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

    Neuronpedia

    INDEX
    Explanations

    words related to physical attributes, specifically focusing on the concept of height

    oai_token-act-pair · gpt-3.5-turbo

    references to height

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.91
    eer
    -0.85
    vernment
    -0.78
    IRO
    -0.77
    eln
    -0.77
    ruption
    -0.72
    ktop
    -0.72
    trak
    -0.72
     Reloaded
    -0.72
    eers
    -0.72
    POSITIVE LOGITS
     taller
    1.03
     stature
    1.01
     tallest
    0.98
     tall
    0.92
    ness
    0.88
     enough
    0.86
    nesses
    0.82
    ened
    0.81
    tall
    0.79
     weeds
    0.79
    Act Density 0.010%

    No Known Activations