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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific pronouns and verbs that indicate actions or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     explaining
    -1.02
     suggestion
    -0.96
     saying
    -0.95
     describing
    -0.94
     suggesting
    -0.94
     mentioning
    -0.94
     explains
    -0.93
     explanation
    -0.92
     stating
    -0.92
     explain
    -0.91
    POSITIVE LOGITS
     divorced
    0.54
     disbanded
    0.54
    exits
    0.53
     AssemblyProduct
    0.51
     stoppage
    0.51
     retiring
    0.51
     parked
    0.51
     dropout
    0.50
    uninstall
    0.50
     uninstall
    0.50
    Act Density 1.094%

    No Known Activations