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

    Neuronpedia

    INDEX
    Explanations

    placeholders or underscores, suggesting a focus on variable names or parameters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.84
    '>
    -0.83
     CreateTagHelper
    -0.75
    '},
    -0.65
    ResumeLayout
    -0.65
    ThroughAttribute
    -0.64
    )";
    -0.64
    '}>
    -0.64
    }>
    -0.63
     bezeichneter
    -0.62
    POSITIVE LOGITS
    GeoNames
    0.70
    </em>
    0.69
    cambrian
    0.68
    出版年
    0.66
    _
    0.66
    "
    0.65
     ‚
    0.64
     mijne
    0.63
     [_
    0.61
    adaptiveStyles
    0.61
    Act Density 0.179%

    No Known Activations