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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -basic
    -0.07
     entries
    -0.06
     الذه
    -0.06
     comprehension
    -0.06
    _si
    -0.06
    .Car
    -0.06
     towns
    -0.06
     Menschen
    -0.06
    Markers
    -0.06
    -flex
    -0.06
    POSITIVE LOGITS
     dictator
    0.07
    	fire
    0.07
     }},↵
    0.07
     vb
    0.06
     mů
    0.06
    Guard
    0.06
    가능
    0.06
     встре
    0.06
     witnessing
    0.06
    SYM
    0.06
    Act Density 0.046%

    No Known Activations