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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "any" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pis
    -0.19
    ped
    -0.19
    ikon
    -0.17
    yll
    -0.17
    pie
    -0.16
    nicas
    -0.15
    zens
    -0.15
    po
    -0.14
    iff
    -0.14
    uran
    -0.14
    POSITIVE LOGITS
    onymous
    0.17
    ways
    0.16
    olds
    0.16
    ëĭ¹
    0.16
    sson
    0.16
    quist
    0.15
    ullo
    0.15
    onya
    0.15
    ould
    0.14
    ãĥ³ãĤ¬
    0.14
    Act Density 0.043%

    No Known Activations