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

    Neuronpedia

    INDEX
    Explanations

    references to the mainstream media

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    Бахар
    -0.76
    protoimpl
    -0.60
    Initializable
    -0.59
    ."));
    -0.59
     obicei
    -0.58
    AxisAlignment
    -0.56
     ↓,
    -0.56
     storica
    -0.56
    dataloader
    -0.55
     chapel
    -0.55
    POSITIVE LOGITS
     mainstream
    3.19
    主流
    1.45
     mainline
    0.66
    PerformLayout
    0.59
    eroon
    0.54
     Integrate
    0.54
     legitim
    0.53
     mainland
    0.50
    TargetException
    0.50
    toupper
    0.49
    Act Density 0.001%

    No Known Activations