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

    Neuronpedia

    INDEX
    Explanations

    concessive phrases that indicate contradictions or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    despite and notwithstanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.49
    omalainen
    -0.43
    inaire
    -0.40
     GenerationType
    -0.39
     dopln
    -0.39
    istry
    -0.39
     accesibles
    -0.38
     safer
    -0.38
    illoin
    -0.38
    ждествен
    -0.37
    POSITIVE LOGITS
     despite
    0.89
    despite
    0.85
     Despite
    0.83
    Despite
    0.77
     Malgré
    0.72
     trotz
    0.72
    尽管
    0.70
     несмотря
    0.69
     malgré
    0.69
     nonostante
    0.69
    Act Density 0.196%

    No Known Activations