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

    Neuronpedia

    INDEX
    Explanations

    references to legislative actions and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.15
    3:0.34
    4:0.13
    5:0.03
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    ��
    -1.52
    ME
    -1.48
     continuing
    -1.41
    irs
    -1.38
    WHO
    -1.37
    KNOWN
    -1.37
    anwhile
    -1.36
     accordingly
    -1.36
     bisc
    -1.35
    mble
    -1.31
    POSITIVE LOGITS
     slightest
    2.05
     anymore
    2.00
     remotely
    1.78
    esides
    1.74
    throp
    1.62
     anywhere
    1.58
    obl
    1.52
     nor
    1.52
     whatsoever
    1.48
    uddenly
    1.47
    Act Density 0.012%

    No Known Activations