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

    Neuronpedia

    INDEX
    Explanations

    measurements, such as distances, weights, and lengths

    oai_token-act-pair · gpt-3.5-turbo

    measurements and units of distance, length, and weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bidden
    -0.80
    grade
    -0.73
    irie
    -0.72
    vale
    -0.72
    inous
    -0.72
    opic
    -0.69
    ellar
    -0.69
    ean
    -0.66
    tal
    -0.66
    raise
    -0.64
    POSITIVE LOGITS
    icka
    0.83
     increments
    0.76
     apiece
    0.76
     EDT
    0.73
     diameter
    0.68
    ²
    0.65
    UGE
    0.63
     separates
    0.62
     submerged
    0.62
    bsp
    0.60
    Act Density 0.052%

    No Known Activations