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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate expectations or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     religieuses
    -0.71
     énergé
    -0.70
     eccl
    -0.69
     emprunt
    -0.69
     ambientale
    -0.66
     Independencia
    -0.65
     persecu
    -0.65
     Bonding
    -0.65
     sonre
    -0.64
     condiv
    -0.64
    POSITIVE LOGITS
     suppose
    0.72
     dalamnya
    0.68
     cherchés
    0.64
    rawDesc
    0.63
    UIAlert
    0.62
    Зноскі
    0.60
     fact
    0.59
     concession
    0.58
     SwiftUI
    0.56
    — 
    0.56
    Act Density 0.103%

    No Known Activations