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

    Neuronpedia

    INDEX
    Explanations

    references to specific centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to historical time periods or centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.76
    Rules
    -0.73
    Cra
    -0.70
    glomer
    -0.64
    activation
    -0.63
    infeld
    -0.63
    iguous
    -0.63
    BIL
    -0.62
    uploads
    -0.62
    ket
    -0.62
    POSITIVE LOGITS
    eenth
    1.26
    ieth
    1.09
     century
    1.08
    teenth
    0.91
    century
    0.90
     Century
    0.86
     inning
    0.85
    irty
    0.84
    venth
    0.83
    ousand
    0.82
    Act Density 0.034%

    No Known Activations