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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "hello."

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

    hello, hello world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.58
     Chwiliwch
    -0.54
     дописавши
    -0.48
    Parcelize
    -0.45
    存于互联网档案馆
    -0.43
     raiſ
    -0.42
    apore
    -0.42
    tisgarh
    -0.41
     leſs
    -0.41
     BoxFit
    -0.41
    POSITIVE LOGITS
     Hello
    1.61
     hello
    1.49
    Hello
    1.48
    hello
    1.30
     HelloWorld
    1.28
     HELLO
    1.24
    HELLO
    1.23
    HelloWorld
    1.08
    Greeting
    1.00
    helloworld
    0.95
    Act Density 0.005%

    No Known Activations