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

    Neuronpedia

    INDEX
    Explanations

    locations with associated dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" related to various locations and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.67
    arth
    -0.66
    REL
    -0.65
    hement
    -0.64
     concedes
    -0.62
    anon
    -0.62
    henko
    -0.61
    lando
    -0.60
     assures
    -0.60
    killed
    -0.59
    POSITIVE LOGITS
     winter
    0.72
    ember
    0.66
     September
    0.66
     tourist
    0.65
    soDeliveryDate
    0.64
     Week
    0.64
    ignt
    0.63
     behalf
    0.62
     1893
    0.62
    FINE
    0.62
    Act Density 0.289%

    No Known Activations