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

    Neuronpedia

    INDEX
    Explanations

    references to intrusive or invasive content

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     yyl
    -0.61
     Exactos
    -0.59
     IBOutlet
    -0.58
     hoop
    -0.55
    graded
    -0.55
     partita
    -0.53
    ыгана
    -0.52
    rawDesc
    -0.52
     Monticello
    -0.51
    ModelAdmin
    -0.50
    POSITIVE LOGITS
    cdnjs
    0.82
     ATR
    0.77
    DotNetBar
    0.75
    SQLiteDatabase
    0.75
    instein
    0.71
    olation
    0.68
     tkinter
    0.66
    oxane
    0.66
     kasarigan
    0.65
     caste
    0.64
    Act Density 0.076%

    No Known Activations