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

    Neuronpedia

    INDEX
    Explanations

    references to mythical creatures and legendary beings

    oai_token-act-pair · gpt-3.5-turbo

    references to fantastical creatures and mythological figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rique
    -0.81
    ļéĨĴ
    -0.78
    ¡
    -0.76
    pring
    -0.76
     Brune
    -0.74
    CHAT
    -0.74
     GOODMAN
    -0.73
    ability
    -0.73
    dullah
    -0.71
    ĺ
    -0.71
    POSITIVE LOGITS
     sorcerer
    0.93
     dragons
    0.92
     beasts
    0.92
     monsters
    0.90
     lair
    0.89
     slaying
    0.87
     assassins
    0.82
     rav
    0.80
     extermination
    0.80
     labyrinth
    0.80
    Act Density 0.045%

    No Known Activations