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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of feature films

    oai_token-act-pair · gpt-3.5-turbo

    references to feature films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignt
    -0.71
     ALP
    -0.70
     Klux
    -0.69
    ça
    -0.69
    vernment
    -0.68
    cale
    -0.67
    hiba
    -0.66
     conflic
    -0.64
    alty
    -0.64
    女
    -0.63
    POSITIVE LOGITS
    icle
    1.14
    icles
    1.02
     prominently
    0.99
    ttes
    0.95
    Feature
    0.84
    orial
    0.82
    aceous
    0.82
    film
    0.82
    iful
    0.82
    icularly
    0.78
    Act Density 0.057%

    No Known Activations