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

    Neuronpedia

    INDEX
    Explanations

    statements about political positions and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.02
    2:0.12
    3:0.08
    4:0.06
    5:0.10
    6:0.05
    7:0.11
    8:0.14
    9:0.05
    10:0.03
    11:0.07
    Negative Logits
    Ocean
    -2.58
    beard
    -2.47
    EStream
    -2.46
    estern
    -2.46
    perture
    -2.44
    cheat
    -2.42
     Realms
    -2.38
    olphin
    -2.35
    abeth
    -2.31
    ipples
    -2.28
    POSITIVE LOGITS
     BJP
    4.68
     Rahul
    4.46
     Kejriwal
    4.31
     Delhi
    4.22
     AAP
    4.06
     Gujarat
    3.65
     Sonia
    3.63
     Modi
    3.59
     Lok
    3.58
     RSS
    3.49
    Act Density 0.160%

    No Known Activations