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

    Neuronpedia

    INDEX
    Explanations

    references to matrices and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.59
    forName
    -0.50
     ویکی‌پدی
    -0.46
     moll
    -0.40
    ulemon
    -0.39
    󠁮
    -0.39
     esternos
    -0.39
    setdefault
    -0.37
    igshid
    -0.36
    }*/
    -0.35
    POSITIVE LOGITS
     matrix
    0.82
     indication
    0.77
     indicated
    0.74
     Matrix
    0.74
     indicator
    0.71
     Indicator
    0.71
    Eastern
    0.70
     Eastern
    0.69
     eastern
    0.67
     Indic
    0.67
    Act Density 0.218%

    No Known Activations