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

    Neuronpedia

    INDEX
    Explanations

    height and weight measurements of individuals

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to weights and heights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Instruments
    -0.72
     bott
    -0.66
     Leonardo
    -0.64
     Spiegel
    -0.63
     Dresden
    -0.63
    urtles
    -0.62
     Authors
    -0.61
     Directors
    -0.60
    better
    -0.59
     Chrys
    -0.59
    POSITIVE LOGITS
     pounds
    1.25
     lbs
    1.21
    lbs
    1.20
     yards
    1.17
    lb
    1.07
     pound
    1.05
     lb
    1.02
    pound
    0.95
     mph
    0.93
     watts
    0.86
    Act Density 0.076%

    No Known Activations