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

    Neuronpedia

    INDEX
    Explanations

    themes related to social roles and stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gyhoeddwyd
    -0.51
     him
    -0.43
    bonnet
    -0.43
    alp
    -0.42
    wap
    -0.41
    atalos
    -0.41
    eux
    -0.40
    Попис
    -0.40
    Compat
    -0.40
     himself
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.87
    MigrationBuilder
    0.77
     ویکی‌پدیا
    0.76
    MemoryWarning
    0.75
     kasarigan
    0.75
    yntaxException
    0.71
     <<<<<<<<<<<<<<
    0.71
    labelledby
    0.69
     CURIAM
    0.68
    AndEndTag
    0.67
    Act Density 0.261%

    No Known Activations