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

    Neuronpedia

    INDEX
    Explanations

    salutations or greetings, particularly variations of "Hello"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "Hello" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aic
    -0.92
    arian
    -0.83
    ipl
    -0.81
    icum
    -0.79
    eele
    -0.77
    iculture
    -0.75
    hip
    -0.74
    arians
    -0.74
    ifiable
    -0.74
    pite
    -0.73
    POSITIVE LOGITS
     Kitty
    1.10
     hello
    0.87
    !.
    0.82
     Neighbor
    0.81
    !
    0.76
    ãĥ¼ãĥ«
    0.76
     Hello
    0.75
     Goodbye
    0.75
    !".
    0.74
    !,
    0.74
    Act Density 0.030%

    No Known Activations