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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "form."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emas
    -0.19
     formula
    -0.18
    ernes
    -0.17
     formally
    -0.17
    bane
    -0.17
     formal
    -0.16
    grams
    -0.16
    esis
    -0.16
    á»Ĩ
    -0.16
    _fmt
    -0.15
    POSITIVE LOGITS
    ulating
    0.37
    ulates
    0.31
    ulary
    0.30
    idable
    0.30
    ative
    0.29
    ulate
    0.27
    atters
    0.26
    ality
    0.25
    ulated
    0.25
    atted
    0.25
    Act Density 0.092%

    No Known Activations