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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and numerical comparisons

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and numeric measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :,
    -0.62
    ():
    -0.58
    aryl
    -0.58
    rive
    -0.56
    anners
    -0.55
    ourning
    -0.54
     ('
    -0.54
     jo
    -0.54
    redd
    -0.53
     âĵĺ
    -0.53
    POSITIVE LOGITS
     compared
    0.79
    actly
    0.78
     equivalent
    0.75
     fraction
    0.69
    phabet
    0.66
     deviation
    0.66
     times
    0.66
     deviations
    0.65
     enough
    0.64
    %).
    0.64
    Act Density 0.247%

    No Known Activations