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

    Neuronpedia

    INDEX
    Explanations

    references to specific data entries or points within a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kwargs
    -0.83
     viewModel
    -0.77
     whiteColor
    -0.75
    ❯
    -0.73
    "}>
    -0.72
    Berikut
    -0.72
    펙
    -0.72
    FieldBuilder
    -0.72
    ']?>
    -0.70
     moonlight
    -0.70
    POSITIVE LOGITS
     entry
    1.92
     Entry
    1.83
    entry
    1.76
     entries
    1.73
    Entry
    1.69
     ENTRY
    1.69
     Entries
    1.65
    Entries
    1.65
    ENTRY
    1.60
    entries
    1.59
    Act Density 0.057%

    No Known Activations