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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or a significant section marking such as "<bos>"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.56
     what
    -0.49
     cre
    -0.46
     “
    -0.46
     top
    -0.46
    Kjelder
    -0.45
    rishnan
    -0.45
    Revenir
    -0.44
    மான
    -0.44
     apa
    -0.44
    POSITIVE LOGITS
    TagMode
    0.98
     للاسماء
    0.81
     ivelany
    0.78
    parsedMessage
    0.73
    IsContent
    0.73
    UnusedPrivate
    0.72
     fumée
    0.68
     tfsi
    0.68
     Efq
    0.67
    oredCriteria
    0.66
    Act Density 0.059%

    No Known Activations