act Density 0.316%

    No Known Activations