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

    Neuronpedia

    INDEX
    Explanations

    terms related to accusations and their prevalence in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icip
    -0.16
    TEM
    -0.14
    aise
    -0.14
    _expect
    -0.14
    lag
    -0.14
    folk
    -0.14
    duk
    -0.14
    à¹ģà¸ģ
    -0.14
    aż
    -0.14
     Parkway
    -0.14
    POSITIVE LOGITS
    lys
    0.20
    noop
    0.16
    atively
    0.15
    æı®
    0.14
     errorCallback
    0.14
     Inner
    0.14
     sắc
    0.14
    imar
    0.14
    Ïģαβ
    0.14
    une
    0.14
    Act Density 0.007%

    No Known Activations