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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rated
    -0.15
    ÙĪÙĨد
    -0.15
    ILED
    -0.14
    βε
    -0.14
    sss
    -0.14
    called
    -0.13
     LENG
    -0.13
    amt
    -0.13
    ico
    -0.13
    ase
    -0.13
    POSITIVE LOGITS
     used
    0.18
     USED
    0.16
    _used
    0.16
    emple
    0.15
    USED
    0.15
     they
    0.15
    bara
    0.15
     Used
    0.15
     being
    0.14
     parach
    0.14
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.