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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of knowledge or involvement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the phrase "haven't" indicating regret or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rall
    -0.75
    çīĪ
    -0.72
     Lynd
    -0.70
    åħī
    -0.68
    soDeliveryDate
    -0.66
     prone
    -0.64
     Kerr
    -0.64
     unworthy
    -0.63
     Swordsman
    -0.63
    nels
    -0.61
    POSITIVE LOGITS
    been
    1.06
    Constructed
    0.83
    gotten
    0.80
    since
    0.75
     been
    0.72
    gui
    0.72
    ĵĺ
    0.70
     âĢº
    0.68
     Entered
    0.67
    ework
    0.67
    Act Density 0.074%

    No Known Activations