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

    Neuronpedia

    INDEX
    Explanations

    specific groups or entities mentioned within larger contexts

    oai_token-act-pair · gpt-3.5-turbo

    nouns that refer to groups of people or subjects being mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.81
    DragonMagazine
    -0.74
    uyomi
    -0.71
    ãĥĥ
    -0.67
    ãĤ´ãĥ³
    -0.66
    tainment
    -0.65
    rontal
    -0.63
    ãĥ¯
    -0.63
    æĪ¦
    -0.61
     sqor
    -0.61
    POSITIVE LOGITS
     lacked
    0.82
     behaved
    0.82
     weren
    0.78
     below
    0.78
     didn
    0.78
     seemed
    0.74
     tasted
    0.74
     hadn
    0.73
     smelled
    0.72
     wore
    0.72
    Act Density 0.419%

    No Known Activations