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

    Neuronpedia

    INDEX
    Explanations

    data formatted as bullet points

    oai_token-act-pair · gpt-3.5-turbo

    numerical information or specific measures related to processes or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wander
    -0.78
     Thornton
    -0.71
    ardless
    -0.69
    atis
    -0.66
     midway
    -0.66
    yan
    -0.66
     neighb
    -0.65
    sburgh
    -0.65
    cules
    -0.65
    ury
    -0.64
    POSITIVE LOGITS
    âĹı
    1.10
    âĸł
    0.97
    âľ
    0.85
    ·
    0.84
    âĺħ
    0.84
    âĢ¢
    0.82
    ðĿ
    0.80
    ³³³
    0.80
    ³³³³³³³³
    0.78
    ³³³³
    0.76
    Act Density 0.090%

    No Known Activations