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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating age

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly those representing ages or other statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folk
    -0.70
    lie
    -0.62
    board
    -0.62
    rill
    -0.61
    hold
    -0.61
    lay
    -0.60
    ramid
    -0.59
    uyomi
    -0.59
    ezvous
    -0.58
    plement
    -0.57
    POSITIVE LOGITS
    %
    1.24
     percent
    1.19
    %-
    1.13
     mph
    1.12
    %:
    1.10
    %"
    1.08
    %,
    1.08
    %.
    1.06
    %;
    1.03
     cents
    0.98
    Act Density 0.123%

    No Known Activations