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

    Neuronpedia

    INDEX
    Explanations

    specific references to movies and entertainment related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ktorí
    -0.55
     kteří
    -0.51
    ventes
    -0.51
    cektir
    -0.50
    gefü
    -0.48
     prouver
    -0.48
     régler
    -0.47
     akik
    -0.47
     illustrationer
    -0.47
     peindre
    -0.47
    POSITIVE LOGITS
     guru
    0.73
     leader
    0.72
     boss
    0.72
     creator
    0.72
     analyst
    0.70
     strategist
    0.70
     worker
    0.69
     supremo
    0.69
     administrator
    0.69
     spokesperson
    0.68
    Act Density 0.367%

    No Known Activations