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

    Neuronpedia

    INDEX
    Explanations

    dates and times written in different formats

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "on" and similar prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rushing
    -0.62
     Tsukuyomi
    -0.61
     intervening
    -0.57
     Fib
    -0.55
     Roses
    -0.55
     Reynolds
    -0.55
     dial
    -0.54
     Cran
    -0.54
     Viz
    -0.53
     clinically
    -0.53
    POSITIVE LOGITS
    mast
    0.81
    merce
    0.75
    uff
    0.73
    livion
    0.73
    idate
    0.73
    cott
    0.72
    20439
    0.70
    oustic
    0.70
    ulate
    0.70
    arette
    0.69
    Act Density 0.048%

    No Known Activations