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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Restaurant
    -0.08
    restore
    -0.08
    (state
    -0.08
    十个
    -0.08
    .free
    -0.07
    (runtime
    -0.07
     trail
    -0.07
    _CD
    -0.07
    (map
    -0.07
     존재
    -0.07
    POSITIVE LOGITS
    Unc
    0.07
    EX
    0.07
     abril
    0.06
    汕头
    0.06
    NOT
    0.06
    TI
    0.06
    決め
    0.06
     Britain
    0.06
    ników
    0.06
    abez
    0.06
    Act Density 0.002%

    No Known Activations