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

    Neuronpedia

    INDEX
    Explanations

    references to wasting time and money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    subclass
    -0.16
    zo
    -0.15
    otti
    -0.15
    reesome
    -0.14
     Äijá»Ļ
    -0.14
    defgroup
    -0.13
    浦
    -0.13
    080
    -0.13
    tell
    -0.13
    fty
    -0.13
    POSITIVE LOGITS
    aken
    0.18
    æİī
    0.17
    gate
    0.16
    guard
    0.15
    ECTOR
    0.15
    fully
    0.14
    _ARB
    0.14
    anka
    0.14
    éĴ±
    0.14
    è¾
    0.14
    Act Density 0.027%

    No Known Activations