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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ()<<"
    -0.07
     Messi
    -0.07
    安康
    -0.07
     decis
    -0.07
     genç
    -0.07
     energies
    -0.06
    哈尔
    -0.06
    💒
    -0.06
     заяв
    -0.06
    Usu
    -0.06
    POSITIVE LOGITS
     quarantine
    0.08
    䓫
    0.07
    _sep
    0.07
    Spawn
    0.07
    monitor
    0.07
     reclaim
    0.07
     Callback
    0.07
     hypocrisy
    0.07
     pathological
    0.06
    IM
    0.06
    Act Density 0.079%

    No Known Activations