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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "formed" and associated phrases indicating the establishment of organizations or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.04
    4:0.15
    5:0.03
    6:0.08
    7:0.39
    8:0.03
    9:0.03
    10:0.08
    11:0.05
    Negative Logits
    iencies
    -1.67
    adequ
    -1.67
    ean
    -1.65
    ruciating
    -1.58
    arton
    -1.51
    etsy
    -1.46
     aside
    -1.45
     cumbers
    -1.43
     bothered
    -1.42
     pause
    -1.42
    POSITIVE LOGITS
     Doodle
    1.65
     Faction
    1.57
     Fres
    1.55
     fold
    1.47
     [&
    1.46
     Lauder
    1.45
     fract
    1.43
     alliances
    1.43
     Resurrection
    1.43
     compact
    1.42
    Act Density 0.010%

    No Known Activations