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

    Neuronpedia

    INDEX
    Explanations

    references to glass and glass-related materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    epam
    -0.76
     Huns
    -0.76
     häm
    -0.71
     Soit
    -0.71
     Whigs
    -0.70
    первых
    -0.68
    Monique
    -0.67
    ➹
    -0.67
     Cornelia
    -0.66
     Thrust
    -0.65
    POSITIVE LOGITS
     glass
    3.37
     Glass
    3.28
    glass
    3.15
    Glass
    3.13
     GLASS
    3.07
    GLASS
    2.72
     glas
    2.31
     glasses
    2.19
     Glas
    2.15
    glas
    2.09
    Act Density 0.052%

    No Known Activations