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

    Neuronpedia

    INDEX
    Explanations

    statistical measurements and references to research methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predicting
    -0.19
     predicts
    -0.19
    ouro
    -0.17
     predictive
    -0.17
    eurs
    -0.15
    predicted
    -0.15
     predictions
    -0.15
     Flake
    -0.15
    िà¤Ń
    -0.15
     probabil
    -0.15
    POSITIVE LOGITS
     Stat
    0.23
    iid
    0.20
    Stat
    0.20
    stat
    0.19
     statist
    0.19
     Rubin
    0.19
    .Stat
    0.18
     Econ
    0.17
    MLE
    0.17
    Statistic
    0.16
    Act Density 0.127%

    No Known Activations