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

    Neuronpedia

    INDEX
    Explanations

    quantitative estimates and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '
    -0.63
     "
    -0.58
     '
    -0.54
    </b>
    -0.52
     e
    -0.50
    -
    -0.50
    )
    -0.50
     i
    -0.50
     ta
    -0.50
    ss
    -0.49
    POSITIVE LOGITS
     myſelf
    1.34
     pleaſure
    1.25
     houſe
    1.19
     المعيارى
    1.17
     raiſ
    1.17
     Monfieur
    1.17
     itſelf
    1.15
     whoſe
    1.14
     Reſ
    1.14
     ſte
    1.14
    Act Density 1.661%

    No Known Activations