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

    Neuronpedia

    INDEX
    Explanations

    concepts related to generalizations and differences in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.76
    Спасылкі
    -0.70
    NameInMap
    -0.69
    ValueGeneration
    -0.63
    })();
    -0.62
     CanadaChoose
    -0.58
    ürze
    -0.57
     ویکی‌پدی
    -0.54
    AndEndTag
    -0.53
     Și
    -0.52
    POSITIVE LOGITS
     unlike
    0.85
     compared
    0.79
    unlike
    0.75
    compared
    0.71
     differs
    0.68
     compares
    0.68
     Unlike
    0.67
    equivalent
    0.66
     equivalent
    0.66
     Gegensatz
    0.66
    Act Density 0.214%

    No Known Activations