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

    Neuronpedia

    INDEX
    Explanations

    discussions on socio-economic issues and their effects on specific communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.28
    3:0.15
    4:0.09
    5:0.03
    6:0.06
    7:0.03
    8:0.04
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
     Indra
    -1.77
     Lank
    -1.69
     Mud
    -1.54
     Wad
    -1.54
    �
    -1.52
     Lumpur
    -1.48
    soType
    -1.46
    MAS
    -1.43
     Witch
    -1.43
     Cosponsors
    -1.38
    POSITIVE LOGITS
    eren
    1.71
    nt
    1.65
     predomin
    1.59
     intersect
    1.57
     intertw
    1.50
    ERE
    1.47
    ér
    1.41
    overed
    1.41
    oppable
    1.40
    oeuv
    1.39
    Act Density 0.243%

    No Known Activations