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

    Neuronpedia

    INDEX
    Explanations

    URLs and web page paths

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    hoeddwyd
    -0.91
    الحياه
    -0.77
     AssemblyCulture
    -0.75
    icitis
    -0.75
    ̈́
    -0.74
     EnglishChoose
    -0.72
     يتيمه
    -0.72
    Personensuche
    -0.69
    eradish
    -0.68
    出版年
    -0.67
    POSITIVE LOGITS
     
    0.50
     Mer
    0.50
    -
    0.49
     -
    0.48
    ?
    0.47
     “
    0.46
    let
    0.44
     i
    0.44
     Let
    0.43
     Don
    0.43
    Act Density 0.022%

    No Known Activations