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

    Neuronpedia

    INDEX
    Explanations

    references to investigative reporting and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.17
    acci
    -0.15
    QA
    -0.15
    üt
    -0.14
    oupon
    -0.14
    vä
    -0.14
    dG
    -0.14
    raman
    -0.13
    nets
    -0.13
    HeaderValue
    -0.13
    POSITIVE LOGITS
     Reporting
    0.24
    Reporting
    0.23
     reporting
    0.23
     stories
    0.20
     reporters
    0.18
     reporter
    0.18
     VERIFY
    0.17
    844
    0.17
     bure
    0.17
     investigative
    0.17
    Act Density 0.126%

    No Known Activations