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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or significance in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.11
     ModelExpression
    -0.93
     виправивши
    -0.88
     мәкал
    -0.85
     thingy
    -0.79
     שוליים
    -0.78
    جوايز
    -0.75
     חיצוניים
    -0.73
    tagHelperRunner
    -0.72
    principalColumn
    -0.72
    POSITIVE LOGITS
     fact
    0.71
     lack
    0.61
    ,
    0.60
     “
    0.59
     same
    0.59
     combination
    0.57
     is
    0.56
     result
    0.54
     success
    0.53
     combined
    0.52
    Act Density 0.294%

    No Known Activations