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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.89
     myſelf
    -0.85
     themſelves
    -0.80
     himſelf
    -0.78
     Conſ
    -0.72
     itſelf
    -0.71
    neſs
    -0.70
     Theſe
    -0.69
    + 
    -0.69
     unknownFields
    -0.69
    POSITIVE LOGITS
    Fig
    2.14
    Figure
    1.86
     Fig
    1.70
     Figure
    1.49
    Figs
    1.15
     Figs
    1.11
    Table
    1.08
    Рис
    0.96
    Figura
    0.91
    FIGURE
    0.88
    Act Density 0.283%

    No Known Activations