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

    Neuronpedia

    INDEX
    Explanations

    references to mills and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.65
    Azur
    -0.63
    pensive
    -0.60
     gleicher
    -0.58
     same
    -0.55
    ounced
    -0.54
    batore
    -0.54
     Snackbar
    -0.52
    aje
    -0.52
    same
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.80
    ennium
    0.69
    enium
    0.69
     Milford
    0.68
    AddTagHelper
    0.65
    enial
    0.62
    Mili
    0.62
     kasarigan
    0.60
     Milne
    0.59
     MILL
    0.58
    Act Density 0.061%

    No Known Activations