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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.73
     Dise
    -0.70
    Cry
    -0.67
    arez
    -0.67
    ++++
    -0.66
    CLA
    -0.66
    Brave
    -0.66
    Ire
    -0.64
    Merit
    -0.62
    çĦ
    -0.62
    POSITIVE LOGITS
    icket
    0.84
    unta
    0.81
    abase
    0.76
    ucket
    0.73
     accordingly
    0.69
    eret
    0.69
    renches
    0.69
     Rove
    0.68
     Jarrett
    0.67
     Petersen
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.