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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "this" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickets
    -0.74
    rics
    -0.69
    ular
    -0.67
    tery
    -0.64
    gans
    -0.64
    stones
    -0.64
    sers
    -0.61
    cases
    -0.61
    icons
    -0.60
    riott
    -0.60
    POSITIVE LOGITS
     week
    1.58
     morning
    1.53
     afternoon
    1.50
     weekend
    1.49
     month
    1.39
     evening
    1.30
     summer
    1.28
     year
    1.18
     past
    1.18
     spring
    1.17
    Act Density 0.078%

    No Known Activations