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

    Neuronpedia

    INDEX
    Explanations

    words related to specific geographical locations, particularly cities such as NY (New York), SF (San Francisco), and NJ (New Jersey)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations or regions, particularly New York and San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.73
     Gustav
    -0.65
     Danish
    -0.64
    framework
    -0.63
     Finnish
    -0.63
     functioning
    -0.63
     Swedish
    -0.62
     Notting
    -0.62
     eg
    -0.61
    wagen
    -0.60
    POSITIVE LOGITS
    RA
    1.31
    OTUS
    1.29
    WA
    1.26
    FW
    1.23
    PD
    1.21
    BI
    1.19
    RB
    1.19
    DP
    1.18
    DEP
    1.17
    SO
    1.17
    Act Density 0.065%

    No Known Activations