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

    Neuronpedia

    INDEX
    Explanations

    instances where people meet or interact in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "met"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.79
    Ħ¢
    -0.71
    cember
    -0.71
    ignt
    -0.68
    wrap
    -0.67
    adoes
    -0.66
    container
    -0.66
    ¥ŀ
    -0.65
    ItemTracker
    -0.65
    ļéĨĴ
    -0.63
    POSITIVE LOGITS
    amorph
    1.05
    ropolis
    1.00
    ropolitan
    0.83
     Meet
    0.80
     met
    0.80
    ered
    0.80
    aunt
    0.78
     Valhalla
    0.73
    allic
    0.73
    tle
    0.71
    Act Density 0.015%

    No Known Activations