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

    Neuronpedia

    INDEX
    Explanations

    references to the moon

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the moon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maduro
    -0.72
    nikov
    -0.70
     Sark
    -0.68
    eq
    -0.64
    IDE
    -0.64
    IME
    -0.63
     Marketable
    -0.63
    tml
    -0.63
    oba
    -0.63
     Ahmad
    -0.62
    POSITIVE LOGITS
    beam
    1.23
    lit
    1.17
    light
    1.09
    stone
    1.08
    rise
    1.05
    walking
    1.04
    lighting
    1.04
     orbiting
    1.02
    stru
    1.01
     rover
    0.95
    Act Density 0.022%

    No Known Activations