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

    Neuronpedia

    INDEX
    Explanations

    affirmations and acknowledgments in conversation

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

    yes, wait, private, ok

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.62
     estekak
    -0.61
    httphttps
    -0.56
     beginnetje
    -0.50
    MessageOf
    -0.46
    الحياه
    -0.46
    tanleria
    -0.46
     cherchés
    -0.45
     للاسماء
    -0.45
    ETHING
    -0.43
    POSITIVE LOGITS
     yes
    0.85
     yeah
    0.84
     Yes
    0.70
     YES
    0.68
     yep
    0.66
     YEAH
    0.63
     Yep
    0.60
     yea
    0.60
     Yeah
    0.60
    yeah
    0.60
    Act Density 0.002%

    No Known Activations