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

    Neuronpedia

    INDEX
    Explanations

    references to celebrations or events related to holidays

    oai_token-act-pair · gpt-3.5-turbo

    mentions of holidays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lev
    -0.71
    nered
    -0.68
    PLA
    -0.67
     Keller
    -0.66
    uclear
    -0.62
     Canal
    -0.60
    ECH
    -0.60
    gel
    -0.60
     Haitian
    -0.59
    DE
    -0.58
    POSITIVE LOGITS
     holidays
    1.15
    idays
    1.06
    hops
    0.79
     festivities
    0.78
     vacations
    0.77
    urnal
    0.77
     weekends
    0.76
     weekend
    0.76
     anniversary
    0.76
    cot
    0.75
    Act Density 0.009%

    No Known Activations