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

    Neuronpedia

    INDEX
    Explanations

    references to speeches and public speaking events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.46
    IntoConstraints
    -0.45
    EndInit
    -0.44
    клопе
    -0.35
     Afghans
    -0.31
     SafeMath
    -0.31
    ंदीखरीदारी
    -0.31
     cats
    -0.30
     ब्रेकडाउन
    -0.30
     ویکی‌پدی
    -0.30
    POSITIVE LOGITS
     speech
    1.12
     lecture
    1.09
     speeches
    1.00
     lectures
    0.98
     Speech
    0.97
    Speech
    0.96
     oration
    0.94
     Vortrag
    0.93
     sermon
    0.91
     Speeches
    0.90
    Act Density 0.296%

    No Known Activations