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

    Neuronpedia

    INDEX
    Explanations

    locations and distances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating geographical locations and their distances from notable landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Prev
    -0.69
    appropriate
    -0.69
    impro
    -0.68
    */(
    -0.64
    oret
    -0.64
    Versions
    -0.63
    Community
    -0.62
    CHO
    -0.62
     Cosponsors
    -0.60
    Helper
    -0.58
    POSITIVE LOGITS
     downtown
    1.08
     Baghdad
    1.06
     Perth
    1.03
     Anchorage
    1.02
     town
    1.01
     Bethlehem
    0.99
     Indianapolis
    0.97
     Interstate
    0.96
     Pittsburgh
    0.94
     Kabul
    0.94
    Act Density 0.082%

    No Known Activations