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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discrimination and social commentary

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    onViewCreated
    -0.82
     myſelf
    -0.79
     itſelf
    -0.73
     himſelf
    -0.71
     NSCoder
    -0.69
     themſelves
    -0.66
    ArgsConstructor
    -0.65
     pleaſure
    -0.65
     uſe
    -0.64
     Monfieur
    -0.63
    POSITIVE LOGITS
     controversy
    0.50
     disambiguazione
    0.50
    Atsauces
    0.47
     références
    0.45
    נס
    0.43
     omission
    0.43
     ‘
    0.42
     poll
    0.42
     ویکی‌پدی
    0.41
     situation
    0.41
    Act Density 0.218%

    No Known Activations