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

    Neuronpedia

    INDEX
    Explanations

    percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    percentage figures and their associated context in economic or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scarce
    -0.64
    ãĥ¤
    -0.64
     neighb
    -0.62
    lict
    -0.62
     lone
    -0.57
     larg
    -0.57
    byter
    -0.57
    pressed
    -0.56
    pton
    -0.56
    IRT
    -0.55
    POSITIVE LOGITS
    xual
    0.83
    uary
    0.79
     Decay
    0.78
     increments
    0.77
     ABV
    0.76
    rowth
    0.72
    factor
    0.71
     apiece
    0.70
    +.
    0.70
    elsius
    0.70
    Act Density 0.062%

    No Known Activations