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

    Neuronpedia

    INDEX
    Explanations

    dates and events as described by names and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates and times in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ($)
    -0.67
    GOP
    -0.62
    illard
    -0.61
    ront
    -0.60
    ritis
    -0.60
    killer
    -0.60
    olds
    -0.59
    inge
    -0.59
    rolet
    -0.58
    rote
    -0.58
    POSITIVE LOGITS
     January
    1.26
     December
    1.26
     February
    1.26
     September
    1.25
     October
    1.24
     August
    1.24
     November
    1.23
     behalf
    1.23
     July
    1.22
     April
    1.20
    Act Density 0.109%

    No Known Activations