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

    Neuronpedia

    INDEX
    Explanations

    question formats and affirmations

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

    Followed by "yes" as an affirmation

    np_acts-logits-general · gemini-2.0-flash

    affirmation or agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apore
    -0.49
    ınca
    -0.46
    onto
    -0.46
    azzi
    -0.46
    Abitanti
    -0.46
     Bourgoin
    -0.46
    ütün
    -0.46
    ardians
    -0.45
    anía
    -0.45
    arate
    -0.44
    POSITIVE LOGITS
     yes
    3.87
     Yes
    3.40
    Yes
    3.28
    yes
    3.17
     YES
    3.00
    YES
    2.69
     yeah
    2.37
     yep
    2.13
     Yeah
    2.06
     Yep
    2.02
    Act Density 0.517%

    No Known Activations