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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authorship or publication information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    gin
    -0.45
     r
    -0.43
     kö
    -0.42
    burg
    -0.41
    inh
    -0.41
     rij
    -0.40
     base
    -0.39
     extra
    -0.39
    SS
    -0.39
    ine
    -0.38
    POSITIVE LOGITS
     متعلقه
    0.92
     surla
    0.89
    ThroughAttribute
    0.80
     createState
    0.79
    GraphicsUnit
    0.77
     Roskov
    0.72
    abestanden
    0.71
     CreateTagHelper
    0.70
     springfox
    0.69
     onCancelled
    0.69
    Act Density 0.002%

    No Known Activations