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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers related to dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Honest
    -0.18
    ium
    -0.18
     office
    -0.17
    area
    -0.17
     official
    -0.16
     Ho
    -0.16
     issue
    -0.16
    office
    -0.15
     area
    -0.15
    onia
    -0.15
    POSITIVE LOGITS
    ault
    0.16
    antee
    0.16
    ży
    0.15
    EATURE
    0.15
    áce
    0.15
    ptune
    0.14
    (Level
    0.14
    θε
    0.14
    ibr
    0.14
    untime
    0.14
    Act Density 0.009%

    No Known Activations