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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LCS
    -0.53
    +#+#
    -0.50
     Dominguez
    -0.49
     LW
    -0.47
     McCormick
    -0.46
     Deacon
    -0.45
     Brito
    -0.45
     LV
    -0.45
     LM
    -0.44
     insuffisamment
    -0.44
    POSITIVE LOGITS
     RAL
    0.86
    JAL
    0.85
     Yel
    0.82
    AEL
    0.79
     NAL
    0.78
     Jel
    0.78
    Jal
    0.78
     Jal
    0.77
    MTL
    0.77
    Jel
    0.76
    Act Density 5.581%

    No Known Activations