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

    Neuronpedia

    INDEX
    Explanations

    references to authors and tabular data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pure
    -0.39
     policy
    -0.37
     libre
    -0.36
    częściej
    -0.35
     prosecution
    -0.34
     mainstream
    -0.34
     Pandit
    -0.33
     ripe
    -0.33
    ่า
    -0.33
     Sharma
    -0.33
    POSITIVE LOGITS
    tabular
    1.38
     للاسماء
    0.77
    aarrggbb
    0.69
     pinulongan
    0.68
     ComVisible
    0.67
     Infórmanos
    0.64
    ագրություններ
    0.63
    OGND
    0.63
    Tikang
    0.62
     betweenstory
    0.61
    Act Density 0.018%

    No Known Activations