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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ark
    -0.17
    unya
    -0.15
    imple
    -0.15
    wan
    -0.14
    agn
    -0.14
     Ding
    -0.14
    inst
    -0.14
    째
    -0.14
    cate
    -0.14
    ombo
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĵ
    0.18
    pie
    0.17
    bic
    0.15
     subrange
    0.15
    disposing
    0.15
     VÅ¡
    0.14
     ÑĤÑı
    0.14
    еление
    0.14
     Levin
    0.14
     pie
    0.13
    Act Density 0.030%

    No Known Activations