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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ontrol
    -0.17
    esome
    -0.16
     Dio
    -0.16
    asant
    -0.15
    ype
    -0.15
    ãģŁãģĹ
    -0.14
    eneg
    -0.14
    ewise
    -0.14
    .Locale
    -0.14
    hape
    -0.14
    POSITIVE LOGITS
    gate
    0.17
    887
    0.15
    ost
    0.14
     proto
    0.14
    achu
    0.14
    iac
    0.13
    797
    0.13
    oir
    0.13
     till
    0.13
    otros
    0.13
    Act Density 0.038%

    No Known Activations