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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of embarrassment or shame

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names associated with notable individuals or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thickness
    -0.72
    bones
    -0.71
     graz
    -0.69
    sheet
    -0.69
     detectors
    -0.69
    cules
    -0.66
    illac
    -0.66
    roma
    -0.66
    itton
    -0.65
    rock
    -0.63
    POSITIVE LOGITS
    ingu
    0.80
    ums
    0.78
    itute
    0.78
    atory
    0.76
    ãĥł
    0.72
    ospace
    0.72
    itution
    0.72
    upid
    0.72
    ð
    0.71
     Genesis
    0.70
    Act Density 0.030%

    No Known Activations