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

    Neuronpedia

    INDEX
    Explanations

    key concepts and important points in a discussion or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PyTuple
    -0.64
     Favorites
    -0.64
     unfavourable
    -0.63
     Fland
    -0.62
     quadrature
    -0.62
     unfavorable
    -0.62
     officielles
    -0.62
    ViewImports
    -0.61
    FAVOR
    -0.61
    ooper
    -0.60
    POSITIVE LOGITS
     underlying
    0.61
    ThroughAttribute
    0.59
    underlying
    0.52
    重要的是
    0.50
    دانشنامهٔ
    0.49
    rawDesc
    0.48
     mental
    0.46
     message
    0.45
    umbre
    0.44
    rungsseite
    0.44
    Act Density 0.307%

    No Known Activations