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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lack
    -0.74
     dyed
    -0.74
     slightest
    -0.73
     millenn
    -0.72
     wed
    -0.70
     nodd
    -0.70
    undai
    -0.70
     inexper
    -0.70
    ailability
    -0.69
     clot
    -0.69
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    0.80
    @#&
    0.79
    =-=-=-=-
    0.79
    raise
    0.74
    ¶
    0.73
     Authors
    0.73
    buster
    0.72
    pps
    0.70
    utenberg
    0.69
    ?!
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.