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

    Neuronpedia

    INDEX
    Explanations

    numbers related to various countries or entities

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.82
    ablishment
    -0.73
    brance
    -0.73
    ific
    -0.72
    ãĥ¼ãĥ³
    -0.69
    Reviewer
    -0.67
    ilant
    -0.67
    utory
    -0.67
    icide
    -0.66
    é¾įåĸļ士
    -0.65
    POSITIVE LOGITS
     RM
    0.59
     Darth
    0.58
     Martial
    0.58
    aucus
    0.57
     Mandarin
    0.57
     hers
    0.56
     Sasha
    0.56
     Professor
    0.56
     Jungle
    0.54
     martial
    0.54
    Act Density 0.115%

    No Known Activations