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

    Neuronpedia

    INDEX
    Explanations

    patterns of misconceptions and stereotypes associated with gender and social norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abestanden
    -0.87
     متعلقه
    -0.86
     cherchés
    -0.81
    AndEndTag
    -0.76
    šanai
    -0.74
     wireType
    -0.71
     intptr
    -0.70
     autorytatywna
    -0.69
     ExecuteAsync
    -0.68
    VersionUID
    -0.67
    POSITIVE LOGITS
     culture
    0.74
     attitudes
    0.67
     ingrained
    0.66
     cultural
    0.59
     cultura
    0.56
     Attitudes
    0.56
     mindset
    0.56
     stigma
    0.55
     kulture
    0.53
     widespread
    0.53
    Act Density 0.413%

    No Known Activations