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

    Neuronpedia

    INDEX
    Explanations

    references to celestial bodies, particularly Earth

    oai_token-act-pair · gpt-3.5-turbo

    references to Earth and its features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.79
    acco
    -0.71
    weeney
    -0.66
    enges
    -0.65
    interstitial
    -0.65
    owler
    -0.63
    ority
    -0.63
    acca
    -0.62
    utic
    -0.62
    UGE
    -0.61
    POSITIVE LOGITS
    lings
    1.07
    worm
    0.99
    worms
    0.98
    sea
    0.97
    leigh
    0.96
    Bound
    0.94
     Orbit
    0.89
    works
    0.88
    arium
    0.87
    shine
    0.83
    Act Density 0.021%

    No Known Activations