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

    Neuronpedia

    INDEX
    Explanations

    words related to the city of San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    references to San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stall
    -0.82
    lain
    -0.79
    taker
    -0.74
    pins
    -0.74
    berus
    -0.69
    hift
    -0.69
    pin
    -0.68
    abase
    -0.65
     Kant
    -0.65
    etsk
    -0.63
    POSITIVE LOGITS
    WA
    1.00
    PD
    0.98
    ML
    0.97
    ORE
    0.96
    ORTS
    0.92
    DC
    0.90
    DP
    0.88
    RA
    0.87
    DF
    0.87
     Chronicle
    0.86
    Act Density 0.015%

    No Known Activations