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

    Neuronpedia

    INDEX
    Explanations

    instances of revelation or exposure of secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eum
    -0.18
    _NC
    -0.15
    \Events
    -0.14
    herits
    -0.14
    hsi
    -0.14
    EDIA
    -0.14
    Registrar
    -0.14
     spirit
    -0.14
    RIX
    -0.14
    ابÙĬ
    -0.14
    POSITIVE LOGITS
     underlying
    0.21
     reveal
    0.19
     behind
    0.17
     revealing
    0.17
     reveals
    0.16
    ippi
    0.16
    reveal
    0.16
     revealed
    0.15
     beneath
    0.15
    ERE
    0.15
    Act Density 0.266%

    No Known Activations