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
    /**
    -0.73
     Kitts
    -0.72
     Marbella
    -0.71
    apunov
    -0.69
    GenerationType
    -0.68
     Kardashian
    -0.67
    amiya
    -0.67
    marle
    -0.66
     Cagliari
    -0.63
     Tatar
    -0.62
    POSITIVE LOGITS
     ONCE
    1.27
     Once
    1.27
     once
    1.20
    Once
    1.20
    once
    1.13
    ONCE
    1.08
    thoughts
    0.79
     Upon
    0.77
     UPON
    0.76
     Jos
    0.74
    Act Density 0.036%

    No Known Activations