INDEX
    Explanations

    demonstrative pronouns

    This neuron activates on Portuguese words.

    New Auto-Interp
    Negative Logits
    Theo
    -0.07
    ipsoid
    -0.07
    //
    -0.07
    Dice
    -0.06
     Couldn
    -0.06
     เง
    -0.06
    iac
    -0.06
    -0.06
    parity
    -0.06
     pist
    -0.06
    POSITIVE LOGITS
    _DOUBLE
    0.07
    					    
    0.07
    ahaha
    0.07
     ConcurrentHashMap
    0.07
    					      
    0.07
     IGNORE
    0.06
    _wrap
    0.06
    (L
    0.06
    (sh
    0.06
    <ll
    0.06
    Act Density 0.089%

    No Known Activations