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

    Neuronpedia

    INDEX
    Explanations

    statistical data values, such as numbers related to distances, sizes, speeds, and quantities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    estine
    -0.73
    bara
    -0.73
    essen
    -0.72
    hran
    -0.68
    warts
    -0.68
    nam
    -0.66
    iqu
    -0.65
    lying
    -0.64
    robe
    -0.63
    ufact
    -0.62
    POSITIVE LOGITS
     ILCS
    1.15
     MHz
    1.14
    MHz
    1.14
    px
    1.06
     lbs
    1.06
    mAh
    1.04
    lbs
    1.03
     pounds
    1.00
     calories
    0.98
    bps
    0.96
    Act Density 0.846%

    No Known Activations