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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and terms indicating rankings or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.82
     Wheatley
    -0.75
     Krie
    -0.75
    erra
    -0.71
     Gries
    -0.71
    zet
    -0.66
     Ordin
    -0.64
    ות
    -0.64
    ed
    -0.63
    сну
    -0.61
    POSITIVE LOGITS
    th
    1.07
     Tenth
    1.05
    tenth
    1.04
     tenth
    0.96
    AsUp
    0.95
     Fifth
    0.93
     Thirteenth
    0.91
    teenth
    0.90
     nth
    0.90
     Ninth
    0.90
    Act Density 0.096%

    No Known Activations