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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographic locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Richards
    -0.77
     Cah
    -0.77
     Rica
    -0.76
     Wiz
    -0.76
     Mermaid
    -0.73
     Shutterstock
    -0.73
     Norris
    -0.73
     Moreno
    -0.72
     Twain
    -0.70
     Shaw
    -0.70
    POSITIVE LOGITS
    bodied
    1.44
    sounding
    1.40
    sized
    1.35
    level
    1.30
    eyed
    1.28
    minded
    1.26
    based
    1.24
    enough
    1.22
    looking
    1.19
    to
    1.19
    Act Density 0.425%

    No Known Activations