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

    Neuronpedia

    INDEX
    Explanations

    specific references to individuals involved in legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sally
    -0.53
     HttpNotFound
    -0.49
     Sally
    -0.49
     Annahme
    -0.49
    Katy
    -0.47
     Lucie
    -0.47
     Lightboxes
    -0.47
    Sophie
    -0.47
    andExpect
    -0.47
    Lucy
    -0.46
    POSITIVE LOGITS
     Lamont
    0.65
     Tyrone
    0.63
     Ras
    0.62
     Ty
    0.58
     Lat
    0.57
     Jav
    0.57
    Tyr
    0.56
     Lamar
    0.54
     Jama
    0.54
     Tre
    0.52
    Act Density 0.371%

    No Known Activations