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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Dragon" and related fantasy contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ£ãģ¡
    -0.17
    iy
    -0.16
    gere
    -0.16
    sis
    -0.15
    awah
    -0.14
    prak
    -0.14
    tures
    -0.14
    ippi
    -0.14
     Animal
    -0.13
     Alger
    -0.13
    POSITIVE LOGITS
    fly
    0.37
    flies
    0.35
    Fly
    0.22
    etti
    0.22
    fruit
    0.21
    flight
    0.21
    -fly
    0.19
    ess
    0.19
     Boat
    0.19
     Nest
    0.18
    Act Density 0.010%

    No Known Activations