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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     evacuate
    -0.08
    .python
    -0.07
    שאיר
    -0.07
     sworn
    -0.07
     stumble
    -0.07
    umbnail
    -0.07
     fps
    -0.06
     '>'
    -0.06
     Decision
    -0.06
    𝒸
    -0.06
    POSITIVE LOGITS
     Planner
    0.07
    	back
    0.07
     pł
    0.07
    (),↵
    0.07
    Stats
    0.07
     BED
    0.06
     Beam
    0.06
    Prostit
    0.06
     wired
    0.06
    说着
    0.06
    Act Density 0.001%

    No Known Activations