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

    Neuronpedia

    INDEX
    Explanations

    attributes and values in a structured markup or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.73
     pinulongan
    -0.57
    RegressionTest
    -0.52
     Numerade
    -0.52
     فريبيس
    -0.50
    .³
    -0.49
    VersionUID
    -0.49
    SequentialGroup
    -0.49
    fortawesome
    -0.49
     Administrativna
    -0.47
    POSITIVE LOGITS
    1
    1.06
    2
    0.95
    3
    0.87
    4
    0.83
    5
    0.83
    6
    0.79
    9
    0.77
    8
    0.77
    7
    0.74
    0
    0.70
    Act Density 3.030%

    No Known Activations