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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.66
    </strong>
    -0.54
     […]
    -0.53
    -
    -0.53
    '
    -0.52
    ‘
    -0.52
     
    -0.50
     ‘
    -0.49
    </em>
    -0.48
    …
    -0.45
    POSITIVE LOGITS
     pleaſure
    1.00
     cauſe
    0.97
     purpoſe
    0.96
     ſtate
    0.96
     ſy
    0.89
     perſon
    0.88
    ſelf
    0.88
    MessageTagHelper
    0.87
    =$?
    0.87
     houſe
    0.87
    Act Density 0.928%

    No Known Activations