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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligations or the actions tied to legal or financial responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.90
     они
    -0.83
    They
    -0.76
     ellas
    -0.74
     ellos
    -0.74
     вони
    -0.74
     They
    -0.69
     them
    -0.67
    they
    -0.66
     eles
    -0.65
    POSITIVE LOGITS
     their
    2.55
    Their
    2.00
    their
    2.00
     Their
    1.93
     leur
    1.84
     deres
    1.77
     jejich
    1.74
     их
    1.72
     leurs
    1.68
     deras
    1.67
    Act Density 0.739%

    No Known Activations