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

    Neuronpedia

    INDEX
    Explanations

    numbers that represent specific technological specifications or measurements, such as processor sizes or screen resolutions

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, specifically ones related to technology specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ync
    -0.70
    iple
    -0.69
    herer
    -0.69
    hower
    -0.67
    onen
    -0.66
    hiba
    -0.64
    owered
    -0.64
    ERSON
    -0.62
    herty
    -0.61
    utra
    -0.60
    POSITIVE LOGITS
    nd
    1.35
    rd
    1.25
    00
    1.04
    50
    0.79
    mph
    0.75
    nm
    0.73
    RD
    0.72
    009
    0.71
    ald
    0.70
    mpeg
    0.68
    Act Density 0.064%

    No Known Activations