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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods in the past

    oai_token-act-pair · gpt-3.5-turbo

    instances of time references related to previous events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.72
    ixtape
    -0.68
    hma
    -0.68
    uilt
    -0.65
    urrent
    -0.63
    checks
    -0.63
    asting
    -0.63
    asts
    -0.62
    icket
    -0.60
    cases
    -0.60
    POSITIVE LOGITS
     ago
    1.17
    èª
    0.73
     Invalid
    0.70
     Ago
    0.69
     goodbye
    0.67
     Ples
    0.67
    MpServer
    0.65
    fw
    0.65
    terday
    0.63
     sunset
    0.62
    Act Density 0.016%

    No Known Activations