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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     upravo
    0.58
     piena
    0.52
     tentativas
    0.48
     cidade
    0.48
     nome
    0.48
     untrue
    0.48
     essayer
    0.48
     ofic
    0.47
     restaurant
    0.46
     utwor
    0.46
    POSITIVE LOGITS
    Synced
    0.47
     Ф
    0.46
    Joke
    0.46
    Quota
    0.45
    Cand
    0.44
    Came
    0.44
    Mystery
    0.43
    Trace
    0.42
    Jump
    0.42
    Mind
    0.42
    Act Density 0.001%

    No Known Activations