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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "modal" and its variations, indicating a focus on modal aspects in the context of the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.80
    PerformLayout
    -0.77
    +#+
    -0.69
    ]))
    -0.69
    yty
    -0.68
    таратура
    -0.68
    SizeF
    -0.68
     CWE
    -0.67
    csname
    -0.67
    ">—
    -0.66
    POSITIVE LOGITS
     Modal
    1.44
     modal
    1.34
    modal
    1.32
    Modal
    1.27
    MODAL
    1.13
    setModal
    0.93
    closeModal
    0.86
     modalities
    0.75
     Dijk
    0.72
     Boch
    0.72
    Act Density 0.001%

    No Known Activations