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

    Neuronpedia

    INDEX
    Explanations

    words related to computer programming error codes or syntax

    oai_token-act-pair · gpt-3.5-turbo

    instances of the special character 'âĢ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manhattan
    -0.61
     Kenyan
    -0.60
    anwhile
    -0.59
    ItemThumbnailImage
    -0.57
     catering
    -0.57
     Mous
    -0.56
     UID
    -0.56
     Classification
    -0.55
     Alc
    -0.54
     Kraken
    -0.54
    POSITIVE LOGITS
    ¬
    1.30
    ľ
    1.21
    ¿
    1.18
    Ń
    1.11
    ¦
    1.09
    Ķ
    1.07
    ¼
    1.07
    ±
    1.05
    º
    1.03
    ı
    1.01
    Act Density 0.154%

    No Known Activations