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

    Neuronpedia

    INDEX
    Explanations

    mentions of celestial objects, specifically galaxies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of galaxies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.81
    ake
    -0.76
    orney
    -0.74
    ointed
    -0.73
    drawn
    -0.68
    eff
    -0.67
    ebin
    -0.64
    lying
    -0.64
    ded
    -0.63
    AK
    -0.62
    POSITIVE LOGITS
     galaxy
    1.25
     galaxies
    1.01
     Andromeda
    0.95
     Nebula
    0.87
     Milky
    0.86
    ãĤ¼ãĤ¦ãĤ¹
    0.85
    stellar
    0.84
     galactic
    0.82
     Galaxy
    0.81
     capacitor
    0.78
    Act Density 0.009%

    No Known Activations