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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ortium
    -0.89
    Stars
    -0.75
    PET
    -0.73
     Strikes
    -0.70
    chuk
    -0.70
    INGTON
    -0.70
     IMAGES
    -0.68
    ULAR
    -0.68
    ZE
    -0.67
     PET
    -0.64
    POSITIVE LOGITS
    abase
    1.00
    acan
    0.90
    olkien
    0.77
     Anon
    0.73
     proport
    0.72
    agram
    0.69
     behavi
    0.69
    âĶĢâĶĢâĶĢâĶĢ
    0.68
    hens
    0.68
    ©¶æ
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.