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

    Neuronpedia

    INDEX
    Explanations

    references to characters or elements related to the fantasy genre, particularly dwarves, goblins, and wacky scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to dwarves and related fantasy elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mayer
    -0.79
     Raymond
    -0.75
    inois
    -0.73
     ap
    -0.73
    jay
    -0.73
     retire
    -0.72
     Nunes
    -0.72
    yss
    -0.72
    ois
    -0.71
    angelo
    -0.69
    POSITIVE LOGITS
     Dwar
    3.02
     dwarves
    1.53
     Dwarf
    1.49
     Goblin
    1.36
     Atari
    1.19
     USSR
    1.14
    DOS
    1.09
    acky
    1.06
     Autob
    0.98
     Elves
    0.97
    Act Density 0.053%

    No Known Activations