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

    Neuronpedia

    INDEX
    Explanations

    references to academic subjects or disciplines, particularly focusing on literature

    oai_token-act-pair · gpt-3.5-turbo

    references to literature and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twitch
    -0.65
    ermanent
    -0.62
    gg
    -0.61
    gur
    -0.61
    addafi
    -0.60
    earth
    -0.60
    oland
    -0.59
    fty
    -0.59
     Maurit
    -0.58
     Bots
    -0.57
    POSITIVE LOGITS
     literature
    1.10
    DragonMagazine
    0.90
     Literature
    0.87
     laureate
    0.85
     manuscripts
    0.80
     RELE
    0.79
     writ
    0.77
     scen
    0.75
    istry
    0.74
     novels
    0.72
    Act Density 0.017%

    No Known Activations