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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical attributes like height and weight

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to height and weight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.75
    oÄŁ
    -0.72
    sth
    -0.71
    heit
    -0.67
     Trials
    -0.67
    acci
    -0.66
    ularity
    -0.66
     Warn
    -0.66
    consumer
    -0.66
    quest
    -0.65
    POSITIVE LOGITS
     tall
    0.84
     lumber
    0.80
     humanoid
    0.73
     blonde
    0.73
     towering
    0.73
     floppy
    0.72
     taller
    0.72
     blond
    0.71
     skinny
    0.70
     shoulders
    0.70
    Act Density 0.066%

    No Known Activations