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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation related to variable subscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -1.00
    OnTop
    -0.79
     Pape
    -0.78
    bayes
    -0.77
    onde
    -0.76
     Schultz
    -0.75
    findpost
    -0.73
    لينكات
    -0.72
    createNewFile
    -0.72
    rubin
    -0.71
    POSITIVE LOGITS
    _{\
    1.87
     }_{\
    1.47
     _{\
    1.46
    }_{\
    1.41
    )_{\
    1.37
    }}_{\
    1.29
    ]_{\
    1.13
    {{\
    1.12
    \|_{\
    1.01
     {\
    0.99
    Act Density 0.167%

    No Known Activations