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

    Neuronpedia

    INDEX
    Explanations

    marketing and sales-related terms, especially in the context of promotional events like Black Friday

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cannot
    -0.23
     neither
    -0.23
    cannot
    -0.20
    ANNOT
    -0.19
     rất
    -0.18
     nobody
    -0.17
     Neither
    -0.17
    éĿŀ常
    -0.17
    ALSE
    -0.17
    alse
    -0.17
    POSITIVE LOGITS
     ever
    0.51
     EVER
    0.40
     Ever
    0.35
    ever
    0.33
     really
    0.33
     REALLY
    0.31
     still
    0.31
    -ever
    0.31
     Really
    0.30
     вообÑīе
    0.28
    Act Density 0.366%

    No Known Activations