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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ash
    -0.17
    åĿª
    -0.15
    Ú¯ÙĦ
    -0.14
    ker
    -0.14
    ãģĻãģĻ
    -0.13
    YLE
    -0.13
    yle
    -0.13
    .Dispatcher
    -0.13
     Feinstein
    -0.13
    aub
    -0.13
    POSITIVE LOGITS
    frac
    0.46
     fraction
    0.38
     frac
    0.33
     ratio
    0.32
     Ratio
    0.31
     fractions
    0.31
     Fraction
    0.30
    fraction
    0.29
     Fra
    0.29
     ratios
    0.29
    Act Density 0.146%

    No Known Activations