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

    Neuronpedia

    INDEX
    Explanations

    references to encyclopedias and dictionaries

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.57
    UrlResolution
    -0.54
    TypedDataSet
    -0.53
     оригіналу
    -0.50
    ✭✭
    -0.50
    Kast
    -0.50
    izung
    -0.50
     Skyline
    -0.49
    UIControlState
    -0.48
    twimg
    -0.48
    POSITIVE LOGITS
     encyclopedia
    0.80
     Encyclopedia
    0.79
    Encyclopedia
    0.73
     Encyclopaedia
    0.70
    Encyclo
    0.64
    
    0.63
    encyclo
    0.63
    وعة
    0.61
     encyclo
    0.60
     dictionaries
    0.60
    Act Density 0.009%

    No Known Activations