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

    Neuronpedia

    INDEX
    Explanations

    phrases related to astrophysics and cosmology

    oai_token-act-pair · gpt-3.5-turbo

    references to the universe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.77
    bourg
    -0.73
    espie
    -0.71
    idate
    -0.70
    ippi
    -0.67
    dog
    -0.67
    ership
    -0.67
    utic
    -0.67
    ownt
    -0.66
    odox
    -0.66
    POSITIVE LOGITS
    arium
    1.10
     continuum
    0.94
    entric
    0.88
     cosmic
    0.83
    ALLY
    0.82
    eers
    0.79
     collide
    0.76
     Eucl
    0.76
     universe
    0.75
     Creator
    0.73
    Act Density 0.065%

    No Known Activations