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

    Neuronpedia

    INDEX
    Explanations

    references to systems, management, and organization within discussions of structure and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Escort
    -0.17
    uras
    -0.16
     Chaos
    -0.15
    ÑĢаниÑĨ
    -0.14
    urve
    -0.13
    ysi
    -0.13
    OTS
    -0.13
    Ïģει
    -0.13
     Escorts
    -0.13
    -rich
    -0.13
    POSITIVE LOGITS
    anje
    0.19
     Hüs
    0.15
    psz
    0.15
    üm
    0.15
    /cs
    0.15
    czy
    0.14
    neck
    0.14
    disposing
    0.14
    浦
    0.14
    stead
    0.14
    Act Density 0.056%

    No Known Activations