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

    Neuronpedia

    INDEX
    Explanations

    inquiries regarding methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.69
    HtmlAttribute
    -0.67
     kasarigan
    -0.67
     himo
    -0.66
    Viited
    -0.66
    -0.65
    <bos>
    -0.65
    Personensuche
    -0.64
    IVEREF
    -0.63
    ViewFeatures
    -0.63
    POSITIVE LOGITS
     they
    1.26
     we
    1.11
     much
    1.05
     exactly
    1.02
     best
    0.95
     far
    0.91
     you
    0.86
     things
    0.85
     the
    0.79
     quickly
    0.77
    Act Density 0.070%

    No Known Activations