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

    Neuronpedia

    INDEX
    Explanations

    aspects and dimensions related to comprehensive evaluations of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     algunas
    -0.69
     algunos
    -0.69
     two
    -0.64
     algumas
    -0.63
     alguns
    -0.62
     some
    -0.62
     alcune
    -0.61
     alcuni
    -0.59
     certains
    -0.57
     certain
    -0.56
    POSITIVE LOGITS
    everything
    1.06
     Everything
    1.02
    Everything
    1.01
     everything
    1.00
     EVERYTHING
    1.00
     imaginable
    1.00
     conceivable
    0.94
    AddTagHelper
    0.94
     וכל
    0.92
     وكل
    0.91
    Act Density 0.715%

    No Known Activations