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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.73
    EndGlobalSection
    -0.72
    DeleteBehavior
    -0.61
     توسط
    -0.56
     kepada
    -0.56
     conformément
    -0.53
     zodat
    -0.52
     voidaan
    -0.52
    lapsingToolbar
    -0.50
    ilerini
    -0.50
    POSITIVE LOGITS
    来说
    0.98
    而言
    0.94
    來說
    0.92
     it
    0.90
     это
    0.82
     NSCoder
    0.74
     isso
    0.68
    来讲
    0.67
     đây
    0.65
     this
    0.64
    Act Density 0.265%

    No Known Activations