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

    Neuronpedia

    INDEX
    Explanations

    references to dragons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ£ãģ¡
    -0.18
    ismet
    -0.15
    acles
    -0.15
    ilis
    -0.15
    Ïĩε
    -0.15
     gì
    -0.14
    /Register
    -0.14
    reeze
    -0.14
    ابÙĬ
    -0.14
    iy
    -0.14
    POSITIVE LOGITS
    fly
    0.36
    flies
    0.32
    etti
    0.19
    Fly
    0.19
    flight
    0.18
    fruit
    0.17
     Rider
    0.17
    layer
    0.17
    ess
    0.17
    rid
    0.17
    Act Density 0.011%

    No Known Activations