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

    Neuronpedia

    INDEX
    Explanations

    numerical statistics related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.17
    issance
    -0.15
    elon
    -0.15
    JD
    -0.15
    loan
    -0.15
     ELSE
    -0.14
    ãĤ¤ãĥī
    -0.14
    zimmer
    -0.14
    porter
    -0.14
     newcom
    -0.14
    POSITIVE LOGITS
    125
    0.22
    875
    0.22
    625
    0.21
    375
    0.19
     Mast
    0.15
    250
    0.15
    937
    0.14
     nomin
    0.14
    750
    0.14
    æĪ
    0.14
    Act Density 0.066%

    No Known Activations