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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    expressions of thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.88
     Italijani
    -0.85
     betweenstory
    -0.84
     Италијани
    -0.82
    fromnode
    -0.81
    UserScript
    -0.78
     Мексичка
    -0.78
    +#+
    -0.75
    :✨
    -0.74
    postsleuth
    -0.70
    POSITIVE LOGITS
    Cordialement
    0.55
     thank
    0.41
     Bitte
    0.40
     Thank
    0.40
    Thank
    0.40
     Thanks
    0.40
     thanks
    0.39
     cortesía
    0.37
     Please
    0.36
    Thanks
    0.36
    Act Density 0.008%

    No Known Activations