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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     advisors
    -0.09
    jump
    -0.07
     cmd
    -0.07
     kurz
    -0.07
     IT
    -0.07
    _INFINITY
    -0.07
     cockpit
    -0.07
    erot
    -0.07
     рожд
    -0.07
     oz
    -0.07
    POSITIVE LOGITS
    왼
    0.09
    很难
    0.08
    הול
    0.08
    Cancelar
    0.08
    Dallas
    0.07
    アン
    0.07
    瘋
    0.07
    認為
    0.07
    郑重
    0.07
    gte
    0.06
    Act Density 0.000%

    No Known Activations