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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "form" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emas
    -0.21
    pai
    -0.17
    grams
    -0.17
    vert
    -0.17
    era
    -0.17
    bane
    -0.16
     formally
    -0.16
     formal
    -0.16
    IAL
    -0.16
    qui
    -0.15
    POSITIVE LOGITS
    ulating
    0.35
    ulates
    0.32
    idable
    0.30
    ulary
    0.27
    ulate
    0.27
    ative
    0.26
    atted
    0.25
    atters
    0.25
    íĥľ
    0.25
    ulas
    0.24
    Act Density 0.075%

    No Known Activations