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

    Neuronpedia

    INDEX
    Explanations

    references to version control actions related to Git commits

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Havolalar
    -0.69
     Zar
    -0.68
     Lorenz
    -0.66
     Dara
    -0.65
    Hauptartikel
    -0.64
    Zar
    -0.63
     Nade
    -0.63
    فار
    -0.62
     Esau
    -0.60
    RAD
    -0.57
    POSITIVE LOGITS
     Commit
    1.38
     commit
    1.26
     COMMIT
    1.23
    commit
    1.20
     commits
    1.20
    Commit
    1.19
    commits
    1.12
     committed
    1.09
     committing
    1.08
     Committed
    0.96
    Act Density 0.003%

    No Known Activations