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

    Neuronpedia

    INDEX
    Explanations

    the number "three" occurring frequently

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "three."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IAS
    -0.68
    UGE
    -0.63
    isky
    -0.62
    utable
    -0.61
    gain
    -0.61
    Hub
    -0.58
    agate
    -0.57
    buffer
    -0.56
    ULE
    -0.56
    fore
    -0.56
    POSITIVE LOGITS
    teenth
    1.22
    rd
    1.14
    teen
    1.12
     hundred
    1.02
    peat
    1.01
     quarters
    0.99
     consecutive
    0.96
    uously
    0.94
     successive
    0.94
     dimensional
    0.93
    Act Density 0.094%

    No Known Activations