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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of 'everything'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "everything."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.73
    uca
    -0.73
    eda
    -0.69
    gart
    -0.69
    eka
    -0.68
    odan
    -0.68
    arty
    -0.68
    uador
    -0.67
    ithering
    -0.67
    rers
    -0.65
    POSITIVE LOGITS
     except
    1.21
     imaginable
    1.05
    except
    1.04
     Including
    0.84
     hoop
    0.77
     mathemat
    0.76
    including
    0.75
    Except
    0.72
     nodd
    0.72
    soever
    0.70
    Act Density 0.630%

    No Known Activations