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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparison and evaluation of quantities or qualities

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

    much less, whether, especially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconvénients
    -0.43
     julk
    -0.43
    ßerdem
    -0.43
    WebpackPlugin
    -0.42
     iNdEx
    -0.41
    magitan
    -0.40
    PullParser
    -0.38
     aikaa
    -0.38
    closedir
    -0.37
    epresidente
    -0.37
    POSITIVE LOGITS
     including
    0.65
    尤其是
    0.56
     especially
    0.53
     whether
    0.53
    包括
    0.52
    even
    0.52
     regardless
    0.52
     بوی
    0.52
     Including
    0.51
    including
    0.51
    Act Density 0.137%

    No Known Activations