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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associations in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreInfinity
    -0.60
     Chriftian
    -0.57
     betweenstory
    -0.53
     باخ
    -0.52
     téléphonique
    -0.51
     AssemblyCompany
    -0.47
    ządu
    -0.47
     Jefus
    -0.47
     beſt
    -0.47
     Conſ
    -0.47
    POSITIVE LOGITS
    verwijspagina
    0.70
     autorytatywna
    0.70
     Gleaner
    0.66
    docx
    0.64
    ValueStyle
    0.64
     سكانية
    0.64
    rungsseite
    0.62
     transfieras
    0.62
     кӀ
    0.61
    endcsname
    0.59
    Act Density 0.480%

    No Known Activations