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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or indicators within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -1.27
     AssemblyCulture
    -1.17
    adaptiveStyles
    -1.11
    Przypisy
    -1.03
     nahilalakip
    -1.02
    ьаж
    -1.01
    skjaer
    -1.00
    AutoScaleMode
    -1.00
     disambiguazione
    -1.00
    phur
    -0.98
    POSITIVE LOGITS
    y
    1.60
    i
    1.59
    o
    1.52
    ه
    1.43
    e
    1.37
    a
    1.37
    er
    1.07
    an
    0.95
    u
    0.95
    ה
    0.90
    Act Density 1.677%

    No Known Activations