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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.02
    3:0.07
    4:0.09
    5:0.36
    6:0.05
    7:0.04
    8:0.06
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
    stocks
    -2.27
    %%%%
    -2.07
     bart
    -1.96
     eternity
    -1.87
     Collider
    -1.84
     relegation
    -1.83
    cro
    -1.83
    erald
    -1.82
    ixtures
    -1.80
     promotions
    -1.79
    POSITIVE LOGITS
     versus
    2.65
     vs
    2.26
     secondly
    2.25
    renheit
    2.11
     also
    1.95
     preceded
    1.94
     differs
    1.94
     punishable
    1.92
    Pg
    1.92
     Secondly
    1.91
    Act Density 0.015%

    No Known Activations