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

    Neuronpedia

    INDEX
    Explanations

    syntactical elements and operations related to programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guil
    -0.63
     Trav
    -0.60
     Kuri
    -0.59
     Malo
    -0.58
     Monter
    -0.58
     Mala
    -0.57
     Mura
    -0.56
     hee
    -0.55
     Koch
    -0.55
     Frey
    -0.55
    POSITIVE LOGITS
     EconPapers
    0.87
     scolaires
    0.86
     varandra
    0.85
     stället
    0.83
     kvinnor
    0.82
     kvinna
    0.81
     spagno
    0.81
    tvguidetime
    0.81
     regeringen
    0.81
     mundiales
    0.79
    Act Density 0.874%

    No Known Activations