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

    Neuronpedia

    INDEX
    Explanations

    emotional states related to dissatisfaction or disappointment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    opus
    -0.68
    onut
    -0.66
    umn
    -0.65
    icrobial
    -0.64
    RN
    -0.63
    fman
    -0.61
    skirts
    -0.61
    origin
    -0.60
    ahead
    -0.59
    zyme
    -0.59
    POSITIVE LOGITS
    actory
    0.98
    ments
    0.91
    ment
    0.83
    mented
    0.81
    iated
    0.76
    imaru
    0.73
     Satisf
    0.72
     disappointed
    0.72
    ienced
    0.71
    MENTS
    0.70
    Act Density 0.114%

    No Known Activations