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

    Neuronpedia

    INDEX
    Explanations

    references to actors and their performances in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogno
    -0.56
    igrette
    -0.55
     facilité
    -0.53
     verbre
    -0.53
    esModule
    -0.52
    autaire
    -0.51
     charité
    -0.49
     vitesses
    -0.49
     amélior
    -0.49
     juridiques
    -0.48
    POSITIVE LOGITS
     actors
    0.97
     actor
    0.87
     Actors
    0.82
     Actor
    0.80
     actores
    0.78
     actress
    0.77
    Actors
    0.76
    actors
    0.71
     actresses
    0.71
    Actor
    0.69
    Act Density 0.188%

    No Known Activations