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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aspect
    -0.07
     цей
    -0.07
    _restrict
    -0.07
     listener
    -0.07
    VEL
    -0.06
    ITOR
    -0.06
    expr
    -0.06
    reset
    -0.06
    베
    -0.06
     lui
    -0.06
    POSITIVE LOGITS
     committing
    0.07
    .hh
    0.06
    GB
    0.06
     GB
    0.06
     đột
    0.06
     ()=>
    0.06
     좀
    0.06
       ↵
    0.06
    _Tool
    0.06
    onte
    0.06
    Act Density 0.001%

    No Known Activations