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

    Neuronpedia

    INDEX
    Explanations

    words related to tall structures or buildings

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical structures and items, particularly in the context of buildings and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neut
    -0.74
    ndra
    -0.73
     pestic
    -0.69
    cedented
    -0.65
    chwitz
    -0.65
     misunder
    -0.64
     exha
    -0.63
    uctions
    -0.63
    iltr
    -0.63
    iris
    -0.62
    POSITIVE LOGITS
    oute
    0.67
    ught
    0.63
    aneously
    0.62
    hedon
    0.62
    ***
    0.60
    lihood
    0.60
    VER
    0.60
    board
    0.58
    ishly
    0.57
    allah
    0.57
    Act Density 0.259%

    No Known Activations