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

    Neuronpedia

    INDEX
    Explanations

    words related to measurements and physical attributes, specifically focusing on height

    oai_token-act-pair · gpt-3.5-turbo

    mentions of height

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.86
    tical
    -0.85
    plet
    -0.79
    zsche
    -0.76
    ournal
    -0.76
    BOOK
    -0.75
    vernment
    -0.75
    ãģ¦
    -0.73
    ctive
    -0.72
    pload
    -0.70
    POSITIVE LOGITS
     height
    1.00
     heights
    0.98
     stature
    0.86
     ceilings
    0.79
     altitude
    0.78
     tallest
    0.77
     indoors
    0.76
     elevation
    0.75
     cliffs
    0.74
    falls
    0.73
    Act Density 0.010%

    No Known Activations