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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.02
    niſſe
    -0.84
     ſind
    -0.80
    parsedMessage
    -0.79
     iſt
    -0.77
    iſchen
    -0.76
     صوتيه
    -0.76
    ロウィン
    -0.75
    ſehen
    -0.75
    Personendaten
    -0.75
    POSITIVE LOGITS
     מל
    0.52
     כש
    0.50
     וב
    0.49
    </table>
    0.49
     وك
    0.48
     وال
    0.48
     כשה
    0.47
     שה
    0.43
     וה
    0.42
    ømme
    0.42
    Act Density 1.794%

    No Known Activations