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

    Neuronpedia

    INDEX
    Explanations

    significant numerical values and references in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ackets
    -0.16
    ries
    -0.15
     Lo
    -0.15
    .bz
    -0.14
    icro
    -0.14
    ningen
    -0.14
    least
    -0.14
    éº
    -0.14
     Makeup
    -0.14
     Freed
    -0.14
    POSITIVE LOGITS
    962
    0.17
    ále
    0.16
    ละ
    0.16
    ssi
    0.16
    亮
    0.15
    olie
    0.15
    omin
    0.15
    æ±
    0.15
    itta
    0.14
    ãĤ¹ãĥŀ
    0.14
    Act Density 0.001%

    No Known Activations