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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or connections among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.10
    3:0.07
    4:0.28
    5:0.04
    6:0.03
    7:0.21
    8:0.03
    9:0.06
    10:0.05
    11:0.06
    Negative Logits
    iners
    -1.47
    obin
    -1.44
    oslav
    -1.42
    quit
    -1.40
    aughs
    -1.39
    iversal
    -1.38
    opped
    -1.35
    andowski
    -1.33
    bum
    -1.32
    inters
    -1.32
    POSITIVE LOGITS
     workings
    1.95
     whereabouts
    1.71
     cloaked
    1.58
     nuances
    1.55
    worm
    1.53
     specifics
    1.53
     origins
    1.52
     particulars
    1.48
     birthplace
    1.44
     shrouded
    1.42
    Act Density 0.080%

    No Known Activations