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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atsu
    -0.17
    icol
    -0.15
    uset
    -0.15
    едж
    -0.15
    AndServe
    -0.14
    UBY
    -0.14
    ldre
    -0.14
    449
    -0.14
     fucked
    -0.14
    883
    -0.13
    POSITIVE LOGITS
     Wol
    0.17
     output
    0.17
     sector
    0.16
    ince
    0.15
    kowski
    0.15
    ż
    0.14
     inflation
    0.14
    ],[-
    0.13
     manufacturing
    0.13
     expans
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.