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

    Neuronpedia

    INDEX
    Explanations

    quantities or statistics related to numerical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.77
    DeleteBehavior
    -0.75
    InitVars
    -0.72
     tartalomajánló
    -0.71
     resourceCulture
    -0.70
    AnchorTagHelper
    -0.69
    mtrl
    -0.69
    adaptiveStyles
    -0.68
     ویکی‌پدی
    -0.67
    Tembelea
    -0.66
    POSITIVE LOGITS
     nearly
    0.68
     
    0.56
    Nearly
    0.56
    ruptedException
    0.56
     yli
    0.55
     dozen
    0.55
     hundreds
    0.55
     seventy
    0.55
    bbene
    0.55
     thousands
    0.54
    Act Density 0.250%

    No Known Activations