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

    Neuronpedia

    INDEX
    Explanations

    references to space exploration and celestial phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elevation
    -0.14
     Bom
    -0.14
     Jar
    -0.14
     yat
    -0.14
    apia
    -0.14
    apult
    -0.14
     Ath
    -0.13
    rado
    -0.13
     Sle
    -0.13
    resi
    -0.13
    POSITIVE LOGITS
     gal
    0.42
     galaxy
    0.37
    gal
    0.36
     Galaxy
    0.35
     galaxies
    0.35
     stars
    0.33
     Milky
    0.32
     гал
    0.32
    Gal
    0.30
     Gal
    0.29
    Act Density 0.272%

    No Known Activations