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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscores and section annotations in structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     étoient
    -0.87
     indietro
    -0.80
     démocr
    -0.79
     avoient
    -0.77
    ">'.$
    -0.73
     Anſ
    -0.73
     CreateTagHelper
    -0.73
     Monfieur
    -0.72
     Theſe
    -0.71
    بوابة
    -0.70
    POSITIVE LOGITS
     i
    0.53
    ,
    0.53
    WireFormatLite
    0.52
    
    0.50
     I
    0.48
    appcompat
    0.47
     @"/
    0.46
     members
    0.45
     base
    0.45
    XtraEditors
    0.45
    Act Density 0.006%

    No Known Activations