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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Else
    -0.78
    cale
    -0.72
    conom
    -0.68
    Fram
    -0.68
    yth
    -0.67
    Reviewer
    -0.64
     Ye
    -0.64
    Cole
    -0.62
     Attribution
    -0.62
     Yog
    -0.61
    POSITIVE LOGITS
    uca
    0.93
    itars
    0.67
    awei
    0.66
    querque
    0.65
    enhagen
    0.65
     lav
    0.63
    illet
    0.62
    aucuses
    0.62
    isoft
    0.62
     embassies
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.