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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dynamo
    -0.79
    SHARE
    -0.68
     Wem
    -0.67
     deport
    -0.65
     recapt
    -0.65
    WORK
    -0.65
    OOL
    -0.64
     Trainer
    -0.63
     incorpor
    -0.62
     Dak
    -0.62
    POSITIVE LOGITS
    oft
    0.71
    reme
    0.70
    oreal
    0.69
    oppers
    0.67
    susp
    0.66
    linux
    0.66
    ophy
    0.66
    terday
    0.65
    rophic
    0.64
    gnu
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.