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

    Neuronpedia

    INDEX
    Explanations

    technical elements related to JSON objects and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Photocase
    -0.84
    IsContent
    -0.74
     Chrift
    -0.71
     المعيارى
    -0.70
    Хьажоргаш
    -0.70
    Lähteet
    -0.69
     Numerade
    -0.66
     الرياضيه
    -0.66
    ViewFeatures
    -0.65
    ItemBackground
    -0.65
    POSITIVE LOGITS
     skall
    0.47
     whilst
    0.46
     utilizar
    0.44
    Whilst
    0.43
     iż
    0.41
     dolayı
    0.40
     Whilst
    0.40
    miştir
    0.40
     jeżeli
    0.38
     cannot
    0.38
    Act Density 0.195%

    No Known Activations