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

    Neuronpedia

    INDEX
    Explanations

    programming keywords that indicate the inclusion of libraries or modules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zed
    -0.16
    bu
    -0.16
    ounty
    -0.14
     incom
    -0.14
    ody
    -0.14
    AKE
    -0.14
    oure
    -0.13
    беÑĢ
    -0.13
     Sawyer
    -0.13
    inosaur
    -0.13
    POSITIVE LOGITS
    ãģĿãĤĮãģ¯
    0.17
    ÏĥÏĦο
    0.14
    CACHE
    0.14
     Tiles
    0.14
    slaught
    0.14
    826
    0.14
    andre
    0.13
    æī¶
    0.13
     Monter
    0.13
     Σε
    0.13
    Act Density 0.001%

    No Known Activations