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

    Neuronpedia

    INDEX
    Explanations

    arguments and discussions related to political positions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.03
    2:0.00
    3:0.09
    4:0.04
    5:0.08
    6:0.04
    7:0.01
    8:0.41
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
    quartered
    -1.75
     Mara
    -1.72
     Located
    -1.58
    blance
    -1.58
     Location
    -1.56
    ahime
    -1.56
    owment
    -1.55
     CrossRef
    -1.54
     Visit
    -1.53
    atri
    -1.48
    POSITIVE LOGITS
    against
    2.59
    Against
    2.49
     convinc
    2.41
     arguments
    2.26
     against
    2.14
     plaint
    2.07
     arguing
    2.00
    govtrack
    1.97
     passionately
    1.96
     futile
    1.96
    Act Density 0.010%

    No Known Activations