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

    Neuronpedia

    INDEX
    Explanations

    titles of films or productions, particularly those that convey significant themes or stories.

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

    information regarding specific events or developments.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    articles ("the", "a", "an") and other common grammatical elements at the start of sentences or clauses.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    "The" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    the followed by descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.72
    存于互联网档案馆
    -0.69
     виправивши
    -0.68
     outros
    -0.65
    دانشنامهٔ
    -0.65
    +#+#
    -0.62
     Процитовано
    -0.59
     baik
    -0.58
    的其他
    -0.57
    ItemBackground
    -0.56
    POSITIVE LOGITS
     sprawling
    0.92
     multi
    0.81
     highly
    0.81
     densely
    0.80
     richly
    0.80
     heavily
    0.79
     widely
    0.78
     multifaceted
    0.77
    highly
    0.76
     lengthy
    0.74
    Act Density 0.310%

    No Known Activations