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

    Neuronpedia

    INDEX
    Explanations

    objects in the sky, particularly those related to astronomy like comets, planets, stars, and UFOs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Childhood
    -0.33
     Parables
    -0.29
    arten
    -0.29
     Nights
    -0.27
    expression
    -0.27
    ior
    -0.26
     Promotion
    -0.26
     Genie
    -0.25
    thood
    -0.25
     Fn
    -0.25
    POSITIVE LOGITS
     hovering
    0.35
     resembling
    0.34
     orbiting
    0.34
     sightings
    0.33
     inhabited
    0.33
     UFOs
    0.33
     sighting
    0.32
     inhab
    0.32
     protr
    0.31
     resembled
    0.31
    Act Density 11.956%

    No Known Activations