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

    Neuronpedia

    INDEX
    Explanations

    phrases in a specific regional language

    oai_token-act-pair · gpt-3.5-turbo

    elements related to personal identity and cultural expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cub
    -0.79
    casters
    -0.71
    Series
    -0.69
     Swordsman
    -0.68
    Plex
    -0.67
    VIDEO
    -0.66
    RESULTS
    -0.66
    GROUP
    -0.66
     Spotlight
    -0.65
     Revelations
    -0.65
    POSITIVE LOGITS
     ki
    1.50
     ja
    1.48
     ko
    1.40
     ka
    1.39
     ke
    1.33
     kan
    1.21
     k
    1.21
     tu
    1.18
     kh
    1.17
     ni
    1.17
    Act Density 0.166%

    No Known Activations