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

    Neuronpedia

    INDEX
    Explanations

    language associated with inflammatory and derogatory statements or behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyá»ħn
    -0.15
     plagiar
    -0.15
    fak
    -0.15
    emaker
    -0.15
    585
    -0.14
    clar
    -0.14
    onto
    -0.14
    .Compile
    -0.13
    oll
    -0.13
    emin
    -0.13
    POSITIVE LOGITS
     language
    0.70
     Language
    0.56
    language
    0.53
    Language
    0.50
     LANGUAGE
    0.49
    -language
    0.44
    è¯Ńè¨Ģ
    0.44
    _language
    0.42
     lang
    0.40
    -Language
    0.37
    Act Density 0.088%

    No Known Activations