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

    Neuronpedia

    INDEX
    Explanations

    references to various types and characteristics of glass and ceramics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sanitaires
    -0.82
     cauliflower
    -0.81
     démocr
    -0.80
     répon
    -0.77
     chré
    -0.76
     Soit
    -0.75
     circonst
    -0.75
    gomery
    -0.74
     joyeux
    -0.74
     häm
    -0.74
    POSITIVE LOGITS
     Glass
    1.79
     glass
    1.75
     GLASS
    1.74
    Glass
    1.70
    glass
    1.63
    GLASS
    1.52
     glas
    1.49
     Glas
    1.49
    Glas
    1.47
     glasses
    1.42
    Act Density 0.068%

    No Known Activations