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

    Neuronpedia

    INDEX
    Explanations

    words related to antagonists or villains in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    references to villains in storytelling and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dating
    -0.75
    independent
    -0.75
    ordering
    -0.72
    olen
    -0.72
    ollen
    -0.71
    aternity
    -0.71
    kept
    -0.71
    press
    -0.71
    obar
    -0.68
    ensation
    -0.67
    POSITIVE LOGITS
     villain
    1.29
     villains
    1.09
     mastermind
    0.95
    ous
    0.87
     antagonist
    0.84
     Bane
    0.83
    esses
    0.78
     satir
    0.77
     strugg
    0.74
    hattan
    0.70
    Act Density 0.009%

    No Known Activations