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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "many."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anela
    -0.17
    ainers
    -0.16
    age
    -0.16
    sts
    -0.15
     various
    -0.15
     svob
    -0.15
    emmel
    -0.14
    istrovstvÃŃ
    -0.14
    chers
    -0.14
    OF
    -0.14
    POSITIVE LOGITS
    -times
    0.18
    /all
    0.17
     of
    0.17
    ison
    0.16
    ones
    0.16
    -sided
    0.16
    ISON
    0.15
     parts
    0.14
    /m
    0.14
    parts
    0.14
    Act Density 0.047%

    No Known Activations