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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and research-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Books
    -0.15
     Newsp
    -0.15
    agn
    -0.15
    alyzer
    -0.15
    Books
    -0.14
    Æ°
    -0.13
    NCY
    -0.13
    ysa
    -0.13
    orama
    -0.13
    417
    -0.12
    POSITIVE LOGITS
     paper
    0.42
     article
    0.33
    paper
    0.30
     work
    0.30
     note
    0.27
    -paper
    0.27
     talk
    0.27
     contribution
    0.26
     Letter
    0.26
    article
    0.25
    Act Density 0.061%

    No Known Activations