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

    Neuronpedia

    INDEX
    Explanations

    references to specific book publishers

    oai_token-act-pair · gpt-3.5-turbo

    references to publishing companies and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.80
    ornia
    -0.76
    eteria
    -0.66
    ĸļ
    -0.66
    jriwal
    -0.63
    ournals
    -0.62
    anty
    -0.62
    ujah
    -0.59
    DIR
    -0.59
    lished
    -0.58
    POSITIVE LOGITS
     Diesel
    0.70
     metic
    0.69
     XL
    0.65
    ר
    0.65
    achev
    0.65
    kov
    0.64
    manship
    0.64
    etric
    0.63
    terness
    0.62
     Boxing
    0.62
    Act Density 0.311%

    No Known Activations