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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or acknowledgment

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

    thanks to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ganzes
    -0.36
     mittlere
    -0.36
     beginnetje
    -0.35
    Hochspringen
    -0.35
     yapmak
    -0.35
     pojed
    -0.35
     residencial
    -0.34
     käyt
    -0.34
     would
    -0.34
    Trả
    -0.34
    POSITIVE LOGITS
     благодаря
    1.00
    Благодаря
    0.94
    thanks
    0.90
     grâce
    0.89
     thanks
    0.88
     graças
    0.88
     grazie
    0.86
    ďaka
    0.85
     dzięki
    0.85
     díky
    0.85
    Act Density 0.008%

    No Known Activations