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

    Neuronpedia

    INDEX
    Explanations

    keywords related to physical measurements, specifically focusing on height

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical height measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.94
    tical
    -0.89
    uterte
    -0.79
    BOOK
    -0.78
    ño
    -0.78
    zsche
    -0.72
    ãģ¦
    -0.72
    ournal
    -0.72
    vernment
    -0.70
    ctive
    -0.70
    POSITIVE LOGITS
     heights
    0.91
     height
    0.89
     stature
    0.80
     cliffs
    0.80
     elevation
    0.77
    falls
    0.74
     tallest
    0.74
     altitude
    0.74
     indoors
    0.74
     ceilings
    0.73
    Act Density 0.012%

    No Known Activations