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

    Neuronpedia

    INDEX
    Explanations

    mentions of boxes or bags.

    oai_token-act-pair · gemini-2.0-flashTriggered by @johnny

    references to physical containers or packages, particularly boxes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of boxes and bags

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

    nouns related to containers, specifically "boxes."

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.73
    Phys
    -0.73
    Leader
    -0.68
    ERAL
    -0.66
     Nation
    -0.66
    oÄŁ
    -0.65
    liest
    -0.65
    gh
    -0.64
    rawdownloadcloneembedreportprint
    -0.64
    Synopsis
    -0.63
    POSITIVE LOGITS
    paces
    1.27
    mith
    1.25
    hops
    1.22
    poons
    1.21
    ourcing
    1.18
    ongs
    1.17
    uggest
    1.15
    hips
    1.14
    pots
    1.11
    hooting
    1.05
    Act Density 0.076%

    No Known Activations