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

    Neuronpedia

    INDEX
    Explanations

    dates, locations, and information related to specific events or individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names and titles associated with individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     differe
    -0.72
    Versions
    -0.66
     versa
    -0.63
     UNCLASSIFIED
    -0.62
    —"
    -0.61
    }.
    -0.61
     aforementioned
    -0.60
     [*
    -0.60
     increments
    -0.59
    âĹ¼
    -0.58
    POSITIVE LOGITS
     Calculator
    0.74
     Release
    0.63
    ¶
    0.62
    utterstock
    0.61
     Quote
    0.60
     Belfast
    0.60
     âĢº
    0.60
     Originally
    0.58
     Updated
    0.57
    ↵Âł
    0.56
    Act Density 0.930%

    No Known Activations