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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to actions or concepts of judgment, decision-making, or criticism

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ges" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.65
     anten
    -0.63
     LIFE
    -0.62
    kefeller
    -0.60
     Jordanian
    -0.59
     unnecess
    -0.58
     aim
    -0.57
    ãģĤ
    -0.57
    INC
    -0.56
     nodd
    -0.56
    POSITIVE LOGITS
    ges
    1.23
    enary
    0.91
    hog
    0.87
    ury
    0.77
    arthed
    0.76
    ertodd
    0.76
    orge
    0.75
    imore
    0.75
    rows
    0.75
    eper
    0.74
    Act Density 0.009%

    No Known Activations