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

    Neuronpedia

    INDEX
    Explanations

    the word "Moon"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Moon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iability
    -0.83
    axter
    -0.74
    kson
    -0.70
    Downloadha
    -0.70
    leneck
    -0.70
    Interstitial
    -0.69
    initions
    -0.66
    utic
    -0.66
    thodox
    -0.65
    tml
    -0.65
    POSITIVE LOGITS
    beam
    1.20
    lit
    1.04
    stru
    0.90
    walking
    0.86
    rise
    0.84
     rover
    0.82
     Jae
    0.81
    light
    0.81
    phase
    0.81
    lighting
    0.78
    Act Density 0.011%

    No Known Activations