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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values or codes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    лябин
    -0.58
    AddTagHelper
    -0.54
    مصادر
    -0.52
     kimia
    -0.51
    featureID
    -0.50
    TemporalType
    -0.49
    íncia
    -0.49
     récon
    -0.49
    ://$
    -0.49
     edif
    -0.49
    POSITIVE LOGITS
     []:
    0.63
    expandindo
    0.63
     Swedes
    0.56
     packers
    0.55
     ſeveral
    0.54
     gneiss
    0.53
    کز
    0.52
    SuppressLint
    0.51
    ientôt
    0.49
     corne
    0.49
    Act Density 0.002%

    No Known Activations