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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote a ranking or ordinal position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.18
    usercontent
    -0.15
    _ASSUME
    -0.15
    thane
    -0.14
    rå
    -0.14
    enate
    -0.14
    lical
    -0.13
    kal
    -0.13
    older
    -0.13
     fac
    -0.13
    POSITIVE LOGITS
    s
    0.26
     tiên
    0.20
     timers
    0.19
    -ever
    0.19
    born
    0.19
    -hand
    0.17
    arily
    0.17
    ald
    0.16
    sand
    0.16
    urdy
    0.15
    Act Density 0.111%

    No Known Activations