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

    Neuronpedia

    INDEX
    Explanations

    terms related to stigma and discrimination, particularly in the context of mental health

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

    stigma and shame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plan
    -0.50
     prepare
    -0.48
     Prepare
    -0.46
     preparation
    -0.45
     prepared
    -0.43
     PREPAR
    -0.43
     machines
    -0.42
    preparation
    -0.42
     Prepar
    -0.42
    uteri
    -0.42
    POSITIVE LOGITS
     stigma
    1.05
     stigmati
    0.91
    CppMethod
    0.82
    Stig
    0.81
     Stig
    0.81
    stig
    0.79
     stig
    0.77
    UnknownFields
    0.63
    RegressionTest
    0.62
     honte
    0.58
    Act Density 0.012%

    No Known Activations