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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

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

    thanks, gracias, graças

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    -0.42
     and
    -0.35
     particle
    -0.35
    mtd
    -0.34
    listItem
    -0.34
    viewmodel
    -0.34
     company
    -0.33
     pleaſure
    -0.33
     aeron
    -0.33
     sacerd
    -0.32
    POSITIVE LOGITS
     graças
    1.05
     thanks
    1.03
    âce
    0.95
     THANKS
    0.91
     grâce
    0.91
     nahilalakip
    0.91
    thanks
    0.90
    gracias
    0.90
     autorytatywna
    0.87
     gracias
    0.87
    Act Density 0.006%

    No Known Activations