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

    Neuronpedia

    INDEX
    Explanations

    editions of books or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to different editions of publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asive
    -0.76
    uli
    -0.71
    orage
    -0.69
    romancer
    -0.67
    ato
    -0.67
    pload
    -0.66
    maxwell
    -0.66
     blat
    -0.66
    ortium
    -0.65
     decl
    -0.65
    POSITIVE LOGITS
     thereof
    1.01
    ansion
    0.73
     of
    0.71
    velop
    0.71
     edition
    0.70
    ctl
    0.65
    @#
    0.63
     Gamb
    0.61
     editions
    0.61
    DonaldTrump
    0.60
    Act Density 0.027%

    No Known Activations