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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes and emotional reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal emotional reactions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exceptions
    -0.64
     Assist
    -0.63
    lict
    -0.62
     occupancy
    -0.62
    itism
    -0.60
    performing
    -0.59
     Failure
    -0.59
    entry
    -0.58
     departures
    -0.58
    Vs
    -0.58
    POSITIVE LOGITS
     exclaimed
    1.32
     wondered
    1.21
     immediately
    1.20
     instantly
    1.17
     gasped
    1.13
     realized
    1.09
     exclaim
    1.09
     realised
    1.09
     instinctively
    1.09
     knew
    1.05
    Act Density 0.296%

    No Known Activations