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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal notions and systemic errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    createClass
    -0.57
    WriteLiteral
    -0.53
    ع
    -0.53
    IMPORTED
    -0.51
    ImageContext
    -0.49
    Clar
    -0.49
    ․
    -0.48
    RegistryLite
    -0.47
     known
    -0.47
    interopRequire
    -0.47
    POSITIVE LOGITS
     Shakspeare
    0.87
    homonymie
    0.84
    blume
    0.81
     emotion
    0.76
    gdx
    0.76
     Shaksp
    0.75
    IntoConstraints
    0.72
    quiao
    0.72
     notion
    0.72
     Jefus
    0.72
    Act Density 0.251%

    No Known Activations