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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    LD
    -0.07
     typ
    -0.07
    手续
    -0.07
     keto
    -0.07
     tob
    -0.07
     ambigu
    -0.07
    .FullName
    -0.07
    武士
    -0.07
    银河
    -0.06
     substr
    -0.06
    POSITIVE LOGITS
     Intelligence
    0.07
    intelligence
    0.07
    师事务所
    0.06
    -day
    0.06
     breeze
    0.06
     opportunity
    0.06
     באמת
    0.06
    portunity
    0.06
    .frequency
    0.06
    ーター
    0.06
    Act Density 0.025%

    No Known Activations