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

    Neuronpedia

    INDEX
    Explanations

    words related to documentaries

    oai_token-act-pair · gpt-3.5-turbo

    references to documentaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.89
    hr
    -0.79
    seless
    -0.78
    hare
    -0.73
    olen
    -0.71
    arching
    -0.70
    ingers
    -0.69
    othes
    -0.67
    regulated
    -0.66
    adding
    -0.66
    POSITIVE LOGITS
     documentary
    1.16
     filmmaker
    1.04
     filmmaking
    0.97
     documentaries
    0.96
     filmmakers
    0.85
     film
    0.84
    document
    0.82
     Surviv
    0.80
    thouse
    0.79
    ÃįÃį
    0.78
    Act Density 0.024%

    No Known Activations