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

    Neuronpedia

    INDEX
    Explanations

    notable performances by actors in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elves
    -0.15
    oppers
    -0.15
     Thema
    -0.14
    irts
    -0.14
    ells
    -0.14
    (strict
    -0.13
    itoris
    -0.13
     skip
    -0.13
    .roll
    -0.13
    ovel
    -0.13
    POSITIVE LOGITS
    ppe
    0.18
    飾
    0.16
     facial
    0.16
     PERFORMANCE
    0.16
    vac
    0.16
    spa
    0.15
     vac
    0.15
     performances
    0.15
    performance
    0.15
     performance
    0.15
    Act Density 0.077%

    No Known Activations