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

    Neuronpedia

    INDEX
    Explanations

    references to various types of rings or circular structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.09
    存于互联网档案馆
    -0.91
     Maho
    -0.86
    anskje
    -0.84
    حياته
    -0.83
    \{\\
    -0.82
     Gaston
    -0.81
     McLeod
    -0.80
    assertIs
    -0.79
     myſelf
    -0.79
    POSITIVE LOGITS
     ring
    2.07
     rings
    2.04
     Ring
    1.99
     RING
    1.93
     Rings
    1.88
    Rings
    1.83
    Ring
    1.83
    rings
    1.73
    ring
    1.66
    RING
    1.53
    Act Density 0.056%

    No Known Activations