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

    Neuronpedia

    INDEX
    Explanations

    common conversational words and indicators of user engagement

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

    "chatbot robot automated bots"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.49
     posted
    -0.47
     AssemblyTitle
    -0.45
     published
    -0.44
     tweeted
    -0.43
     Betracht
    -0.41
     Posted
    -0.40
    posted
    -0.40
    published
    -0.38
     numerous
    -0.37
    POSITIVE LOGITS
     chatbot
    0.58
     Савезне
    0.54
     robot
    0.52
    pushFollow
    0.52
     sorry
    0.51
    Diweddarwch
    0.50
     automated
    0.50
     Sorry
    0.50
     bots
    0.49
     please
    0.49
    Act Density 0.136%

    No Known Activations