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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data points and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gets
    -0.77
    giving
    -0.73
    holders
    -0.71
    bub
    -0.71
    tub
    -0.69
    shots
    -0.67
    seeing
    -0.67
    iky
    -0.67
     nationalists
    -0.66
    stract
    -0.65
    POSITIVE LOGITS
    90
    0.92
    65
    0.90
    97
    0.88
    80
    0.86
    999
    0.86
    95
    0.84
    96
    0.83
    98
    0.82
    99
    0.82
    765
    0.81
    Act Density 0.023%

    No Known Activations