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

    Neuronpedia

    INDEX
    Explanations

    measurements of height or distance in different units

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    activation
    -0.69
    onement
    -0.67
     negativity
    -0.64
    ibal
    -0.59
    ritz
    -0.56
     redemption
    -0.55
    igil
    -0.54
    ifference
    -0.53
    timer
    -0.53
     Renew
    -0.53
    POSITIVE LOGITS
    ')
    0.99
    ').
    0.97
    %)
    0.95
    ")
    0.90
    '),
    0.88
    ").
    0.86
    %),
    0.84
    "),
    0.83
    %).
    0.82
     mi
    0.82
    Act Density 0.053%

    No Known Activations