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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and published research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kys
    -0.17
    .ru
    -0.15
    ossa
    -0.15
    Copyright
    -0.14
     surre
    -0.14
    .alloc
    -0.13
    æ´¥
    -0.13
     manuals
    -0.13
    innie
    -0.13
    ours
    -0.12
    POSITIVE LOGITS
     journal
    0.33
     journals
    0.28
     paper
    0.24
     peer
    0.23
     Journal
    0.23
     published
    0.22
     papers
    0.22
     jour
    0.20
    .published
    0.20
    ëħ¼
    0.20
    Act Density 0.044%

    No Known Activations