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

    Neuronpedia

    INDEX
    Explanations

    numerical data in a specified format, like dates and corresponding values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 27 and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beir
    -0.84
    urated
    -0.80
    achus
    -0.77
    aleb
    -0.74
    ensed
    -0.72
    ovie
    -0.67
    mble
    -0.66
    ifully
    -0.66
    omatic
    -0.66
    anamo
    -0.65
    POSITIVE LOGITS
    00
    1.14
    th
    0.95
    rd
    0.91
    017
    0.82
    87
    0.79
    66
    0.76
    06
    0.76
    MIN
    0.76
    88
    0.75
    71
    0.75
    Act Density 0.031%

    No Known Activations