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

    Neuronpedia

    INDEX
    Explanations

    dates represented in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly dates or significant numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.92
    orc
    -0.89
    ensed
    -0.79
    ovie
    -0.75
    odynamic
    -0.73
     regenerate
    -0.73
    mble
    -0.73
    etsk
    -0.72
    onite
    -0.72
    aired
    -0.71
    POSITIVE LOGITS
    06
    0.90
    76
    0.90
    08
    0.86
    05
    0.83
    rd
    0.82
    87
    0.82
    07
    0.80
    89
    0.80
    03
    0.80
    00
    0.79
    Act Density 0.034%

    No Known Activations