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

    Neuronpedia

    INDEX
    Explanations

    film directors and their respective countries

    oai_token-act-pair · gpt-3.5-turbo

    references to film directors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peb
    -0.72
     Jericho
    -0.67
    tics
    -0.65
    arov
    -0.62
    ovych
    -0.61
    orie
    -0.61
     Homes
    -0.58
     Canadians
    -0.58
     Candy
    -0.58
    achine
    -0.58
    POSITIVE LOGITS
    igible
    1.27
    iger
    0.86
     Dir
    0.83
    renheit
    0.82
    vana
    0.82
    bys
    0.79
    nit
    0.79
    igent
    0.79
    sb
    0.75
    idon
    0.74
    Act Density 0.027%

    No Known Activations