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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Stamina
    -0.71
     Enhancement
    -0.68
    Scroll
    -0.66
    ods
    -0.63
     forks
    -0.62
     Ashton
    -0.61
    cod
    -0.60
    urity
    -0.60
     NOTICE
    -0.60
    cv
    -0.59
    POSITIVE LOGITS
    ©¶æ
    0.94
     challeng
    0.72
     uneven
    0.70
     antit
    0.68
     optimistic
    0.67
    ãĤ´ãĥ³
    0.67
    isman
    0.67
     disparate
    0.66
     ante
    0.66
    âĶĢâĶĢâĶĢâĶĢ
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.