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

    Neuronpedia

    INDEX
    Explanations

    phrases related to findings and data presentation in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trains
    -0.49
     CSRF
    -0.43
    Abp
    -0.43
    !(:
    -0.42
    cartItems
    -0.41
    pegno
    -0.40
     diatur
    -0.40
     zasady
    -0.40
    在外
    -0.40
    思
    -0.40
    POSITIVE LOGITS
    twimg
    0.85
     report
    0.74
     отчет
    0.72
     summarizing
    0.70
     results
    0.69
     Reports
    0.67
    report
    0.67
    results
    0.66
     Reporting
    0.66
     reports
    0.65
    Act Density 0.878%

    No Known Activations