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

    Neuronpedia

    INDEX
    Explanations

    statistical values and measurements, such as numbers and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aband
    -0.67
    sth
    -0.60
    Tweet
    -0.57
     mah
    -0.56
    KING
    -0.56
    ="#
    -0.55
    ãĥĩãĤ£
    -0.55
    atl
    -0.53
    iji
    -0.53
    Letter
    -0.52
    POSITIVE LOGITS
     respectively
    1.87
     alike
    1.21
    depending
    1.03
     depending
    0.91
     respective
    0.83
    +.
    0.75
     combined
    0.69
     approaches
    0.67
    estic
    0.67
    SPONSORED
    0.65
    Act Density 0.303%

    No Known Activations