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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Once" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iostream
    -0.67
    Kami
    -0.65
     Kardashian
    -0.64
     meda
    -0.63
     Lombardo
    -0.63
    変わり
    -0.60
    FirebaseAuth
    -0.60
    ward
    -0.60
    llary
    -0.59
    Flynn
    -0.59
    POSITIVE LOGITS
     once
    2.03
     ONCE
    1.99
     Once
    1.96
    Once
    1.96
    once
    1.95
    ONCE
    1.87
     einmal
    1.02
    一旦
    0.98
     fois
    0.98
    一度
    0.95
    Act Density 0.051%

    No Known Activations