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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing strong opinions or reactions, often involving praise or criticism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.77
    ilight
    -0.72
    grounds
    -0.71
     existed
    -0.70
    adj
    -0.69
    estate
    -0.68
     with
    -0.67
     Laboratories
    -0.67
    eworks
    -0.64
    there
    -0.62
    POSITIVE LOGITS
     bang
    1.11
     vengeance
    1.04
     impunity
    0.97
     newfound
    0.97
     dignity
    0.88
     vig
    0.87
     flourish
    0.87
     gust
    0.85
     limp
    0.85
     suitcase
    0.84
    Act Density 0.242%

    No Known Activations