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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and arguments related to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.16
    à¤Łà¤ķ
    -0.14
    oppable
    -0.14
    esome
    -0.14
    Ø´Ùĩ
    -0.14
    typings
    -0.14
    drs
    -0.14
    ãģ«éĸ¢ãģĻãĤĭ
    -0.13
    _DIGEST
    -0.13
    ä½IJ
    -0.13
    POSITIVE LOGITS
     too
    0.22
     TOO
    0.19
    too
    0.18
     Too
    0.18
     since
    0.18
    Too
    0.16
     simply
    0.16
     ought
    0.15
    太
    0.15
     should
    0.15
    Act Density 0.111%

    No Known Activations