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

    Neuronpedia

    INDEX
    Explanations

    dates in various formats

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods at the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rall
    -0.87
     tide
    -0.72
     stocking
    -0.72
     unconscious
    -0.72
     trembling
    -0.70
     sunset
    -0.69
     blush
    -0.69
     matured
    -0.67
     purse
    -0.67
     awake
    -0.67
    POSITIVE LOGITS
    com
    1.27
    org
    1.09
    net
    1.03
    biz
    0.90
    nl
    0.88
    psc
    0.88
     However
    0.88
    co
    0.87
    cn
    0.86
    dk
    0.85
    Act Density 0.116%

    No Known Activations