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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nop
    -0.90
     Hector
    -0.76
     UNO
    -0.74
     Stratford
    -0.73
    Välislingid
    -0.71
    DockStyle
    -0.71
     Ney
    -0.70
     Cora
    -0.70
     rø
    -0.70
    Bigr
    -0.69
    POSITIVE LOGITS
    en
    0.81
     Betten
    0.79
    pen
    0.78
    vegan
    0.75
     Bowden
    0.74
     Tobin
    0.74
     vin
    0.73
    han
    0.73
     mxArray
    0.72
     Harman
    0.72
    Act Density 7.187%

    No Known Activations