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

    Neuronpedia

    INDEX
    Explanations

    locations or places related to a specific city

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of San Jose or cities starting with "San"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.75
    ilater
    -0.71
    llor
    -0.71
    ï¸ı
    -0.68
    xual
    -0.68
    mercial
    -0.63
    llers
    -0.63
    anwhile
    -0.63
     numbering
    -0.63
     Wink
    -0.61
    POSITIVE LOGITS
    San
    1.14
     Francisco
    1.10
     Diego
    1.04
    ctuary
    1.01
     Antonio
    0.98
    ibel
    0.94
    gha
    0.93
    ction
    0.93
    itary
    0.92
    Disk
    0.90
    Act Density 0.020%

    No Known Activations