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

    Neuronpedia

    INDEX
    Explanations

    specific street names and locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and street names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     genetically
    -0.78
    advertisement
    -0.74
     exorc
    -0.72
     persecuted
    -0.70
    CLAIM
    -0.70
     dictator
    -0.70
    ccording
    -0.70
     Canaver
    -0.69
     contagious
    -0.69
     underdog
    -0.67
    POSITIVE LOGITS
     Junction
    1.51
     Boulevard
    1.42
     Airport
    1.34
     Avenue
    1.33
     Station
    1.27
     Streets
    1.26
     Plaza
    1.24
     Blvd
    1.23
     Parkway
    1.22
     Shopping
    1.22
    Act Density 0.328%

    No Known Activations