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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     digestibility
    1.25
    tn
    1.22
    jLabel
    1.21
    thm
    1.19
    <0xB0>
    1.18
     spinster
    1.17
    deaths
    1.15
    📷
    1.14
    deviation
    1.14
     casualties
    1.14
    POSITIVE LOGITS
    леп
    1.11
    на
    1.02
     Kung
    1.01
     Kong
    1.01
    aient
    0.99
     Mensch
    0.97
     Оте
    0.95
    л
    0.95
     Capítulo
    0.94
    रिक
    0.94
    Act Density 0.000%

    No Known Activations