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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jelent
    -0.61
     ngoại
    -0.51
     \%)$
    -0.50
     ges
    -0.50
     смо
    -0.50
    %;
    -0.50
    Zir
    -0.50
    的有
    -0.49
     Furn
    -0.49
     xuất
    -0.49
    POSITIVE LOGITS
     صوتيه
    0.98
     boo
    0.94
    supposed
    0.82
    Boo
    0.79
    boo
    0.77
     تانيه
    0.74
     supuestamente
    0.70
     Boo
    0.70
     supposed
    0.70
    parsedMessage
    0.68
    Act Density 0.124%

    No Known Activations