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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical values related to measurements or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Merit
    -0.80
    Attributes
    -0.76
    Reviewer
    -0.73
    kefeller
    -0.71
    GROUP
    -0.71
    ITED
    -0.69
    æ³
    -0.68
    LAN
    -0.67
    PORT
    -0.67
    imir
    -0.66
    POSITIVE LOGITS
    imet
    1.32
    imeter
    1.05
    oning
    0.83
    uation
    0.79
    enary
    0.75
    rate
    0.74
    rated
    0.73
    urance
    0.73
    uary
    0.72
    elsen
    0.71
    Act Density 0.024%

    No Known Activations