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

    Neuronpedia

    INDEX
    Explanations

    references to statistical evaluation methods and metrics in a computational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geh
    -0.16
    dek
    -0.16
    gambar
    -0.16
    abeth
    -0.16
    ynet
    -0.15
    otti
    -0.15
    ẹp
    -0.15
    canf
    -0.14
     gag
    -0.14
     Chandler
    -0.14
    POSITIVE LOGITS
     Lear
    0.19
     learner
    0.19
     mah
    0.18
     Mah
    0.18
     learners
    0.17
     Fraud
    0.16
     learning
    0.15
     kla
    0.15
    learner
    0.15
    learn
    0.15
    Act Density 0.071%

    No Known Activations