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

    Neuronpedia

    INDEX
    Explanations

    markup and HTML tags

    oai_token-act-pair · gpt-3.5-turbo

    link or reference elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesses
    -0.68
     Selection
    -0.67
    irements
    -0.65
     negatives
    -0.65
    verning
    -0.63
     Solitaire
    -0.61
     selections
    -0.61
    ©¶æ
    -0.60
     Absent
    -0.60
    epad
    -0.60
    POSITIVE LOGITS
    Twitter
    1.15
     tweeted
    1.08
    twitter
    1.01
     tweet
    0.95
     tweeting
    0.94
    )</
    0.93
    pic
    0.92
     Twitter
    0.91
    https
    0.89
     hashtag
    0.89
    Act Density 0.067%

    No Known Activations