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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehir
    -0.16
    Ñĩ
    -0.16
    iosis
    -0.14
     Beaut
    -0.14
    ÑĸнÑĮ
    -0.13
    ird
    -0.13
    ai
    -0.13
    漫
    -0.13
    .Gradient
    -0.13
    irst
    -0.13
    POSITIVE LOGITS
    bau
    0.14
    aken
    0.14
    erg
    0.13
    ernals
    0.13
    apia
    0.13
    porte
    0.13
     Hond
    0.13
    -play
    0.13
    ever
    0.13
     Merr
    0.13
    Act Density 0.068%

    No Known Activations