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

    Neuronpedia

    INDEX
    Explanations

    mentions or references of celestial bodies, specifically the moon

    oai_token-act-pair · gpt-3.5-turbo

    references to the moon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.85
    ÃĽ
    -0.77
    illance
    -0.75
    IME
    -0.72
    irrel
    -0.71
    eq
    -0.70
    ifax
    -0.69
    oba
    -0.69
    WER
    -0.69
    IFF
    -0.67
    POSITIVE LOGITS
    light
    1.00
     orbiting
    0.96
     moons
    0.95
    beam
    0.92
    lit
    0.89
     moon
    0.88
     eclipse
    0.83
    flower
    0.83
     rover
    0.80
    stone
    0.79
    Act Density 0.010%

    No Known Activations