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

    Neuronpedia

    INDEX
    Explanations

    terms related to permission and consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aths
    -0.15
    ourg
    -0.15
    dap
    -0.14
    Äįe
    -0.14
    AIM
    -0.14
    alars
    -0.14
    ern
    -0.14
     vip
    -0.14
    ê¸ī
    -0.13
    urma
    -0.13
    POSITIVE LOGITS
    endoza
    0.17
    /lic
    0.16
    ance
    0.16
    /disable
    0.16
    454
    0.16
    /licenses
    0.16
    lessly
    0.15
    ACLE
    0.15
    _GRANTED
    0.14
    391
    0.14
    Act Density 0.023%

    No Known Activations