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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    outine
    -0.85
    plete
    -0.80
    staff
    -0.75
    anche
    -0.75
    abal
    -0.74
    rup
    -0.70
    enser
    -0.67
    abre
    -0.67
    andy
    -0.67
    ongyang
    -0.67
    POSITIVE LOGITS
     titles
    0.77
     Surface
    0.76
     sul
    0.74
     Cumm
    0.71
     Duty
    0.69
    Posts
    0.68
     buddies
    0.68
     Robots
    0.66
    çīĪ
    0.66
    UF
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.