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

    Neuronpedia

    INDEX
    Explanations

    references to political votes and resolutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.04
    4:0.02
    5:0.05
    6:0.04
    7:0.10
    8:0.07
    9:0.38
    10:0.07
    11:0.08
    Negative Logits
    paralle
    -1.34
    fol
    -1.27
    Writer
    -1.26
    ÃÂ
    -1.25
    stood
    -1.23
    mouth
    -1.22
    quartered
    -1.21
    ionage
    -1.21
    cells
    -1.18
    severe
    -1.18
    POSITIVE LOGITS
    galitarian
    1.31
     defer
    1.31
     lottery
    1.30
     Zup
    1.28
     forfeit
    1.25
    eday
    1.25
     =>
    1.24
     Breed
    1.24
     TAMADRA
    1.22
     democratically
    1.22
    Act Density 0.050%

    No Known Activations