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

    Neuronpedia

    INDEX
    Explanations

    phrases describing someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional characters or storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.94
    onies
    -0.85
    olutions
    -0.78
     suites
    -0.78
    alysis
    -0.76
     calendars
    -0.76
    seys
    -0.75
     platforms
    -0.75
     departures
    -0.74
     exposures
    -0.74
    POSITIVE LOGITS
     himself
    1.31
     Adolf
    1.05
     Himself
    1.03
    someone
    0.99
     dictator
    0.98
     persona
    0.96
     narrator
    0.96
     businessman
    0.96
     ruler
    0.93
     grandson
    0.93
    Act Density 0.833%

    No Known Activations