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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement and legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.19
    3:0.09
    4:0.02
    5:0.03
    6:0.19
    7:0.11
    8:0.04
    9:0.06
    10:0.05
    11:0.09
    Negative Logits
    yip
    -1.41
    ️
    -1.29
    earable
    -1.20
    isite
    -1.14
    esome
    -1.10
    inventory
    -1.10
    hift
    -1.03
    oute
    -1.02
    essage
    -1.02
    abwe
    -1.01
    POSITIVE LOGITS
     Rae
    1.12
    iren
    1.03
    ENN
    1.01
    CLASSIFIED
    0.99
    enforcement
    0.96
    illac
    0.96
    icus
    0.91
    lesi
    0.91
    HQ
    0.90
    opa
    0.89
    Act Density 0.027%

    No Known Activations