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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of rings in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.01
    anskje
    -0.91
     myſelf
    -0.85
    zepte
    -0.84
     Maul
    -0.84
     McFadden
    -0.83
     Maho
    -0.83
     chofe
    -0.83
    ydı
    -0.82
     ſtate
    -0.81
    POSITIVE LOGITS
     ring
    1.86
     rings
    1.80
     Ring
    1.74
     RING
    1.64
    rings
    1.63
     Rings
    1.62
    Rings
    1.58
    Ring
    1.57
    ring
    1.49
    RING
    1.33
    Act Density 0.019%

    No Known Activations