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

    Neuronpedia

    INDEX
    Explanations

    terms related to power and energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.71
    SpringBootTest
    -0.70
    躇
    -0.66
    ByExample
    -0.62
     power
    -0.57
     powerful
    -0.57
    power
    -0.56
    principalTable
    -0.52
    Portály
    -0.51
    Rüyada
    -0.50
    POSITIVE LOGITS
    houses
    0.80
    plant
    0.72
     plant
    0.67
    puff
    0.66
    train
    0.66
     Plant
    0.63
    Plant
    0.63
     supply
    0.61
     outage
    0.61
    trains
    0.60
    Act Density 0.147%

    No Known Activations