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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming specifications and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ve
    -0.53
     "
    -0.53
     “
    -0.52
     ke
    -0.48
    <eos>
    -0.47
    .
    -0.47
     
    -0.46
     Z
    -0.44
    “
    -0.44
    "
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    7.56
    TagMode
    1.34
    ValueStyle
    1.31
    SourceChecksum
    1.25
    DockStyle
    1.24
     propOrder
    1.23
     GenerationType
    1.16
     referenties
    1.06
    IntoConstraints
    1.06
     للاسماء
    1.04
    Act Density 0.005%

    No Known Activations