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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or frustration related to social interactions and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MMV
    -0.63
    iestety
    -0.62
    eraard
    -0.56
    =$?
    -0.56
    Kelebihan
    -0.56
     بيها
    -0.54
     الدولى
    -0.52
    raisemb
    -0.52
    doPost
    -0.51
    respectively
    -0.51
    POSITIVE LOGITS
     such
    2.40
    such
    1.99
     столь
    1.93
    Such
    1.89
     tão
    1.88
    如此
    1.84
     Such
    1.80
    這麼
    1.77
     SUCH
    1.76
     così
    1.75
    Act Density 0.659%

    No Known Activations