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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of power in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stubbs
    -0.45
     conclusão
    -0.40
     quaisquer
    -0.40
    <![
    -0.39
    <
    -0.39
     Absch
    -0.35
     trùng
    -0.34
     obscene
    -0.34
     Crist
    -0.33
    listItem
    -0.33
    POSITIVE LOGITS
     Power
    1.40
    Power
    1.34
     power
    1.28
    POWER
    1.26
    power
    1.26
     POWER
    1.24
     pleaſure
    1.06
    setPower
    1.02
     Powers
    1.01
    Powers
    1.00
    Act Density 0.033%

    No Known Activations