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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kardashian
    -0.75
    GenerationType
    -0.71
    llary
    -0.70
    marle
    -0.69
     Кі
    -0.69
     Tatar
    -0.66
    írit
    -0.66
     Kitts
    -0.65
     Lombardo
    -0.65
    /**
    -0.64
    POSITIVE LOGITS
     ONCE
    1.35
     Once
    1.26
     once
    1.25
    Once
    1.20
    once
    1.18
    ONCE
    1.16
    eens
    0.77
     fois
    0.77
    forName
    0.77
    thoughts
    0.77
    Act Density 0.031%

    No Known Activations