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

    Neuronpedia

    INDEX
    Explanations

    strong emotional expressions and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     distribut
    -0.78
     pocket
    -0.77
     intended
    -0.77
     detailed
    -0.76
     submerged
    -0.75
    ascus
    -0.74
     broadly
    -0.74
     carbohyd
    -0.72
     inaccur
    -0.72
     commonly
    -0.72
    POSITIVE LOGITS
     Especially
    1.69
     Otherwise
    1.59
     And
    1.57
     But
    1.53
     Maybe
    1.50
     That
    1.50
     Anyway
    1.47
     Whoever
    1.47
     Because
    1.47
     Sometimes
    1.46
    Act Density 2.244%

    No Known Activations