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

    Neuronpedia

    INDEX
    Explanations

    sections discussing a project's progress and evaluations, particularly in the context of a report or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bonus
    -0.15
    ä»Ķ
    -0.15
     Bonus
    -0.14
    pez
    -0.14
    å±Ĭ
    -0.14
    ropol
    -0.14
     Manuals
    -0.13
     illustrations
    -0.13
    ongo
    -0.13
    stre
    -0.13
    POSITIVE LOGITS
     summary
    0.40
    summary
    0.38
     Summary
    0.34
    -summary
    0.34
    Summary
    0.34
     summ
    0.33
    _summary
    0.33
     briefly
    0.33
    .summary
    0.33
     SUMMARY
    0.32
    Act Density 0.237%

    No Known Activations