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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or decisions in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.03
    2:0.05
    3:0.04
    4:0.05
    5:0.04
    6:0.28
    7:0.04
    8:0.04
    9:0.25
    10:0.03
    11:0.03
    Negative Logits
     Tan
    -4.35
     Titanic
    -4.21
    ahime
    -4.00
     Tud
    -3.92
    anu
    -3.78
     Cind
    -3.73
    Tan
    -3.63
     Dia
    -3.59
    BuyableInstoreAndOnline
    -3.56
     Ashton
    -3.53
    POSITIVE LOGITS
    Gro
    10.83
     Gro
    10.17
    gro
    8.62
     gro
    6.51
     Grove
    5.76
     grocer
    4.58
     GR
    4.55
    RO
    4.50
    GR
    4.39
     groove
    4.38
    Act Density 0.005%

    No Known Activations