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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their related frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -Y
    -0.14
     conj
    -0.14
    Ø«ÛĮر
    -0.14
    æľ¯
    -0.13
    auce
    -0.13
    469
    -0.13
    pring
    -0.13
    ,Integer
    -0.13
    ůst
    -0.13
     Care
    -0.13
    POSITIVE LOGITS
    ipop
    0.17
    ãĥ¬ãĥ¼
    0.17
    868
    0.17
    UGH
    0.15
    ines
    0.15
    CJK
    0.15
    vise
    0.14
    alg
    0.14
    âĹİ
    0.14
     tre
    0.14
    Act Density 0.004%

    No Known Activations