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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly in a context that involves performing or analyzing certain roles or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.95
     Juarez
    -0.87
     postIndex
    -0.87
    cadilly
    -0.84
     McLaugh
    -0.81
    postIndex
    -0.80
    \}\\
    -0.80
    ajuato
    -0.80
     EST
    -0.79
    NamedQueries
    -0.79
    POSITIVE LOGITS
     Erick
    0.78
     Scooter
    0.74
     Chwiliwch
    0.71
     Puck
    0.71
     Ket
    0.70
    Scooter
    0.69
    vri
    0.68
     Tuk
    0.68
    Erick
    0.67
     Caspian
    0.67
    Act Density 0.900%

    No Known Activations