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

    Neuronpedia

    INDEX
    Explanations

    references to cultural or societal diversity in media representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.81
     téléph
    -0.79
    NewReader
    -0.78
     препратки
    -0.78
     démocr
    -0.78
    PreferredItem
    -0.78
     Ephraim
    -0.73
     Füßen
    -0.72
     出版
    -0.71
     waschen
    -0.71
    POSITIVE LOGITS
    ButterKnife
    0.79
     Cheese
    0.64
    keySet
    0.64
    #+#
    0.63
     Butterflies
    0.61
     BoxDecoration
    0.61
     Chocolate
    0.61
     pince
    0.60
     Multiplex
    0.59
    Alonso
    0.59
    Act Density 2.143%

    No Known Activations