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

    Neuronpedia

    INDEX
    Explanations

    terms related to political correctness and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.47
     aange
    -0.42
     res
    -0.41
    Datuak
    -0.39
    Marked
    -0.39
     عرو
    -0.39
    dorp
    -0.38
     маши
    -0.38
     Catawiki
    -0.38
    󠁬
    -0.37
    POSITIVE LOGITS
     CommonModule
    0.54
     '\\;'
    0.52
     nonUne
    0.45
     kasarigan
    0.43
    tableFuture
    0.43
     <>",
    0.41
    ंदीखरीदारी
    0.40
     socialista
    0.39
     pretends
    0.39
    tispiece
    0.38
    Act Density 1.071%

    No Known Activations