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

    Neuronpedia

    INDEX
    Explanations

    references to specific years

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "year" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     textual
    -0.84
     cumbers
    -0.77
     zipper
    -0.74
     chains
    -0.72
     encl
    -0.67
     Tray
    -0.62
     collar
    -0.62
    esse
    -0.62
    cro
    -0.62
     descent
    -0.61
    POSITIVE LOGITS
    long
    1.02
    book
    0.82
    mberg
    0.74
     anniversary
    0.71
    å¹
    0.71
    lled
    0.69
     æľ
    0.69
     ago
    0.68
    lins
    0.68
    é¾įåĸļ士
    0.67
    Act Density 0.085%

    No Known Activations