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
    1:0.09
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.07
    8:0.08
    9:0.05
    10:0.09
    11:0.07
    Negative Logits
    orgetown
    -1.91
    ]);
    -1.90
     Interior
    -1.77
    oland
    -1.76
    ]).
    -1.60
    eton
    -1.59
    enum
    -1.59
    ])
    -1.59
     Colon
    -1.57
    ]),
    -1.55
    POSITIVE LOGITS
     playbook
    1.68
     coordin
    1.61
     kits
    1.61
     bat
    1.58
     kit
    1.56
     gel
    1.54
     deed
    1.52
     request
    1.49
     repl
    1.49
     acronym
    1.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.