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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human values and socio-political commentary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.74
    Recommend
    -0.65
    ENE
    -0.63
    ãĤ´ãĥ³
    -0.61
    quickShipAvailable
    -0.60
    HY
    -0.56
    é¾įåĸļ士
    -0.55
    RESULTS
    -0.54
    ]).
    -0.54
    QUIRE
    -0.54
    POSITIVE LOGITS
     wars
    0.52
     or
    0.51
    urches
    0.51
     bombed
    0.51
     factories
    0.50
     revolutions
    0.48
     sweats
    0.48
     famine
    0.48
     roaring
    0.46
    illions
    0.46
    Act Density 1.571%

    No Known Activations