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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    n
    -0.91
    a
    -0.85
    o
    -0.83
     “
    -0.79
    2
    -0.78
    1
    -0.77
    al
    -0.77
    4
    -0.76
     "
    -0.76
     ”
    -0.74
    POSITIVE LOGITS
    throughout
    1.61
    HOUT
    1.43
     throughout
    1.39
     Throughout
    1.23
    Throughout
    1.23
    MLLoader
    1.20
     تضيفلها
    1.13
    ostante
    1.06
     ExecuteAsync
    1.06
    athread
    1.04
    Act Density 0.048%

    No Known Activations