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

    Neuronpedia

    INDEX
    Explanations

    underscores in code or text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coscienza
    -0.83
     culturelles
    -0.77
     commerciali
    -0.73
     isolado
    -0.72
     religieuses
    -0.71
     sanitaires
    -0.70
     judiciaire
    -0.69
     garanzia
    -0.69
     aimé
    -0.69
     contactar
    -0.69
    POSITIVE LOGITS
     nonatomic
    0.68
     premium
    0.56
    AppendLine
    0.56
     Premium
    0.55
     nhân
    0.55
    usermodel
    0.55
    bukkit
    0.54
     Sper
    0.54
    генера
    0.53
    └──
    0.53
    Act Density 0.053%

    No Known Activations