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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusivity or consideration for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    for followed by purpose or recipient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avven
    -0.48
    期刊论文
    -0.43
    Portale
    -0.42
     kaarangay
    -0.41
     bestaan
    -0.40
     claims
    -0.40
    setupUi
    -0.40
    为止
    -0.39
     two
    -0.39
     crochê
    -0.39
    POSITIVE LOGITS
     للاسماء
    0.51
    ">//
    0.47
    AsUp
    0.47
    })*/
    0.45
    HomeComponent
    0.44
    
    0.43
     }],
    0.42
     ComVisible
    0.42
    ."],
    0.40
    ✷
    0.39
    Act Density 0.023%

    No Known Activations