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 gratitude and appreciation

    np_acts-logits-general · gemini-2.0-flash

    expressions of thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.50
     noDo
    -0.48
    Personendaten
    -0.36
     تضيفلها
    -0.35
     Vikipedi
    -0.35
    WriteTagHelper
    -0.34
    "}")
    -0.33
    ❉
    -0.33
    ")));
    -0.32
    DataAnnotations
    -0.31
    POSITIVE LOGITS
    Thanks
    0.52
     Thank
    0.52
    Thank
    0.52
     Thanks
    0.51
    Appreciate
    0.50
    thank
    0.50
     teşekkür
    0.49
     Gracias
    0.49
     mengg
    0.49
    findpost
    0.48
    Act Density 0.410%

    No Known Activations