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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values related to power capacity in megawatts

    oai_token-act-pair · gpt-3.5-turbo

    references to megawatt (MW) power capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bart
    -0.64
     psy
    -0.64
     Labrador
    -0.64
     communist
    -0.63
    kick
    -0.63
     MacArthur
    -0.63
    voy
    -0.61
    amount
    -0.60
     Fract
    -0.60
    leans
    -0.59
    POSITIVE LOGITS
    MW
    1.31
    atts
    1.00
    NT
    0.98
    ILA
    0.92
    ESH
    0.91
     MW
    0.89
    LAN
    0.89
    ILD
    0.89
    ILY
    0.89
    Fs
    0.87
    Act Density 0.005%

    No Known Activations