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

    Neuronpedia

    INDEX
    Explanations

    numbers with monetary values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to financial statistics and population figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irie
    -0.80
    sburg
    -0.68
    ¬¼
    -0.66
    ħĭ
    -0.66
    oslav
    -0.64
    ²¾
    -0.62
    ahu
    -0.62
    icial
    -0.60
    ¤
    -0.58
    ctor
    -0.58
    POSITIVE LOGITS
     respectively
    1.12
    000
    1.01
    Downloadha
    1.00
     according
    0.97
     plus
    0.94
     excluding
    0.92
    depending
    0.91
     including
    0.90
    according
    0.89
     whereas
    0.87
    Act Density 0.379%

    No Known Activations