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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nam
    -0.15
    iap
    -0.15
    iero
    -0.14
     Carol
    -0.14
     Lug
    -0.14
     Durham
    -0.14
     dual
    -0.13
     Bloss
    -0.13
     Dual
    -0.13
     Conway
    -0.13
    POSITIVE LOGITS
    ullo
    0.15
     ÏĢÏģα
    0.15
     GANG
    0.14
    nem
    0.14
    ull
    0.14
    ucz
    0.14
     Affero
    0.14
     WithEvents
    0.14
    å·§
    0.14
    riel
    0.14
    Act Density 0.076%

    No Known Activations