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

    Neuronpedia

    INDEX
    Explanations

    phrases related to philosophical or abstract concepts, especially those related to nature and the world

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of the world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -1.16
    aturday
    -0.84
     actionGroup
    -0.80
    ippi
    -0.79
    ibility
    -0.77
     sidx
    -0.77
    irez
    -0.77
    IFF
    -0.76
    ients
    -0.76
    utenant
    -0.75
    POSITIVE LOGITS
    building
    0.74
    eers
    0.72
    liness
    0.71
     economy
    0.71
     outlook
    0.70
     Order
    0.69
     Zionism
    0.68
     religions
    0.67
    wide
    0.67
    scape
    0.66
    Act Density 0.050%

    No Known Activations