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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleven
    -0.71
     Eleven
    -0.71
    Eleven
    -0.69
     seventeenth
    -0.68
     seventeen
    -0.66
     eleventh
    -0.66
     Seventeenth
    -0.64
     Eleventh
    -0.64
     Seventeen
    -0.63
    Twelve
    -0.62
    POSITIVE LOGITS
    8
    0.70
     Hamlin
    0.66
     estekak
    0.60
    regard
    0.56
    webElementGuid
    0.53
     REGARD
    0.52
    numerusform
    0.51
     مرئيه
    0.50
    BeforeClass
    0.48
     NgModule
    0.47
    Act Density 0.336%

    No Known Activations