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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases relating to legal issues, particularly defamation and civil rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CodeGen
    -0.07
    erah
    -0.07
    phen
    -0.07
    ighet
    -0.07
    ائÙĩ
    -0.06
    ادÙĩ
    -0.06
    izi
    -0.06
    罪
    -0.06
    á»ĩu
    -0.06
    /gui
    -0.06
    POSITIVE LOGITS
     lib
    0.10
     defamation
    0.10
     Reputation
    0.10
     def
    0.09
     reputation
    0.09
     reput
    0.08
     speech
    0.08
    publication
    0.07
     inn
    0.07
     publication
    0.07
    Act Density 0.027%

    No Known Activations