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

    Neuronpedia

    INDEX
    Explanations

    indicators of political criticism or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.07
    3:0.08
    4:0.09
    5:0.09
    6:0.08
    7:0.08
    8:0.09
    9:0.07
    10:0.06
    11:0.09
    Negative Logits
     Corinth
    -1.82
     AMA
    -1.74
     Savannah
    -1.69
     bri
    -1.67
     Paula
    -1.59
     Lump
    -1.56
     Fortune
    -1.55
     ALE
    -1.50
    ��
    -1.50
     overtime
    -1.50
    POSITIVE LOGITS
    enaries
    1.90
    ilts
    1.85
    rogens
    1.77
    ctors
    1.74
    reed
    1.71
    Wiki
    1.70
    erion
    1.70
    YD
    1.62
    External
    1.62
    sei
    1.61
    Act Density 0.000%

    No Known Activations