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

    Neuronpedia

    INDEX
    Explanations

    references to specific nodes in a graph or data structure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.82
     >=",
    -0.77
     nakalista
    -0.65
    IsContent
    -0.64
    rinfo
    -0.63
     تانيه
    -0.62
     estekak
    -0.61
    </tfoot>
    -0.60
    EndInit
    -0.60
    oureuse
    -0.60
    POSITIVE LOGITS
     Lansing
    0.57
     Dess
    0.56
     senior
    0.52
    xtext
    0.51
     “
    0.50
     anh
    0.50
    phas
    0.50
    LOTTE
    0.49
     &'
    0.48
    HomeComponent
    0.48
    Act Density 0.008%

    No Known Activations