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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical labels or equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     OFDb
    -0.81
     avoient
    -0.75
     auroit
    -0.74
    Cyfarwyddwr
    -0.70
     pitié
    -0.69
     feroit
    -0.68
     coscienza
    -0.67
     gagné
    -0.67
    pozdrawiam
    -0.66
     miglia
    -0.66
    POSITIVE LOGITS
    AddTagHelper
    0.82
    label
    0.77
    LABEL
    0.72
    Labels
    0.70
     LABEL
    0.69
     label
    0.65
     Label
    0.64
    labels
    0.63
     Labels
    0.63
    TProtocol
    0.61
    Act Density 0.173%

    No Known Activations