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

    Neuronpedia

    INDEX
    Explanations

    the presence of different categories or classes within a dataset or system

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     difference
    -1.54
     differ
    -1.47
     Differ
    -1.44
    difference
    -1.43
     Difference
    -1.42
     differences
    -1.41
     DIFFER
    -1.38
     differs
    -1.37
     differed
    -1.35
     DIFFERENCE
    -1.33
    POSITIVE LOGITS
     NSCoder
    0.66
    anglès
    0.55
     particularly
    0.46
    printStackTrace
    0.45
    例句
    0.45
     few
    0.44
    diyesi
    0.44
     CallOverrides
    0.44
    ttino
    0.43
     BorderRadius
    0.43
    Act Density 0.026%

    No Known Activations