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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic sources and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.94
     تضيفلها
    -0.90
    UserScript
    -0.82
     يتيمه
    -0.81
    ContentAlignment
    -0.79
    cstdlib
    -0.78
    SequentialGroup
    -0.70
     NSError
    -0.70
    BoxShadow
    -0.70
     Tyl
    -0.69
    POSITIVE LOGITS
     literature
    1.37
     Literature
    1.33
    Literature
    1.31
    literature
    1.23
     liter
    1.19
     literat
    1.17
     Liter
    1.14
     LITERATURE
    1.14
     литера
    1.04
    Liter
    1.04
    Act Density 0.127%

    No Known Activations