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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and references to locations, especially those related to Troy, Michigan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McMahon
    -0.78
    levance
    -0.76
    Msp
    -0.70
     Granger
    -0.70
     Eme
    -0.70
    rances
    -0.67
    phanie
    -0.66
    Eme
    -0.66
    [...,
    -0.66
     Graeme
    -0.65
    POSITIVE LOGITS
    التالي
    0.84
     Swords
    0.82
     Batter
    0.80
     Dory
    0.79
     referenties
    0.78
     swords
    0.76
     כן
    0.75
    ModelForm
    0.75
    reszcie
    0.73
     Guen
    0.72
    Act Density 0.883%

    No Known Activations