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

    Neuronpedia

    INDEX
    Explanations

    first-person pronoun

    np_max-act · gemini-2.0-flash

    references to the creation and characteristics of an immoral AI or chatbot.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lawson
    -0.06
    ButtonClick
    -0.06
     DatePicker
    -0.06
    togroup
    -0.06
    pearance
    -0.06
     Jap
    -0.06
     досить
    -0.06
     Nolan
    -0.06
     shining
    -0.06
     Komm
    -0.06
    POSITIVE LOGITS
     coral
    0.07
    $fields
    0.07
    longrightarrow
    0.07
     businesses
    0.06
    	settings
    0.06
     preds
    0.06
    猪
    0.06
     الحل
    0.06
    GetType
    0.06
    0.06
    Act Density 0.007%

    No Known Activations