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

    Neuronpedia

    INDEX
    Explanations

    greetings and conversational prompts

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

    Greetings or saying "hello" in different languages

    np_acts-logits-general · gemini-2.0-flash

    hello, hi, salut

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MORE
    -0.39
     though
    -0.37
     nạn
    -0.36
    却
    -0.35
     unique
    -0.35
    卻
    -0.35
    bson
    -0.35
     точно
    -0.34
    难怪
    -0.34
     yet
    -0.34
    POSITIVE LOGITS
     hello
    2.20
     Hello
    2.10
    Hello
    1.98
    hello
    1.77
     HELLO
    1.68
     Greetings
    1.64
    HELLO
    1.60
     Hi
    1.59
    Hi
    1.59
     hi
    1.56
    Act Density 0.198%

    No Known Activations