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

    Neuronpedia

    INDEX
    Explanations

    references to political advocacy and opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     colony
    -0.15
    peek
    -0.15
     Colony
    -0.15
    ula
    -0.14
     taraf
    -0.14
     narc
    -0.14
    571
    -0.14
     nom
    -0.13
    andr
    -0.13
    apes
    -0.13
    POSITIVE LOGITS
     ITE
    0.15
     Ä°l
    0.14
    sville
    0.14
    aits
    0.14
    ÑĢай
    0.14
    ëĭ¨ì²´
    0.14
    :index
    0.13
    urum
    0.13
     losses
    0.13
     Pitch
    0.13
    Act Density 0.224%

    No Known Activations