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

    Neuronpedia

    INDEX
    Explanations

    references to possessive and personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pias
    -0.64
    iredo
    -0.54
    ++];
    -0.52
    +};
    -0.48
     Griechen
    -0.45
    }:${
    -0.44
    }');
    -0.43
    )++;
    -0.43
     custom
    -0.43
    المل
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.92
    their
    0.90
     their
    0.86
    Their
    0.84
     Their
    0.83
     ujednoznacz
    0.83
     ihre
    0.79
     THEIR
    0.77
     дописавши
    0.74
     its
    0.74
    Act Density 0.501%

    No Known Activations