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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "two" and related quantifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.09
     houſe
    -1.07
     fubject
    -1.04
     Majefty
    -0.98
     Grecs
    -0.98
     Jefus
    -0.98
     ſche
    -0.95
     himſelf
    -0.95
     Eſ
    -0.93
     ſtate
    -0.93
    POSITIVE LOGITS
     two
    1.24
     Two
    1.02
     TWO
    0.91
    TWO
    0.90
    Two
    0.87
     deux
    0.86
    two
    0.86
     zwei
    0.81
    两
    0.81
     två
    0.80
    Act Density 0.234%

    No Known Activations