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

    Neuronpedia

    INDEX
    Explanations

    words related to beams, both concrete like "beam of light" and abstract like "beams of radiation"

    oai_token-act-pair · gpt-3.5-turbo

    references to beams of light or energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DIT
    -0.74
    ADRA
    -0.73
    é»Ĵ
    -0.72
    phis
    -0.72
    afort
    -0.72
    ascular
    -0.71
    hiro
    -0.70
     Claus
    -0.68
     AVG
    -0.66
    sie
    -0.66
    POSITIVE LOGITS
     beams
    0.94
     beam
    0.85
    glass
    0.83
    beam
    0.79
     ray
    0.78
    casters
    0.76
     rays
    0.76
    plane
    0.75
    liner
    0.75
     physicists
    0.74
    Act Density 0.023%

    No Known Activations