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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ovi
    0.43
    कृति
    0.40
    pak
    0.39
     worry
    0.38
    穩定
    0.38
     Presiden
    0.38
    タイ
    0.37
     $:
    0.37
     تیل
    0.37
     foul
    0.37
    POSITIVE LOGITS
    酉
    0.49
     वान
    0.49
     وین
    0.46
     circost
    0.46
     delimited
    0.46
    andır
    0.46
     Apo
    0.45
     IPs
    0.45
    шками
    0.45
     apocalyptic
    0.44
    Act Density 0.001%

    No Known Activations