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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "abb", specifically at different activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to specific terms related to "Abbott."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    piece
    -0.72
    ptives
    -0.66
     Cheong
    -0.63
    govtrack
    -0.63
    stanbul
    -0.63
     Gutenberg
    -0.61
     obser
    -0.60
    xia
    -0.59
     erosion
    -0.59
    stal
    -0.59
    POSITIVE LOGITS
    ucket
    1.03
    itt
    1.02
    arella
    0.98
    itte
    0.95
    atical
    0.90
    its
    0.90
    atar
    0.89
    inic
    0.86
    ler
    0.86
    inical
    0.86
    Act Density 0.029%

    No Known Activations