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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political decision-making and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.14
    3:0.39
    4:0.09
    5:0.04
    6:0.02
    7:0.06
    8:0.04
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    CLUD
    -1.85
     teasp
    -1.82
    田
    -1.77
    yip
    -1.76
    awei
    -1.76
     GOODMAN
    -1.69
     includ
    -1.69
    Marg
    -1.67
    pei
    -1.66
    senal
    -1.65
    POSITIVE LOGITS
     anymore
    2.49
     nor
    2.04
     anything
    1.91
     overnight
    1.82
    ouses
    1.63
     blazing
    1.60
     yet
    1.57
     anybody
    1.52
     any
    1.50
     anyone
    1.48
    Act Density 0.061%

    No Known Activations