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

    Neuronpedia

    INDEX
    Explanations

    information about video games

    oai_token-act-pair · gpt-3.5-turbo

    references to video games and comic books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -1.00
    20439
    -0.97
    ²¾
    -0.81
    cair
    -0.80
    rex
    -0.79
    days
    -0.79
    staking
    -0.79
    pex
    -0.78
    iless
    -0.77
    south
    -0.76
    POSITIVE LOGITS
     superheroes
    1.04
     enthusiast
    1.04
     heroine
    1.03
     villain
    1.01
     fandom
    1.01
     adaptations
    0.99
     superhero
    0.98
     mogul
    0.97
     encyclopedia
    0.97
     legend
    0.95
    Act Density 0.131%

    No Known Activations