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

    Neuronpedia

    INDEX
    Explanations

    entries related to models in programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.96
     Jefus
    -0.89
     themſelves
    -0.87
     myſelf
    -0.81
    CodeAttribute
    -0.79
     poffible
    -0.79
     Theſe
    -0.79
    UnsafeEnabled
    -0.79
     pleaſure
    -0.78
    InjectAttribute
    -0.77
    POSITIVE LOGITS
    Model
    2.30
     Model
    1.94
    MODEL
    1.33
     MODEL
    1.31
    ItemModel
    1.26
    getModel
    1.18
    Models
    1.16
    model
    1.16
    DataModel
    1.12
    IModel
    1.07
    Act Density 0.077%

    No Known Activations