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

    Neuronpedia

    INDEX
    Explanations

    references to circular objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to circular shapes and patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.88
    INA
    -0.74
    rol
    -0.71
    enez
    -0.71
    ICH
    -0.71
     Pets
    -0.70
    afa
    -0.70
    EG
    -0.68
    OWER
    -0.67
    xa
    -0.67
    POSITIVE LOGITS
     circular
    1.18
     satell
    0.88
    worm
    0.82
     oval
    0.81
     mosqu
    0.79
     occas
    0.78
    ²¾
    0.77
     tiss
    0.77
     nodd
    0.77
     motions
    0.76
    Act Density 0.005%

    No Known Activations