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

    Neuronpedia

    INDEX
    Explanations

    references to or descriptions of dwarfs/dwarves

    oai_token-act-pair · gpt-3.5-turbo

    references to dwarfs or dwarves in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orie
    -0.85
    inventoryQuantity
    -0.79
    ettings
    -0.75
    ored
    -0.71
     Clip
    -0.71
    mble
    -0.68
    essee
    -0.68
     Seller
    -0.66
     antioxid
    -0.66
    henko
    -0.65
    POSITIVE LOGITS
     Dwar
    0.89
     Dwarf
    0.87
     Fortress
    0.84
     dwarves
    0.83
     dwarf
    0.82
    ishly
    0.81
     elves
    0.80
    shire
    0.78
    sson
    0.72
    haus
    0.70
    Act Density 0.017%

    No Known Activations