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

    Neuronpedia

    INDEX
    Explanations

    instances of ordinal numbers or sequences in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    hésite
    -0.80
    -0.79
    ;'>
    -0.75
     mourut
    -0.75
     Krieger
    -0.74
     myſelf
    -0.74
    anneer
    -0.73
    pincode
    -0.73
    woordig
    -0.72
     Efq
    -0.72
    POSITIVE LOGITS
    FIRST
    1.42
     First
    1.41
     first
    1.40
     FIRST
    1.36
    First
    1.30
    first
    1.23
     third
    1.12
     second
    1.05
    第一
    1.04
    isFirst
    1.04
    Act Density 0.998%

    No Known Activations