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

    Neuronpedia

    INDEX
    Explanations

    the number 20

    oai_token-act-pair · gpt-4-turbo

    numbers related to years

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 20 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plom
    -0.85
    kell
    -0.81
    hammad
    -0.76
    afort
    -0.70
    quet
    -0.70
    hei
    -0.69
    pload
    -0.69
    ablo
    -0.69
    osal
    -0.68
    ochet
    -0.68
    POSITIVE LOGITS
    âĸĪâĸĪ
    0.93
    %"
    0.90
    SW
    0.81
    80
    0.79
    th
    0.77
    mA
    0.76
    40
    0.76
    committee
    0.75
    poon
    0.75
    81
    0.72
    Act Density 0.038%

    No Known Activations