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

    Neuronpedia

    INDEX
    Explanations

    terms related to power and its various forms, both positive and negative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     power
    -0.34
    _power
    -0.30
     POWER
    -0.29
     Power
    -0.29
    POWER
    -0.28
    Power
    -0.27
     poder
    -0.27
    power
    -0.26
    -power
    -0.26
     powering
    -0.24
    POSITIVE LOGITS
    fully
    0.38
    ful
    0.28
    full
    0.26
    houses
    0.25
    train
    0.23
    FUL
    0.22
    lifting
    0.22
    plant
    0.21
    FULL
    0.20
    ment
    0.19
    Act Density 0.075%

    No Known Activations