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

    Neuronpedia

    INDEX
    Explanations

    non-alphabetical characters 'Ċ' that possibly indicate separation between sections or paragraphs in text

    oai_token-act-pair · gpt-3.5-turbo

    quantitative metrics or statistics in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Learns
    -0.76
    awaru
    -0.71
     estranged
    -0.71
     unle
    -0.70
     honors
    -0.69
     unveiling
    -0.69
     Compass
    -0.68
     adversaries
    -0.67
     Arrest
    -0.66
     instruments
    -0.65
    POSITIVE LOGITS
    Reply
    1.28
    Posted
    1.24
    ________________
    1.14
    posted
    1.11
    Anonymous
    1.05
    Guest
    1.02
    Edited
    1.02
    Reviewer
    0.99
    Anyway
    0.99
    Comment
    0.98
    Act Density 0.353%

    No Known Activations