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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating general applicability or broader concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    providedIn
    -1.01
     itſelf
    -0.91
     myſelf
    -0.89
     Exactos
    -0.88
     themſelves
    -0.87
     Exacts
    -0.86
     Reſ
    -0.82
     becauſe
    -0.79
     ſtate
    -0.78
     Monfieur
    -0.77
    POSITIVE LOGITS
     earlier
    0.63
     similarly
    0.62
     broader
    0.61
     simpler
    0.59
    もっと
    0.58
     dagegen
    0.57
     other
    0.56
    earlier
    0.55
    tler
    0.55
     bardziej
    0.54
    Act Density 0.383%

    No Known Activations