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

    Neuronpedia

    INDEX
    Explanations

    references to specific clothing items related to the lower body

    oai_token-act-pair · gpt-3.5-turbo

    references to clothing items, specifically skirts, and geographical features like valleys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nost
    -0.92
    ewitness
    -0.77
     Bahá
    -0.76
    ongh
    -0.73
     Luther
    -0.72
     WOR
    -0.72
    ALD
    -0.70
     exorc
    -0.70
    ilingual
    -0.69
     Orioles
    -0.69
    POSITIVE LOGITS
     skirt
    2.64
     skirts
    2.52
     slope
    1.83
     valley
    1.70
     flank
    1.62
     slopes
    1.44
     valleys
    1.40
     gradient
    1.31
     cascade
    1.17
    skirts
    1.16
    Act Density 0.060%

    No Known Activations