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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and symbols used in formal definitions and theorems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    abestanden
    -0.93
     resourceCulture
    -0.76
     itſelf
    -0.75
    KommentareTeilen
    -0.73
    ParallelGroup
    -0.73
    ſelf
    -0.72
     GetEnumerator
    -0.71
     Inſ
    -0.69
     Monfieur
    -0.69
     ufe
    -0.68
    POSITIVE LOGITS
    ,
    0.47
    .
    0.47
     einge
    0.45
    Cie
    0.44
     kapan
    0.44
    mortal
    0.43
     that
    0.42
    біль
    0.40
    획
    0.40
     masses
    0.39
    Act Density 0.025%

    No Known Activations