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

    Neuronpedia

    INDEX
    Explanations

    mention of relationships or connections among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++.
    -0.82
     فريبيس
    -0.76
     سكانية
    -0.66
     \%$.
    -0.66
     {}".
    -0.62
    ®.
    -0.62
    €.
    -0.61
    }$.
    -0.60
    *.
    -0.60
    %.
    -0.59
    POSITIVE LOGITS
     these
    0.79
     těchto
    0.63
    리는
    0.62
     ***!
    0.61
     AssemblyCompany
    0.60
     pleaſure
    0.59
     δὲ
    0.59
     meisten
    0.59
    these
    0.59
    zeitige
    0.58
    Act Density 1.075%

    No Known Activations