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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence and legal cases related to criminal activities or laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.03
    3:0.05
    4:0.08
    5:0.02
    6:0.16
    7:0.31
    8:0.01
    9:0.03
    10:0.02
    11:0.18
    Negative Logits
     Pets
    -2.37
     Vote
    -2.29
     Movies
    -2.15
    dogs
    -2.10
     Vend
    -2.09
    DIT
    -2.07
    bet
    -2.05
     Dogs
    -2.03
     Visit
    -2.01
     Particip
    -1.96
    POSITIVE LOGITS
     cases
    2.79
     case
    2.65
     Horus
    2.52
     Kemp
    2.48
     Sturgeon
    2.43
     Turner
    2.42
     Yose
    2.40
     ILCS
    2.36
    emp
    2.35
    stadt
    2.35
    Act Density 0.061%

    No Known Activations