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
     Hartmann
    -0.75
    LogManager
    -0.75
     Engel
    -0.73
    tvguidetime
    -0.72
    Gobierno
    -0.70
    SMR
    -0.70
    )$\\
    -0.69
    PerformLayout
    -0.68
    bkz
    -0.67
    IsContent
    -0.66
    POSITIVE LOGITS
     Roskov
    0.83
     Crimean
    0.77
     Alonzo
    0.75
     Flur
    0.71
     Alois
    0.71
     RAI
    0.70
     Hür
    0.69
     Alpen
    0.67
     Desmond
    0.67
     Erit
    0.67
    Act Density 2.702%

    No Known Activations