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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technological advancements or updates

    oai_token-act-pair · gpt-3.5-turbo

    instances of "up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ________________________
    -0.70
    ¯¯¯¯
    -0.67
    9999
    -0.66
    ====
    -0.66
    gee
    -0.64
    士
    -0.61
     CLSID
    -0.61
    999
    -0.60
    ¯¯¯¯¯¯¯¯
    -0.60
    Maker
    -0.59
    POSITIVE LOGITS
    stairs
    1.26
    graded
    1.23
    grading
    1.19
    dating
    1.18
    grades
    1.17
    dates
    1.16
    river
    0.99
    raised
    0.93
    skirts
    0.90
    ended
    0.88
    Act Density 0.064%

    No Known Activations