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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and common words in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GeoNames
    -0.82
    Portály
    -0.80
     HasFactory
    -0.78
     kasarigan
    -0.78
     indígen
    -0.75
     estekak
    -0.75
    desertcart
    -0.75
     Majefty
    -0.74
    retudo
    -0.74
     desmotivaciones
    -0.73
    POSITIVE LOGITS
     get
    0.57
     ανα
    0.54
     Get
    0.54
     take
    0.52
     المت
    0.52
     Dis
    0.52
     is
    0.51
     be
    0.51
     dis
    0.50
    Get
    0.49
    Act Density 0.193%

    No Known Activations