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

    Neuronpedia

    INDEX
    Explanations

    references to glass in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whigs
    -0.77
     Huns
    -0.74
     Soit
    -0.71
    RequestParam
    -0.70
     oreilles
    -0.68
     bacterium
    -0.68
     häm
    -0.68
     Coz
    -0.68
     cív
    -0.66
     Bacteriol
    -0.66
    POSITIVE LOGITS
     glass
    3.75
     Glass
    3.61
    glass
    3.47
    Glass
    3.44
     GLASS
    3.33
    GLASS
    2.93
     glas
    2.47
     Glas
    2.29
    玻璃
    2.20
    glas
    2.16
    Act Density 0.037%

    No Known Activations