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

    Neuronpedia

    INDEX
    Explanations

    words related to atomic energy and atomic bombs

    oai_token-act-pair · gpt-3.5-turbo

    references to atomic energy and atomic bombs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atche
    -0.97
    shire
    -0.82
    anson
    -0.82
     Fargo
    -0.73
    llers
    -0.72
    PE
    -0.72
    cific
    -0.72
    nir
    -0.72
    sburgh
    -0.72
    WT
    -0.72
    POSITIVE LOGITS
     nucle
    0.97
     atomic
    0.94
     nucleus
    0.86
     bomb
    0.84
     clocks
    0.84
    atomic
    0.84
     atom
    0.83
     swaps
    0.81
     latt
    0.78
     atoms
    0.78
    Act Density 0.018%

    No Known Activations