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

    Neuronpedia

    INDEX
    Explanations

    references to collections of documents and manuscripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goods
    -0.17
    ethe
    -0.15
    istrib
    -0.15
     tend
    -0.15
    ici
    -0.14
    ilate
    -0.14
    etten
    -0.14
     corner
    -0.14
    .alloc
    -0.14
     relay
    -0.13
    POSITIVE LOGITS
     papers
    0.20
    (Box
    0.19
     Papers
    0.19
     Correspond
    0.19
    finding
    0.18
    Finding
    0.18
     Boxes
    0.17
     Finding
    0.17
     finding
    0.17
    [item
    0.17
    Act Density 0.013%

    No Known Activations