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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional expressiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виÑıв
    -0.24
     елекÑĤÑĢон
    -0.23
    надлеж
    -0.22
     звиÑĩай
    -0.20
     Îijθήνα
    -0.20
     УкÑĢаÑĹна
    -0.20
     Îķλλάδα
    -0.19
     елек
    -0.19
     мÑĸÑģÑĤо
    -0.19
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.18
    POSITIVE LOGITS
     ÑįÑĤого
    0.31
     Ñģамого
    0.31
     Ñģвоего
    0.30
     ÑĤого
    0.29
     нового
    0.29
     одного
    0.29
     пеÑĢвого
    0.28
     бÑĥма
    0.28
     ÑįÑĤиÑħ
    0.28
     каждого
    0.28
    Act Density 0.071%

    No Known Activations