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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Courtesy
    -0.16
     ActionTypes
    -0.16
    FIXME
    -0.14
    noinspection
    -0.14
    OLEAN
    -0.14
    ìĿ´ëĵľ
    -0.14
    ional
    -0.13
    à¸ŀล
    -0.13
     Courtesy
    -0.13
    ughs
    -0.13
    POSITIVE LOGITS
     Hi
    0.33
    Hi
    0.30
     hi
    0.30
     Hello
    0.29
     hello
    0.28
    hi
    0.28
    Hello
    0.27
    HI
    0.26
    hello
    0.24
     HI
    0.24
    Act Density 0.169%

    No Known Activations