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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "or" in context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    —
    -0.57
     near
    -0.55
     or
    -0.55
     “
    -0.55
    ,
    -0.52
     [
    -0.52
     least
    -0.52
     —
    -0.50
     large
    -0.50
     
    -0.49
    POSITIVE LOGITS
    GraphicsUnit
    1.04
    PhysRevD
    1.03
     مشين
    1.00
    AddTagHelper
    0.90
    WillAppear
    0.89
    PhysRev
    0.88
    SerializedSize
    0.85
     contextLoads
    0.83
    揄
    0.83
    ⋙
    0.82
    Act Density 0.008%

    No Known Activations