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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols suggesting technical or programming language elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hawaiian
    -0.19
     Wisconsin
    -0.19
     Hawaii
    -0.19
     Maryland
    -0.18
     Thai
    -0.17
     Pennsylvania
    -0.17
     Milwaukee
    -0.16
     Florida
    -0.16
     Vietnam
    -0.16
    Thai
    -0.16
    POSITIVE LOGITS
     Leone
    0.30
     Night
    0.30
     Tat
    0.29
    Night
    0.27
     Ak
    0.24
     Bul
    0.22
     Nacht
    0.22
     NIGHT
    0.22
     Assass
    0.22
     Mine
    0.21
    Act Density 0.001%

    No Known Activations