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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

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

    gratitude and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BytesLike
    -0.39
    layah
    -0.38
    trät
    -0.36
    férences
    -0.35
     therewith
    -0.34
    imshow
    -0.34
     ActionListener
    -0.34
    dollis
    -0.33
     autorytatywna
    -0.33
     exerci
    -0.33
    POSITIVE LOGITS
     Kudos
    0.65
     agradecimiento
    0.63
    Shout
    0.63
    MemoryWarning
    0.62
    Kudos
    0.61
     Shout
    0.57
    httphttps
    0.56
     kudos
    0.56
     Gratitude
    0.53
     remercie
    0.52
    Act Density 0.010%

    No Known Activations