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

    Neuronpedia

    INDEX
    Explanations

    comments related to tasks or notes for future work, often marked as TODOs or FIXMEs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dataclass
    -0.53
    readFileSync
    -0.53
    TestRunner
    -0.51
     المعيارى
    -0.47
    conexion
    -0.45
     &___
    -0.45
    netinet
    -0.45
    Accueil
    -0.45
     onBind
    -0.45
    Sair
    -0.44
    POSITIVE LOGITS
    TODO
    1.17
     TODO
    1.11
    RegressionTest
    1.02
    :✨
    0.92
     Infórmanos
    0.87
    Todo
    0.84
    todo
    0.81
     odo
    0.74
     dolo
    0.70
     Todo
    0.69
    Act Density 0.015%

    No Known Activations