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

    Neuronpedia

    INDEX
    Explanations

    colons or punctuation that introduces lists or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imations
    -0.17
    гаÑĢ
    -0.15
     ban
    -0.14
    ascar
    -0.14
     zd
    -0.14
    .baidu
    -0.13
     ha
    -0.13
    cascade
    -0.13
    ivant
    -0.13
    Äįka
    -0.13
    POSITIVE LOGITS
    ipers
    0.14
     how
    0.14
    TM
    0.14
    iger
    0.14
    angu
    0.14
    ysize
    0.14
    ynos
    0.14
    ding
    0.14
    tm
    0.13
    gres
    0.13
    Act Density 0.054%

    No Known Activations