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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "their" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*
    -0.70
     Jefus
    -0.61
    MLLoader
    -0.57
     affari
    -0.57
     resourceCulture
    -0.55
    omial
    -0.54
     kasarigan
    -0.54
    Slf
    -0.54
    OGND
    -0.53
    ロウィン
    -0.53
    POSITIVE LOGITS
    their
    1.25
     their
    1.23
    Their
    1.19
     mereka
    1.04
     Their
    1.02
     they
    1.00
    they
    1.00
    They
    0.98
     kanilang
    0.97
     THEIR
    0.94
    Act Density 0.093%

    No Known Activations