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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to movies or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     èĬ
    -0.15
    apas
    -0.14
    ales
    -0.14
     Shi
    -0.14
    å¢
    -0.14
    еком
    -0.14
    pike
    -0.13
     Morav
    -0.13
     morph
    -0.13
     Ngh
    -0.13
    POSITIVE LOGITS
     rang
    0.30
    rang
    0.18
     film
    0.18
    film
    0.18
     bay
    0.18
    Film
    0.18
     selenium
    0.18
     Film
    0.17
     Screw
    0.17
     rewind
    0.17
    Act Density 0.002%

    No Known Activations