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

    Neuronpedia

    INDEX
    Explanations

    statistical trends and relationships within data sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     non
    -0.50
     solo
    -0.45
    ↵↵
    -0.45
     
    -0.45
     السن
    -0.42
    ↵
    -0.39
    !
    -0.39
    unes
    -0.37
     highlights
    -0.37
    <eos>
    -0.37
    POSITIVE LOGITS
     '\\;'
    1.04
     MotionEvent
    0.96
     NSCoder
    0.93
     ModelExpression
    0.93
     propOrder
    0.91
     Roskov
    0.87
    IntoConstraints
    0.86
     numberOfRows
    0.85
     iprot
    0.83
     صوتيه
    0.82
    Act Density 0.862%

    No Known Activations