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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "halving" or variations of the word

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "hal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.86
    æĸ¹
    -0.83
    enegger
    -0.80
    Library
    -0.78
    ãģķ
    -0.78
    URES
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.77
    ULTS
    -0.76
    ierrez
    -0.76
    URE
    -0.73
    POSITIVE LOGITS
    tering
    1.07
    ving
    1.07
    ved
    0.98
    ter
    0.98
    ifax
    0.97
    tered
    0.95
    ftime
    0.93
    ogen
    0.89
    ashed
    0.85
    ting
    0.85
    Act Density 0.014%

    No Known Activations