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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of media production and characters within themed contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.42
     kaarangay
    -1.28
     Roskov
    -1.25
    RectangleBorder
    -1.25
    Personendaten
    -1.20
     myſelf
    -1.15
     NSCoder
    -1.15
     poffible
    -1.14
     виправивши
    -1.14
    tagHelperRunner
    -1.12
    POSITIVE LOGITS
      
    0.68
     of
    0.66
     in
    0.60
     was
    0.59
     and
    0.56
     is
    0.55
    .
    0.52
     (
    0.52
    :
    0.50
     by
    0.50
    Act Density 0.611%

    No Known Activations