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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Here" along with descriptive phrases and examples provided in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    таратура
    -0.94
    InjectAttribute
    -0.90
    ConstraintMaker
    -0.89
     Roskov
    -0.89
    ]")]
    -0.88
     ویکی‌پدی
    -0.86
    Sucesor
    -0.86
    parsedMessage
    -0.85
    الدراسه
    -0.81
     فريبيس
    -0.79
    POSITIVE LOGITS
     a
    0.70
     some
    0.66
     what
    0.62
     the
    0.61
    Heres
    0.60
     another
    0.59
    Ecco
    0.56
     our
    0.56
     lautet
    0.54
     something
    0.52
    Act Density 0.079%

    No Known Activations