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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    い
    1.11
    rat
    1.03
    any
    1.02
    onto
    0.99
    er
    0.96
    rangle
    0.96
    roughly
    0.88
    foreach
    0.86
     पान
    0.86
    βα
    0.86
    POSITIVE LOGITS
    ك
    1.50
    นาน
    1.32
     latter
    1.32
    nosis
    1.29
    اح
    1.22
     amplitudes
    1.21
    𝘻
    1.20
     choses
    1.19
    tio
    1.18
    ⺠
    1.18
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.