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

    Neuronpedia

    INDEX
    Explanations

    mention of specific organizations or groups in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political factions or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Piercing
    -0.71
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    使
    -0.70
    ãĤ´ãĥ³
    -0.69
     Incarn
    -0.68
     Archangel
    -0.66
     Wonderland
    -0.63
     Parkinson
    -0.63
     Penet
    -0.63
     Minotaur
    -0.62
    POSITIVE LOGITS
    serv
    0.90
    eni
    0.88
    accompan
    0.87
    oons
    0.83
    ilitation
    0.82
    ilit
    0.82
    oon
    0.82
    allowed
    0.82
    vous
    0.81
     unden
    0.80
    Act Density 0.019%

    No Known Activations