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

    Neuronpedia

    INDEX
    Explanations

    dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring yearly events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xe
    -0.71
     flipped
    -0.64
     spoiler
    -0.64
    walker
    -0.62
    xc
    -0.60
    Reply
    -0.60
    oldemort
    -0.59
     manip
    -0.59
    lead
    -0.59
    isters
    -0.59
    POSITIVE LOGITS
     annual
    3.61
     yearly
    2.72
     Annual
    2.66
     annually
    2.08
     monthly
    2.03
     quarterly
    1.95
     weekly
    1.71
    ennial
    1.65
     periodic
    1.56
     Monthly
    1.32
    Act Density 0.011%

    No Known Activations