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

    Neuronpedia

    INDEX
    Explanations

    definitions and criteria related to values and legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iprot
    -0.44
    Vig
    -0.43
    AnimationsModule
    -0.42
    DockStyle
    -0.42
    裸
    -0.42
    Explanation
    -0.41
     Lar
    -0.41
    HttpGet
    -0.39
    лям
    -0.39
     Car
    -0.39
    POSITIVE LOGITS
     Monfieur
    0.79
     Theſe
    0.78
     itſelf
    0.78
     ſeveral
    0.71
    )++;
    0.68
     ་་
    0.65
     Jefus
    0.65
     Chriftian
    0.64
    ableness
    0.62
    Rüyada
    0.61
    Act Density 0.590%

    No Known Activations