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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to individuals or specific characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Hit" and references to specific individuals or entities with the names "Hol" and "Sher."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Qiao
    -0.86
     Slate
    -0.84
     Rao
    -0.80
     Kali
    -0.78
     Conway
    -0.76
     Katrina
    -0.76
     Olympia
    -0.76
     Rice
    -0.75
     Coral
    -0.75
     Reed
    -0.75
    POSITIVE LOGITS
    Hit
    3.17
    Hol
    1.86
    Sher
    1.33
    Mer
    1.33
    Mess
    1.29
    Down
    1.27
    Rad
    1.21
    Church
    1.21
    Shin
    1.21
    Jew
    1.19
    Act Density 0.048%

    No Known Activations