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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.72
     purpoſe
    -0.69
     reaſon
    -0.69
     pleaſure
    -0.65
     ſmall
    -0.63
     étoient
    -0.63
     ſtate
    -0.60
     Chriſt
    -0.60
    neſs
    -0.59
     dezelve
    -0.59
    POSITIVE LOGITS
    <bos>
    1.70
    ’
    1.07
    '
    1.03
    TintMode
    0.87
    RegistryLite
    0.87
    LayoutStyle
    0.81
    ########.
    0.79
    XmlAccessType
    0.79
    TagMode
    0.77
     Paglinawan
    0.77
    Act Density 0.001%

    No Known Activations