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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     highly
    -0.48
     formerly
    -0.47
    りに
    -0.46
     expressed
    -0.46
     previously
    -0.45
     Highly
    -0.45
    的有
    -0.44
    selle
    -0.43
    upu
    -0.43
    IDO
    -0.43
    POSITIVE LOGITS
     חיצוניים
    1.05
    AddTagHelper
    0.91
    transQ
    0.84
    oa̍t
    0.83
    OGND
    0.80
     ProtoMessage
    0.80
    ForRow
    0.78
     Meksiku
    0.76
     Audiodateien
    0.76
     للاسماء
    0.75
    Act Density 0.052%

    No Known Activations