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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     (
    -0.57
     spørs
    -0.55
     
    -0.55
     The
    -0.53
     A
    -0.49
     Min
    -0.49
    Session
    -0.45
     vhodné
    -0.44
    S
    -0.43
     prøve
    -0.43
    POSITIVE LOGITS
    StructEnd
    1.11
    IUrlHelper
    1.08
    principalColumn
    1.00
     дописавши
    0.96
     NSCoder
    0.93
    etheless
    0.92
     ویکی‌پدی
    0.92
    ScopeManager
    0.90
     Majefty
    0.90
     iſt
    0.90
    Act Density 0.023%

    No Known Activations