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

    Neuronpedia

    INDEX
    Explanations

    statements advocating for political or social change

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocracy
    -0.68
     ILCS
    -0.64
    ioxide
    -0.62
     Camel
    -0.61
    lua
    -0.60
    #$
    -0.60
     Sheen
    -0.60
    RO
    -0.59
    alion
    -0.58
    RF
    -0.58
    POSITIVE LOGITS
    etheless
    0.92
     editions
    0.91
     generations
    0.89
     incarn
    0.88
     eras
    0.87
    itiz
    0.83
     versions
    0.81
     iterations
    0.78
    ebin
    0.78
    cies
    0.76
    Act Density 0.379%

    No Known Activations