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

    Neuronpedia

    INDEX
    Explanations

    specific locations described by block numbers and street names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reperto
    -0.70
     oblig
    -0.67
    ãĤ§
    -0.66
    =-=-=-=-=-=-=-=-
    -0.66
    âĻ¥
    -0.64
     submar
    -0.63
    ually
    -0.61
     underestimate
    -0.60
    />
    -0.59
     perv
    -0.58
    POSITIVE LOGITS
     flats
    1.03
     stairs
    0.72
     latitude
    0.69
    isSpecialOrderable
    0.66
     Dover
    0.65
     Northwest
    0.65
     scrimmage
    0.64
     Northeast
    0.64
     Highway
    0.63
     Columbus
    0.63
    Act Density 0.057%

    No Known Activations