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

    Neuronpedia

    INDEX
    Explanations

    terms related to governmental and international entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.13
    3:0.08
    4:0.32
    5:0.04
    6:0.04
    7:0.10
    8:0.03
    9:0.04
    10:0.08
    11:0.07
    Negative Logits
    aughs
    -1.67
    apter
    -1.41
     emoji
    -1.40
    ito
    -1.40
    eness
    -1.35
     anthrop
    -1.34
    athy
    -1.31
     emot
    -1.31
    ach
    -1.30
     fact
    -1.30
    POSITIVE LOGITS
     fray
    2.10
     corridors
    1.77
     precincts
    1.72
    ulia
    1.59
     corridor
    1.58
     woods
    1.51
    idden
    1.50
     Corinth
    1.42
     airspace
    1.41
     toile
    1.38
    Act Density 0.027%

    No Known Activations