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

    Neuronpedia

    INDEX
    Explanations

    mentions of the planet Earth

    oai_token-act-pair · gpt-3.5-turbo

    references to the Earth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussen
    -0.84
    acca
    -0.76
    ublic
    -0.70
    weeney
    -0.66
    interstitial
    -0.66
    hett
    -0.65
    enges
    -0.64
    UGE
    -0.63
    acco
    -0.61
    unta
    -0.61
    POSITIVE LOGITS
    worm
    0.92
    leigh
    0.91
    lings
    0.91
    worms
    0.90
     Orbit
    0.89
    sea
    0.88
    works
    0.83
    Bound
    0.82
    ffen
    0.82
     shattering
    0.81
    Act Density 0.012%

    No Known Activations