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

    Neuronpedia

    INDEX
    Explanations

    references to community and public statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Woodward
    -0.16
    Reviewer
    -0.16
    wap
    -0.13
    ãģŀ
    -0.13
     Shed
    -0.13
    ferences
    -0.13
    DUCT
    -0.13
     Reporting
    -0.13
    iesen
    -0.13
    kinson
    -0.13
    POSITIVE LOGITS
     statement
    0.44
     press
    0.35
     release
    0.33
    statement
    0.33
     prepared
    0.28
     Statement
    0.27
    release
    0.27
    Statement
    0.27
     stat
    0.26
    press
    0.25
    Act Density 0.056%

    No Known Activations