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

    Neuronpedia

    INDEX
    Explanations

    references to structured objectives or aims in research contexts, especially involving tables and data representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "2" after specific tokens

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fourth
    -0.99
     Fourth
    -0.88
    Fourth
    -0.87
     fifth
    -0.86
     sixth
    -0.85
     seventh
    -0.84
     ninth
    -0.80
    第四
    -0.79
    fourth
    -0.78
     eighth
    -0.78
    POSITIVE LOGITS
     secondly
    1.17
     Secondly
    1.09
     second
    1.02
     Kedua
    0.99
    Secondly
    0.97
    二
    0.95
     Second
    0.94
     deux
    0.94
     kedua
    0.93
     zwe
    0.93
    Act Density 0.510%

    No Known Activations