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

    Neuronpedia

    INDEX
    Explanations

    keywords related to physical characteristics such as size, shape, length, and strength

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to dimensions and characteristics of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odcast
    -0.79
    anamo
    -0.73
    ndum
    -0.72
    ivan
    -0.71
    ievers
    -0.71
    idav
    -0.71
    inea
    -0.70
    roo
    -0.69
    Beck
    -0.69
    behind
    -0.69
    POSITIVE LOGITS
     thickness
    1.57
     size
    1.48
     complexity
    1.47
     severity
    1.46
     length
    1.44
     breadth
    1.43
     width
    1.43
     quantity
    1.43
     intensity
    1.40
     depth
    1.40
    Act Density 0.170%

    No Known Activations