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

    Neuronpedia

    INDEX
    Explanations

    references to energy generation and electricity production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thermometer
    -0.15
     dét
    -0.15
    _SS
    -0.14
     Proper
    -0.14
    uru
    -0.14
    ubble
    -0.14
    unami
    -0.13
    _FAST
    -0.13
     Lager
    -0.13
     vr
    -0.13
    POSITIVE LOGITS
     electricity
    0.44
     energy
    0.35
     Electricity
    0.34
     electrical
    0.34
    electric
    0.33
     power
    0.33
    energy
    0.29
     electric
    0.28
     grid
    0.26
    Electric
    0.26
    Act Density 0.084%

    No Known Activations