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

    Neuronpedia

    INDEX
    Explanations

    different forms of the word "draw" as well as related artistic terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adera
    -0.18
    avana
    -0.16
     Angelo
    -0.15
    692
    -0.15
    uju
    -0.15
    arily
    -0.15
    ency
    -0.15
    yu
    -0.15
    zon
    -0.14
    nÃŃ
    -0.14
    POSITIVE LOGITS
    string
    0.24
    bridge
    0.23
    backs
    0.22
     attention
    0.22
    esome
    0.20
    ings
    0.20
    down
    0.19
    pile
    0.19
    attention
    0.19
    brid
    0.19
    Act Density 0.029%

    No Known Activations