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

    Neuronpedia

    INDEX
    Explanations

    references to heroes, particularly in the context of superhero narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     photolibrary
    -0.87
     gales
    -0.84
     bushels
    -0.82
     animé
    -0.81
    Personensuche
    -0.79
     виправивши
    -0.79
     Coyote
    -0.77
     myſelf
    -0.76
     itſelf
    -0.75
     Prehistoric
    -0.75
    POSITIVE LOGITS
     hero
    1.01
     heroes
    0.86
     Hero
    0.77
    hero
    0.73
     héroes
    0.73
     Heroes
    0.68
    remarks
    0.66
    Hero
    0.64
     Bel
    0.59
    英雄
    0.59
    Act Density 0.086%

    No Known Activations