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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of "Month Year" with higher activations, suggesting it may be looking for specific time references

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and related numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.76
    mund
    -0.59
     sidx
    -0.54
    iland
    -0.54
    itiveness
    -0.54
     flares
    -0.53
    anchester
    -0.53
    ido
    -0.52
     deserts
    -0.50
    uras
    -0.50
    POSITIVE LOGITS
    scl
    0.75
    eligible
    0.64
    ilts
    0.61
    dfx
    0.58
     Coffin
    0.56
    cf
    0.56
    hospital
    0.54
    payer
    0.53
     Jury
    0.53
    daughter
    0.52
    Act Density 1.412%

    No Known Activations