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

    Neuronpedia

    INDEX
    Explanations

    instances of quotations and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     насељу
    -0.99
     myſelf
    -0.90
    DockStyle
    -0.84
     purpoſe
    -0.84
     auffi
    -0.81
     himſelf
    -0.81
    :✨
    -0.80
     ſtate
    -0.80
     ſeveral
    -0.79
     consciences
    -0.78
    POSITIVE LOGITS
     issues
    0.47
     and
    0.45
    ’
    0.41
    Tembelea
    0.41
    </h3>
    0.40
     plus
    0.40
     re
    0.39
     in
    0.39
     
    0.37
     to
    0.36
    Act Density 0.218%

    No Known Activations