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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and their attributes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     intptr
    -0.85
    */}
    -0.81
     ویکی‌آمباردا
    -0.75
    ()")
    -0.75
     aveug
    -0.73
    Weiterlesen
    -0.72
     bezeichneter
    -0.72
     Jop
    -0.71
     RSSSF
    -0.71
    apatalk
    -0.71
    POSITIVE LOGITS
    Sensi
    0.62
     Ne
    0.58
     s
    0.56
     
    0.56
    Ne
    0.55
    stone
    0.54
    Oss
    0.54
    isfile
    0.52
    SourceChecksum
    0.51
    Berg
    0.50
    Act Density 0.009%

    No Known Activations