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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Dragon" and its variants within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALS
    -0.78
    arning
    -0.73
    ilitary
    -0.71
    ablished
    -0.71
    akeru
    -0.71
     horizont
    -0.70
    EMS
    -0.68
    rontal
    -0.67
     polic
    -0.66
     Crosby
    -0.65
    POSITIVE LOGITS
    fly
    1.36
    flies
    1.04
    Fly
    1.01
    hawk
    0.99
    lance
    0.97
    bone
    0.96
    hook
    0.86
    flight
    0.84
     Tatt
    0.84
    balls
    0.81
    Act Density 0.008%

    No Known Activations