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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal and law enforcement actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.32
    4:0.05
    5:0.04
    6:0.03
    7:0.04
    8:0.08
    9:0.09
    10:0.10
    11:0.07
    Negative Logits
    schild
    -1.64
    ukong
    -1.46
     Refuge
    -1.43
    ructose
    -1.43
     Truly
    -1.42
     ILCS
    -1.41
     Pair
    -1.41
     Redemption
    -1.38
     Whale
    -1.37
    bowl
    -1.36
    POSITIVE LOGITS
     nonetheless
    2.39
    etheless
    1.91
     nevertheless
    1.81
     anyway
    1.74
     suffice
    1.68
     dissu
    1.66
    arser
    1.62
     overr
    1.60
     intervened
    1.58
     thereafter
    1.53
    Act Density 0.724%

    No Known Activations