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

    Neuronpedia

    INDEX
    Explanations

    references to radiation levels and possible contamination

    oai_token-act-pair · gpt-3.5-turbo

    references to radiation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eenth
    -0.86
    lihood
    -0.82
    neys
    -0.76
    lier
    -0.75
    ths
    -0.74
    aws
    -0.73
    avanaugh
    -0.73
    ĵĺ
    -0.72
    eff
    -0.72
    liness
    -0.71
    POSITIVE LOGITS
     radiation
    1.03
     emitted
    0.97
     shielding
    0.92
     belts
    0.88
     detectors
    0.88
     irrad
    0.87
     sickness
    0.85
     rays
    0.84
     horm
    0.83
     iodine
    0.83
    Act Density 0.014%

    No Known Activations