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

    Neuronpedia

    INDEX
    Explanations

    words related to specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and cultural identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.83
    asio
    -0.74
     Canaver
    -0.73
     yourselves
    -0.69
    vier
    -0.67
     yourself
    -0.64
    thia
    -0.64
    auri
    -0.64
     Chung
    -0.62
     Runner
    -0.62
    POSITIVE LOGITS
     counterparts
    1.32
     counterpart
    1.15
     namesake
    0.93
     brethren
    0.87
     cousins
    0.86
     career
    0.81
     cousin
    0.80
     predicament
    0.80
     persona
    0.79
     peers
    0.79
    Act Density 0.631%

    No Known Activations