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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations and their associated power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fir
    -0.15
    quil
    -0.15
    ptune
    -0.15
    ringe
    -0.14
    ynos
    -0.14
    prung
    -0.14
    гоÑĢод
    -0.14
    bane
    -0.14
    341
    -0.13
    aliyet
    -0.13
    POSITIVE LOGITS
     power
    0.53
     Power
    0.52
    Power
    0.45
    power
    0.43
    .Power
    0.43
    /power
    0.42
    (power
    0.41
     POWER
    0.41
    -power
    0.40
    _power
    0.38
    Act Density 0.042%

    No Known Activations