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

    Neuronpedia

    INDEX
    Explanations

    references to specific systems and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neither
    -0.28
     Neither
    -0.22
     cannot
    -0.22
    Neither
    -0.20
     rất
    -0.20
    éĿŀ常
    -0.19
     nobody
    -0.19
     nowhere
    -0.19
    ä¸įäºĨ
    -0.19
     ìĹĨìĿĮ
    -0.19
    POSITIVE LOGITS
     ever
    0.43
     any
    0.39
     EVER
    0.35
     anymore
    0.33
     really
    0.33
     still
    0.31
     REALLY
    0.31
     vůbec
    0.30
    any
    0.29
     Really
    0.28
    Act Density 0.319%

    No Known Activations