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

    Neuronpedia

    INDEX
    Explanations

    references to coal-fired power plants and their operational status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vise
    -0.17
     Dudley
    -0.14
     subs
    -0.13
    wine
    -0.13
    _OPT
    -0.13
     vz
    -0.13
    /tool
    -0.13
    gars
    -0.13
     ÑĤи
    -0.13
    dsl
    -0.13
    POSITIVE LOGITS
     coal
    0.32
     power
    0.31
     plants
    0.29
    coal
    0.26
     Coal
    0.26
     plant
    0.25
     Power
    0.25
     POWER
    0.25
    power
    0.25
    plants
    0.25
    Act Density 0.069%

    No Known Activations