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

    Neuronpedia

    INDEX
    Explanations

    strong negative financial terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Butterfly
    -0.78
    è¦ļéĨĴ
    -0.77
     oun
    -0.65
    hift
    -0.64
    eele
    -0.64
    20439
    -0.64
     deviations
    -0.63
    avorite
    -0.62
     illusions
    -0.62
     enthus
    -0.62
    POSITIVE LOGITS
    utions
    1.18
    utable
    1.15
    uting
    1.08
    mented
    1.06
    vent
    1.04
    vable
    1.00
    ptions
    0.99
    uted
    0.99
    ments
    0.98
    untary
    0.98
    Act Density 0.053%

    No Known Activations