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

    Neuronpedia

    INDEX
    Explanations

    terms related to explaining complex subjects in an accessible manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieber
    -0.14
     Rug
    -0.14
    jez
    -0.14
    رÛĮ
    -0.13
    ooth
    -0.13
    ef
    -0.13
    alt
    -0.13
     Casting
    -0.13
    emen
    -0.13
     ragaz
    -0.13
    POSITIVE LOGITS
     complex
    0.62
    complex
    0.56
     complicated
    0.56
     complexity
    0.54
     Complex
    0.54
    Complex
    0.52
     Complexity
    0.49
     complexities
    0.48
    _complex
    0.47
     technical
    0.44
    Act Density 0.447%

    No Known Activations