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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by a percentage sign

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics or values related to percentage data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folk
    -0.77
    lie
    -0.70
    uyomi
    -0.70
    scape
    -0.70
    lay
    -0.69
    rill
    -0.68
    lied
    -0.66
    ramid
    -0.66
    lik
    -0.65
    hood
    -0.65
    POSITIVE LOGITS
    %
    1.12
     percent
    1.10
    %"
    1.03
     mph
    1.01
    %,
    1.00
    %-
    0.97
    %.
    0.97
    %:
    0.94
    %;
    0.94
    80
    0.91
    Act Density 0.119%

    No Known Activations