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

    Neuronpedia

    INDEX
    Explanations

    references to weights or sizes expressed in pounds

    oai_token-act-pair · gpt-3.5-turbo

    references to weight measured in pounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     background
    -0.75
     passage
    -0.74
     Yu
    -0.71
     util
    -0.69
     eas
    -0.67
     rec
    -0.67
     sol
    -0.66
     civilisation
    -0.66
     Ved
    -0.64
     harmony
    -0.64
    POSITIVE LOGITS
    pound
    3.92
    lb
    1.82
    lbs
    1.64
     pounds
    1.63
     Pound
    1.48
     pound
    1.48
     lbs
    1.34
    weight
    1.21
    mile
    1.21
    dollar
    1.18
    Act Density 0.012%

    No Known Activations