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

    Neuronpedia

    INDEX
    Explanations

    addresses, states, and cities

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographical names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rez
    -0.76
    zers
    -0.74
    thood
    -0.73
    advertisement
    -0.71
    retched
    -0.70
    epad
    -0.70
    obin
    -0.68
    iosyncr
    -0.66
    ullivan
    -0.65
    sbm
    -0.65
    POSITIVE LOGITS
     TN
    1.31
     TX
    1.28
     CA
    1.14
     FL
    1.13
     IL
    1.10
     KY
    1.10
     WA
    1.09
     VA
    1.07
     OH
    1.05
     GA
    1.03
    Act Density 0.063%

    No Known Activations