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

    Neuronpedia

    INDEX
    Explanations

    references to superheroes

    oai_token-act-pair · gpt-3.5-turbo

    references to superheroes and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    redo
    -0.77
    ¿½
    -0.76
    chard
    -0.76
    baugh
    -0.75
    bah
    -0.75
    assetsadobe
    -0.73
    keeper
    -0.72
    obar
    -0.71
    grain
    -0.71
    bos
    -0.69
    POSITIVE LOGITS
     villains
    0.97
     villain
    0.94
     heroes
    0.87
     superhero
    0.87
     superheroes
    0.85
     powers
    0.84
     battling
    0.78
     costumes
    0.77
     hero
    0.75
     cape
    0.74
    Act Density 0.063%

    No Known Activations