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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting in text

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

    "Thanks" or greetings at the end of answers

    np_acts-logits-general · gemini-2.0-flash

    polite greetings and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.64
    Jvm
    -0.49
     Whig
    -0.47
    bacillus
    -0.47
     getopt
    -0.47
    いかに
    -0.47
    IANGLES
    -0.47
     بيها
    -0.46
     outta
    -0.45
    ineo
    -0.45
    POSITIVE LOGITS
    Hi
    1.69
     Hi
    1.66
    Hello
    1.62
     Hello
    1.61
     hello
    1.28
    Dear
    1.27
     hi
    1.24
    您好
    1.17
    hello
    1.15
     Dear
    1.15
    Act Density 0.553%

    No Known Activations