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

    Neuronpedia

    INDEX
    Explanations

    questions asking for specific values, including mathematical calculations and comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Púb
    -0.71
    CppMethod
    -0.71
     ModelExpression
    -0.67
     NSCoder
    -0.67
    HtmlAttribute
    -0.64
     Référence
    -0.63
     yourself
    -0.55
    resave
    -0.55
    :✨
    -0.55
     تانيه
    -0.55
    POSITIVE LOGITS
    +:+
    0.60
    GHIJKLM
    0.59
    mbic
    0.49
    "):
    0.48
    issus
    0.47
    hoeddwyd
    0.47
    ыгана
    0.46
    siasme
    0.46
    .")
    0.45
    ----</
    0.45
    Act Density 0.071%

    No Known Activations