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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.09
    5:0.06
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
    phone
    -1.66
    WIND
    -1.45
     delegates
    -1.44
     passports
    -1.34
     TRUMP
    -1.34
     liquid
    -1.31
     dro
    -1.30
     brake
    -1.28
     brakes
    -1.26
     phone
    -1.26
    POSITIVE LOGITS
    ��
    2.00
     )]
    1.66
    .):
    1.65
    endas
    1.64
    iosyn
    1.59
     サーティワン
    1.58
    kees
    1.57
    ]),
    1.55
    )]
    1.55
    psey
    1.54
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.