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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ÃŃn
    -0.73
    Jon
    -0.70
    Adapt
    -0.70
    TPS
    -0.69
    dy
    -0.69
    ¯
    -0.69
    Shift
    -0.68
    gren
    -0.67
    acy
    -0.67
    Develop
    -0.67
    POSITIVE LOGITS
    ctors
    0.88
     roadside
    0.85
     reasonable
    0.76
     university
    0.70
     medium
    0.69
     contempor
    0.69
     tourist
    0.68
     souven
    0.67
     BUS
    0.67
     DAY
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.