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

    Neuronpedia

    INDEX
    Explanations

    function definitions and variables in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.72
     kiện
    -0.65
     sos
    -0.62
     “
    -0.61
    s
    -0.61
     ce
    -0.60
    bij
    -0.57
     CommonModule
    -0.57
    =“
    -0.56
    :“
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    0.84
     Meters
    0.83
     commerciali
    0.83
     lambs
    0.83
    脚注の使い方
    0.82
    ScopeManager
    0.79
     myſelf
    0.78
     Shaksp
    0.77
     дописавши
    0.77
    Bronnen
    0.74
    Act Density 0.145%

    No Known Activations