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

    Neuronpedia

    INDEX
    Explanations

    height measurements, sometimes with comparisons like 'taller'

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of height

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.85
    tical
    -0.83
    ño
    -0.74
    ãģ¦
    -0.71
    ctive
    -0.70
    zsche
    -0.70
    uterte
    -0.70
    BOOK
    -0.69
    vernment
    -0.69
    ktop
    -0.69
    POSITIVE LOGITS
    falls
    0.84
     heights
    0.84
     height
    0.82
    fall
    0.81
    ened
    0.79
    ening
    0.78
    rises
    0.77
     stature
    0.76
     cliffs
    0.75
     altitude
    0.74
    Act Density 0.015%

    No Known Activations