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

    Neuronpedia

    INDEX
    Explanations

    elements related to criticism of societal systems and their effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardown
    -0.15
    ffffffff
    -0.15
    оÑĢони
    -0.15
    FFFFFFFF
    -0.14
    iego
    -0.14
    Animating
    -0.14
    CLUDING
    -0.13
    incerely
    -0.13
    udy
    -0.13
    ",{
    -0.13
    POSITIVE LOGITS
     even
    0.46
    even
    0.40
     Even
    0.37
     EVEN
    0.35
    Even
    0.34
     when
    0.31
    _even
    0.30
     those
    0.29
     даже
    0.28
    when
    0.27
    Act Density 0.144%

    No Known Activations