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

    Neuronpedia

    INDEX
    Explanations

    references to fictional books or novels

    oai_token-act-pair · gpt-3.5-turbo

    references to specific works of fiction, especially novels and their elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.85
    ntil
    -0.84
    jri
    -0.84
    ustainable
    -0.75
    iquid
    -0.75
    lah
    -0.75
    ollah
    -0.74
    yden
    -0.72
    usra
    -0.72
    paio
    -0.72
    POSITIVE LOGITS
     Characters
    1.43
    Characters
    1.32
     characters
    1.22
     cinematic
    1.14
     protagonist
    1.14
     storyline
    1.11
     flashbacks
    1.11
    acters
    1.08
     narrator
    1.04
     protagonists
    1.03
    Act Density 0.956%

    No Known Activations