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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once" and its variations as transition markers or indicators of a narrative change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llary
    -0.74
     Kardashian
    -0.69
    GenerationType
    -0.67
    /**
    -0.67
     Marbella
    -0.66
     Cordoba
    -0.63
     Sweater
    -0.62
    soort
    -0.62
     Córdoba
    -0.62
    Kami
    -0.62
    POSITIVE LOGITS
     ONCE
    1.35
     Once
    1.32
     once
    1.29
    Once
    1.26
    once
    1.20
    ONCE
    1.15
     Upon
    0.80
     Jos
    0.79
     UPON
    0.77
     upon
    0.75
    Act Density 0.055%

    No Known Activations