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

    Neuronpedia

    INDEX
    Explanations

    references to treaties and legal agreements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ContentAlignment
    -0.65
     Judea
    -0.61
    ranos
    -0.58
     Ashok
    -0.52
     Armando
    -0.52
     تضيفلها
    -0.52
     Silverstone
    -0.52
     Elli
    -0.51
     PRINCE
    -0.51
    Setter
    -0.50
    POSITIVE LOGITS
     treaty
    1.03
     Treaty
    0.99
     treaties
    0.92
     Treaties
    0.88
    AndEndTag
    0.76
     Tratado
    0.68
    $}}
    0.67
    Autoritní
    0.67
    }\]
    0.65
     disambiguazione
    0.64
    Act Density 0.020%

    No Known Activations