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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve numerical quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Athenians
    -0.70
     chevalier
    -0.68
     fédé
    -0.62
     Ordovician
    -0.62
     houſe
    -0.62
     depositors
    -0.61
     soldat
    -0.61
     galerie
    -0.61
     savages
    -0.60
     chimique
    -0.59
    POSITIVE LOGITS
     two
    0.91
     three
    0.82
     major
    0.80
     different
    0.80
     separate
    0.76
     new
    0.75
     prominent
    0.75
     other
    0.74
     mini
    0.73
     dozen
    0.72
    Act Density 0.495%

    No Known Activations