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

    Neuronpedia

    INDEX
    Explanations

    words related to transformations or conversions

    oai_token-act-pair · gpt-3.5-turbo

    concepts and processes related to transformation and conversion across different domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surveyed
    -0.74
     excluded
    -0.66
     interviewed
    -0.65
    aird
    -0.62
    cius
    -0.62
     outnumbered
    -0.61
     waning
    -0.60
    @#&
    -0.59
     disagreements
    -0.59
     wrong
    -0.58
    POSITIVE LOGITS
     manageable
    1.12
     usable
    1.05
    livion
    0.97
    usable
    0.84
    fledged
    0.79
     equivalents
    0.73
     unstoppable
    0.72
     playable
    0.71
     someday
    0.70
    orable
    0.69
    Act Density 0.316%

    No Known Activations