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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bsch
    0.51
     სან
    0.50
    gz
    0.47
    ༘
    0.47
     on
    0.46
    )-\
    0.46
    🐞
    0.45
    $-$
    0.44
    qz
    0.44
    \;
    0.43
    POSITIVE LOGITS
     laminate
    0.46
    Lak
    0.45
     Tenure
    0.45
     Neural
    0.44
     tenure
    0.43
     Lak
    0.43
     Oversight
    0.43
     stone
    0.42
     forcing
    0.42
     Potato
    0.42
    Act Density 0.003%

    No Known Activations