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

    Neuronpedia

    INDEX
    Explanations

    the word "Troy" or related variations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    unknown
    -0.69
    ipper
    -0.68
    backer
    -0.66
    iations
    -0.64
    INESS
    -0.64
    iating
    -0.62
    iator
    -0.62
    iation
    -0.62
    urations
    -0.61
    otine
    -0.61
    POSITIVE LOGITS
    ©¶æ¥µ
    0.90
    anus
    0.80
    alties
    0.77
    eah
    0.76
    master
    0.76
    alty
    0.76
    e
    0.74
    unal
    0.74
    ð
    0.73
    §
    0.73
    Act Density 0.057%

    No Known Activations