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

    Neuronpedia

    INDEX
    Explanations

    references to issues or articles from academic or formal publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³
    -0.21
     ä¸ī
    -0.20
    ä¸ī
    -0.20
     thirds
    -0.20
    âĤĥ
    -0.19
    Û³
    -0.19
    ä¸īå¹´
    -0.19
     Third
    -0.19
    three
    -0.18
     THIRD
    -0.18
    POSITIVE LOGITS
    1
    0.33
    ï¼ij
    0.24
    01
    0.19
    Û±
    0.18
     January
    0.18
     第ä¸Ģ
    0.18
     birinci
    0.17
    第ä¸Ģ
    0.17
     Jan
    0.17
    第ä¸Ģ次
    0.17
    Act Density 0.028%

    No Known Activations