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

    Neuronpedia

    INDEX
    Explanations

    elements related to progress and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restored
    -0.15
     devis
    -0.15
    .partial
    -0.14
    kup
    -0.14
    .createNew
    -0.13
    _restore
    -0.13
     yap
    -0.13
    è³Ģ
    -0.13
    foon
    -0.13
    ÑĤап
    -0.13
    POSITIVE LOGITS
     fine
    0.54
     hon
    0.48
    fine
    0.47
     Fine
    0.45
    Fine
    0.43
     iron
    0.39
     refine
    0.38
     refinement
    0.38
     polish
    0.34
     fines
    0.33
    Act Density 0.329%

    No Known Activations