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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and modal verbs indicating potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.94
    تقاوى
    -0.92
    DeleteBehavior
    -0.90
     Jefus
    -0.88
     poffible
    -0.88
    Geplaatst
    -0.87
     myſelf
    -0.86
     leſs
    -0.84
     дописавши
    -0.84
    Personendaten
    -0.82
    POSITIVE LOGITS
     be
    0.94
     have
    0.80
     also
    0.76
     
    0.73
     being
    0.66
      
    0.65
     not
    0.65
     make
    0.64
     a
    0.62
    .
    0.60
    Act Density 0.269%

    No Known Activations