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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "glass."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agricole
    -0.61
     honte
    -0.60
     nodule
    -0.60
     moly
    -0.60
     Whigs
    -0.60
     nodules
    -0.58
     cozin
    -0.58
     Gehen
    -0.57
     Cornelia
    -0.57
     Bertie
    -0.57
    POSITIVE LOGITS
     glass
    4.97
     Glass
    4.54
    glass
    4.49
    Glass
    4.42
     GLASS
    4.15
    GLASS
    3.58
     glas
    2.93
    玻璃
    2.78
     vidrio
    2.66
     Glas
    2.65
    Act Density 0.102%

    No Known Activations