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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or counts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.87
    Datuak
    -0.83
    Personensuche
    -0.81
     TestBed
    -0.80
     initComponents
    -0.79
     Roskov
    -0.78
    featureID
    -0.77
    awtextra
    -0.76
    uxxxx
    -0.73
     eventdata
    -0.73
    POSITIVE LOGITS
    hängig
    0.62
     umana
    0.62
     grossesse
    0.61
     humaine
    0.60
     grecque
    0.57
     densité
    0.57
     epoca
    0.56
     griega
    0.55
     Houſe
    0.55
     rosse
    0.55
    Act Density 0.059%

    No Known Activations