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

    Neuronpedia

    INDEX
    Explanations

    references to physical height or tallness

    oai_token-act-pair · gpt-3.5-turbo

    references to height, specifically the word "tall."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GN
    -0.73
    erve
    -0.67
    ansk
    -0.67
    ogenesis
    -0.66
    igue
    -0.66
    EU
    -0.66
    ende
    -0.64
    ology
    -0.63
    ovie
    -0.63
    conom
    -0.63
    POSITIVE LOGITS
     tall
    3.69
     taller
    2.52
    tall
    2.48
     tallest
    2.43
     Tall
    1.68
     towering
    1.46
     height
    1.34
     thick
    1.25
     Height
    1.22
    Height
    1.22
    Act Density 0.023%

    No Known Activations