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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses and their repeated usage in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     upside
    -0.74
     spiked
    -0.72
     ion
    -0.69
     inund
    -0.68
     stabil
    -0.68
     soaking
    -0.67
     overl
    -0.67
     face
    -0.67
    ktop
    -0.67
     insurance
    -0.66
    POSITIVE LOGITS
    formerly
    1.17
    also
    1.16
    ...)
    1.14
    sic
    1.12
    both
    1.10
    via
    1.09
    includes
    1.04
    see
    1.03
    feat
    1.01
    excluding
    1.01
    Act Density 0.100%

    No Known Activations