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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain conjunctions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     showcasing
    -0.74
     leveraging
    -0.71
     incentiv
    -0.70
    aka
    -0.69
     transitioning
    -0.66
     aka
    -0.66
     للاسماء
    -0.65
     leveraged
    -0.65
     générer
    -0.63
     grandkids
    -0.63
    POSITIVE LOGITS
     Daß
    0.72
     doubtless
    0.66
     scarcely
    0.57
     ибо
    0.55
     therefrom
    0.54
     mußte
    0.50
     sikkert
    0.49
    Vidite
    0.49
     MonoBehaviour
    0.49
     forthwith
    0.49
    Act Density 0.515%

    No Known Activations