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

    Neuronpedia

    INDEX
    Explanations

    references to financial and economic mismanagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.04
    3:0.07
    4:0.03
    5:0.05
    6:0.19
    7:0.03
    8:0.05
    9:0.38
    10:0.03
    11:0.02
    Negative Logits
     Gast
    -4.07
     Haste
    -3.63
     Teg
    -3.44
     Satellite
    -3.42
     Harvest
    -3.35
    angular
    -3.35
     Grain
    -3.34
     Hemp
    -3.32
     Haf
    -3.28
     Beacon
    -3.25
    POSITIVE LOGITS
    ski
    5.71
    SK
    5.21
    owski
    5.18
    insky
    5.16
    ki
    5.10
    zinski
    4.76
     Schultz
    4.72
    sk
    4.62
    cki
    4.48
    KI
    4.40
    Act Density 0.005%

    No Known Activations