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

    Neuronpedia

    INDEX
    Explanations

    function calls and parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lodge
    -0.18
    ombine
    -0.18
    edback
    -0.16
    ognito
    -0.15
    ringe
    -0.15
    zon
    -0.15
    culo
    -0.15
    etcode
    -0.14
     conqu
    -0.14
    æĥij
    -0.14
    POSITIVE LOGITS
    retch
    0.18
    ãĥ¼ãĥ©
    0.14
     Marc
    0.13
    éĥİ
    0.13
    iterr
    0.13
    rollo
    0.13
     ext
    0.13
     Ne
    0.13
     cas
    0.13
    iginal
    0.13
    Act Density 0.085%

    No Known Activations