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

    Neuronpedia

    INDEX
    Explanations

    references to divisions or categorizations within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dar
    -0.97
    someone
    -0.83
    illard
    -0.77
    aunt
    -0.70
    times
    -0.68
     awoken
    -0.66
    ante
    -0.66
    aston
    -0.66
    iron
    -0.66
    IRO
    -0.64
    POSITIVE LOGITS
     halves
    1.00
     categories
    0.95
     chronological
    0.94
     factions
    0.89
     manageable
    0.87
     phases
    0.87
     groups
    0.83
     separate
    0.83
     tiers
    0.83
     distinct
    0.81
    Act Density 0.063%

    No Known Activations