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

    Neuronpedia

    INDEX
    Explanations

    pronouns and articles in multiple forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.71
    ness
    -0.70
     notes
    -0.48
     Krä
    -0.48
    ity
    -0.48
    derry
    -0.48
    or
    -0.47
     nack
    -0.47
     calab
    -0.45
    ौर
    -0.45
    POSITIVE LOGITS
     seines
    0.94
     unei
    0.94
     eines
    0.93
     Neale
    0.88
    /**
    0.87
    Personensuche
    0.85
     sogni
    0.84
     ihres
    0.83
     του
    0.81
    TypedDataSet
    0.81
    Act Density 0.042%

    No Known Activations