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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names associated with individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mechanical
    -0.33
    sn
    -0.33
    hi
    -0.30
     sn
    -0.30
     
    -0.30
     dep
    -0.29
    ametric
    -0.29
    eng
    -0.28
    i
    -0.28
     human
    -0.28
    POSITIVE LOGITS
    KommentareTeilen
    0.83
     esternos
    0.71
    fjspx
    0.71
    AddTagHelper
    0.68
     zuſammen
    0.68
    ########.
    0.66
    #+#
    0.65
    niſſe
    0.65
    0.64
     Geſch
    0.62
    Act Density 0.065%

    No Known Activations