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

    Neuronpedia

    INDEX
    Explanations

    elements related to scientific research and academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Atsauces
    -0.83
    aarrggbb
    -0.81
    AndEndTag
    -0.80
    parsedMessage
    -0.78
    DockStyle
    -0.71
    DoubleQuotes
    -0.71
    Viited
    -0.70
     myſelf
    -0.69
    elfare
    -0.69
    ętr
    -0.68
    POSITIVE LOGITS
     Berkshire
    0.91
     Berks
    0.83
     snake
    0.74
     Snake
    0.69
     Newbury
    0.67
    Snake
    0.65
     Reading
    0.62
     snakes
    0.61
     Serpent
    0.59
     Windsor
    0.59
    Act Density 0.280%

    No Known Activations