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

    Neuronpedia

    INDEX
    Explanations

    English words that are translated or related to words in other languages, especially terms for specific concepts or objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating definitions or explanations of terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynski
    -0.74
    chenko
    -0.74
    Contact
    -0.71
    omics
    -0.71
    âĶĢ
    -0.71
    Reward
    -0.70
    Ohio
    -0.69
    Math
    -0.68
    LM
    -0.66
    itals
    -0.66
    POSITIVE LOGITS
    gery
    1.21
    bidden
    1.19
     example
    1.03
     instance
    1.01
    geries
    0.98
    gotten
    0.83
     purposes
    0.82
     centuries
    0.82
    aging
    0.82
     starters
    0.81
    Act Density 0.167%

    No Known Activations