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

    Neuronpedia

    INDEX
    Explanations

    words related to the genre of fiction

    oai_token-act-pair · gpt-3.5-turbo

    references to fiction, particularly various genres within fictional narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cles
    -0.70
     KD
    -0.67
     Elect
    -0.67
    une
    -0.67
    ebus
    -0.66
     Nug
    -0.63
     coordinate
    -0.61
     clamp
    -0.60
     Chain
    -0.60
    eh
    -0.60
    POSITIVE LOGITS
     fiction
    3.81
     Fiction
    2.93
    fiction
    2.51
     novels
    1.73
     fictional
    1.68
     novelist
    1.52
     fantasy
    1.34
     poetry
    1.28
     fict
    1.26
     Lovecraft
    1.24
    Act Density 0.016%

    No Known Activations