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

    Neuronpedia

    INDEX
    Explanations

    references to power outages and their effects on daily life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.17
    azzo
    -0.15
     Buna
    -0.14
     cannons
    -0.14
    é¾Ħ
    -0.14
    ождение
    -0.14
    oller
    -0.13
     ÙħادÙĩ
    -0.13
     tabi
    -0.13
    à¸Ńล
    -0.13
    POSITIVE LOGITS
     power
    0.28
    power
    0.23
     electricity
    0.23
     Power
    0.22
    -power
    0.21
     lights
    0.20
    (power
    0.20
     electric
    0.19
    .power
    0.19
    Power
    0.19
    Act Density 0.024%

    No Known Activations