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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "two."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RSSSF
    -0.75
    googleapis
    -0.75
    ItemBackground
    -0.73
    uresti
    -0.70
     Pathol
    -0.67
     للمعارف
    -0.66
    ly
    -0.65
    Belgique
    -0.65
     vaisselle
    -0.65
    ñores
    -0.64
    POSITIVE LOGITS
     two
    2.44
    two
    2.19
     Two
    2.11
    Two
    2.03
     TWO
    2.01
    TWO
    1.92
     deux
    1.84
     zwei
    1.76
     three
    1.64
     två
    1.59
    Act Density 0.141%

    No Known Activations