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

    Neuronpedia

    INDEX
    Explanations

    proper names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of people, particularly in a list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -0.76
    DragonMagazine
    -0.74
    é»Ĵ
    -0.62
    omething
    -0.60
    emort
    -0.59
    lihood
    -0.56
     fixme
    -0.56
    ccording
    -0.55
     Cards
    -0.54
     Gutenberg
    -0.52
    POSITIVE LOGITS
    range
    0.61
    tor
    0.57
    noon
    0.55
    apple
    0.54
    da
    0.54
     ];
    0.54
    enium
    0.53
    storms
    0.52
    Jr
    0.52
    amboo
    0.51
    Act Density 0.246%

    No Known Activations