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

    Neuronpedia

    INDEX
    Explanations

    apostrophes indicating possession or contractions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    sizeCache
    -1.07
    DockStyle
    -0.89
    seamnă
    -0.85
     ThemeData
    -0.84
     BoxDecoration
    -0.78
    UnitTesting
    -0.77
     industriels
    -0.76
    Datuak
    -0.76
    ISupport
    -0.74
     centrales
    -0.73
    POSITIVE LOGITS
    Affirmed
    0.50
     hit
    0.49
     she
    0.48
     Is
    0.46
     
    0.45
     told
    0.45
     ne
    0.44
     NY
    0.43
    рое
    0.42
     multi
    0.42
    Act Density 0.004%

    No Known Activations