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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate leadership or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.10
    2:0.18
    3:0.02
    4:0.02
    5:0.06
    6:0.16
    7:0.07
    8:0.15
    9:0.04
    10:0.09
    11:0.03
    Negative Logits
    .",
    -1.15
     Corsair
    -1.08
    gements
    -1.05
    yip
    -1.05
    chwitz
    -0.99
    .?
    -0.99
     guiActiveUnfocused
    -0.97
     glim
    -0.94
     Which
    -0.94
    relevant
    -0.94
    POSITIVE LOGITS
     herself
    1.26
    edly
    1.20
    ェ
    1.15
     Sandra
    1.13
     himself
    1.13
    uther
    1.08
     Poc
    1.02
     Cosponsors
    1.01
    �
    1.01
    版
    1.01
    Act Density 0.096%

    No Known Activations