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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    soever
    -0.83
     confir
    -0.72
     *)
    -0.70
     answ
    -0.65
     missionaries
    -0.65
     '(
    -0.63
     mattress
    -0.63
     Airbnb
    -0.62
    ecause
    -0.61
     Customers
    -0.61
    POSITIVE LOGITS
    à©
    0.77
    thora
    0.76
    Discussion
    0.70
    icum
    0.69
    NVIDIA
    0.68
    gam
    0.68
    Thirty
    0.67
    PO
    0.67
    Stars
    0.67
    outhern
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.