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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific scientific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ない
    -0.88
    nya
    -0.84
     său
    -0.76
    ness
    -0.59
    liśmy
    -0.59
     nostru
    -0.59
    นั้น
    -0.59
    ling
    -0.58
    ned
    -0.57
    น
    -0.57
    POSITIVE LOGITS
    aaaa
    0.70
    e
    0.68
    aaa
    0.66
    aaaaaaaa
    0.66
    اااا
    0.62
    aaaaaa
    0.61
    aaaaa
    0.58
    a
    0.56
    aa
    0.56
    eins
    0.55
    Act Density 1.227%

    No Known Activations