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

    Neuronpedia

    INDEX
    Explanations

    text related to science fiction and extraterrestrial beings

    oai_token-act-pair · gpt-3.5-turbo

    references to dangerous or destructive activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atility
    -0.81
    ordable
    -0.80
    etitive
    -0.77
    essment
    -0.76
    cipled
    -0.70
    affer
    -0.69
    omore
    -0.69
    annel
    -0.69
    agements
    -0.69
    cipline
    -0.68
    POSITIVE LOGITS
     aliens
    1.19
     dwarves
    1.19
     goblins
    1.18
     mutants
    1.16
     orcs
    1.14
     monsters
    1.11
     dragons
    1.11
     zombies
    1.09
     Lovecraft
    1.05
     teleportation
    1.03
    Act Density 0.647%

    No Known Activations