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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and apostrophes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.69
    ↵↵
    -0.54
    :
    -0.52
     I
    -0.48
     if
    -0.48
    .
    -0.48
    ,
    -0.47
      
    -0.47
     That
    -0.47
     […]
    -0.46
    POSITIVE LOGITS
    :✨
    1.30
    featureID
    1.20
    Portail
    1.18
    parsedMessage
    1.15
    sizeCache
    1.14
    Personensuche
    1.11
    UserScript
    1.10
     незавершена
    1.07
    OGND
    1.06
     Мексичка
    1.05
    Act Density 0.001%

    No Known Activations