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

    Neuronpedia

    INDEX
    Explanations

    references to frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wrk
    -0.62
    ాయి
    -0.57
    AccessorTable
    -0.57
    setCursor
    -0.56
    Datuak
    -0.56
    urator
    -0.56
    lossus
    -0.55
     flotte
    -0.55
     EEU
    -0.55
     ý
    -0.54
    POSITIVE LOGITS
    Twice
    1.21
    twice
    1.18
     twice
    1.14
     Twice
    1.09
     thrice
    1.07
     TWICE
    1.02
     again
    0.91
     Repeated
    0.90
     repeatedly
    0.90
     repeated
    0.88
    Act Density 0.162%

    No Known Activations