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

    Neuronpedia

    INDEX
    Explanations

    terms related to radiation, fallout, and nuclear disasters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eenth
    -0.87
    thood
    -0.83
    lihood
    -0.79
    theless
    -0.78
    lier
    -0.76
    HCR
    -0.76
    lopp
    -0.74
    ths
    -0.71
    hler
    -0.71
    uti
    -0.69
    POSITIVE LOGITS
     radiation
    1.06
     horm
    0.98
     shielding
    0.97
     sickness
    0.95
     irrad
    0.93
     isot
    0.92
     belts
    0.91
     doses
    0.90
     Radiation
    0.90
     detectors
    0.89
    Act Density 0.072%

    No Known Activations