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

    Neuronpedia

    INDEX
    Explanations

    phrases related to challenges and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĮ
    -0.17
    urls
    -0.15
    ud
    -0.14
     blacklist
    -0.14
    itch
    -0.14
    Äįná
    -0.14
    irk
    -0.14
     Setup
    -0.14
    ur
    -0.13
    ut
    -0.13
    POSITIVE LOGITS
    illery
    0.19
    vetica
    0.17
    /down
    0.17
     Bid
    0.17
     bid
    0.16
    TestFixture
    0.15
    Unnamed
    0.15
    Bid
    0.15
    upos
    0.15
    elsen
    0.15
    Act Density 0.049%

    No Known Activations