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

    Neuronpedia

    INDEX
    Explanations

    words related to power and energy

    oai_token-act-pair · gpt-3.5-turbo

    references to electricity and its generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.88
     Von
    -0.82
     Schiff
    -0.74
     Caesar
    -0.73
    eret
    -0.70
    roma
    -0.70
     Taste
    -0.68
     Debor
    -0.68
    oslov
    -0.67
     Mara
    -0.65
    POSITIVE LOGITS
     outage
    1.04
    houses
    0.97
    train
    0.93
     cords
    0.88
     levers
    0.82
    stroke
    0.78
    lifting
    0.78
    atts
    0.78
    boats
    0.78
     generators
    0.77
    Act Density 0.030%

    No Known Activations