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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and governmental control in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bbe
    -0.16
    Anyway
    -0.15
    untime
    -0.15
    ongan
    -0.15
     irresistible
    -0.14
     sez
    -0.14
    kü
    -0.14
     надо
    -0.14
     incidental
    -0.14
    çĮĽ
    -0.13
    POSITIVE LOGITS
     void
    0.18
     engr
    0.17
     cater
    0.17
    chalk
    0.16
    缸
    0.15
     inline
    0.15
     jov
    0.15
     apart
    0.15
     hypo
    0.15
     VOID
    0.15
    Act Density 0.396%

    No Known Activations