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

    Neuronpedia

    INDEX
    Explanations

    references to influential public figures and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.02
    2:0.09
    3:0.04
    4:0.05
    5:0.03
    6:0.19
    7:0.06
    8:0.09
    9:0.19
    10:0.02
    11:0.05
    Negative Logits
     Boyd
    -3.83
     bay
    -3.58
     Flare
    -3.58
     disclaim
    -3.47
     ATI
    -3.45
     forestry
    -3.30
     wildfire
    -3.23
     flares
    -3.22
    leaf
    -3.21
     Gale
    -3.20
    POSITIVE LOGITS
     Schumer
    11.13
    Sch
    5.04
     Cuomo
    4.96
     Pelosi
    4.38
     SEN
    4.37
     Lena
    4.32
    Senate
    4.24
     Senate
    4.19
     Kirst
    4.13
     Schwartz
    4.12
    Act Density 0.003%

    No Known Activations