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

    Neuronpedia

    INDEX
    Explanations

    phrases related to celestial bodies, especially Earth

    oai_token-act-pair · gpt-3.5-turbo

    references to Earth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.75
    acca
    -0.67
    weeney
    -0.66
    ublic
    -0.64
    acco
    -0.64
    hirt
    -0.63
    interstitial
    -0.62
    ority
    -0.62
    UGE
    -0.62
    enges
    -0.62
    POSITIVE LOGITS
    lings
    1.00
    leigh
    0.99
    worm
    0.97
    worms
    0.96
    sea
    0.92
    works
    0.89
     Orbit
    0.88
    Bound
    0.85
     orbiting
    0.82
    shine
    0.82
    Act Density 0.017%

    No Known Activations