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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures of significance and prevalence in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.72
    EndGlobalSection
    -0.63
    InitVars
    -0.61
    afficheront
    -0.59
    DrawerToggle
    -0.59
     <>",
    -0.58
     <=",
    -0.58
    UnusedPrivate
    -0.58
     betweenstory
    -0.58
     Bogor
    -0.57
    POSITIVE LOGITS
     Πολ
    0.48
    ReadInt
    0.48
     Walkover
    0.45
     even
    0.44
     sogar
    0.44
     Connectez
    0.43
     since
    0.42
     אף
    0.42
     TAL
    0.42
     longer
    0.42
    Act Density 0.604%

    No Known Activations