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

    Neuronpedia

    INDEX
    Explanations

    the word "may" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raya
    -0.15
    inia
    -0.15
    istrovstvÃŃ
    -0.15
    ariate
    -0.14
    ailer
    -0.14
    Ùģع
    -0.13
    undra
    -0.13
    ini
    -0.13
    iare
    -0.13
    ifer
    -0.13
    POSITIVE LOGITS
    hem
    0.18
    /all
    0.17
     saja
    0.17
    nard
    0.16
     be
    0.15
    ones
    0.15
    hap
    0.15
    haps
    0.14
    nown
    0.14
    weather
    0.14
    Act Density 0.087%

    No Known Activations