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

    Neuronpedia

    INDEX
    Explanations

    references to recent years in scholarly or technical contexts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    ########.
    -0.69
    DockStyle
    -0.65
    Kjelder
    -0.64
     douleurs
    -0.54
    DeleteBehavior
    -0.54
    pentry
    -0.54
    AddWithValue
    -0.53
    atterns
    -0.52
    ofe
    -0.52
    obed
    -0.51
    POSITIVE LOGITS
    ::~
    0.65
    UnsafeEnabled
    0.65
    HomeController
    0.62
     rospy
    0.54
    BASELINE
    0.52
    stateProvider
    0.52
    simpleType
    0.51
     AllAfrica
    0.50
     meanwhile
    0.50
     Theſe
    0.49
    Act Density 0.012%

    No Known Activations