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

    Neuronpedia

    INDEX
    Explanations

    mentions of cans, canisters, or containers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "minister" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occurrence
    -0.69
     appraisal
    -0.68
     resting
    -0.67
     context
    -0.65
     Gil
    -0.65
     NP
    -0.63
     anticipated
    -0.62
     Hume
    -0.61
     offensive
    -0.60
     automated
    -0.60
    POSITIVE LOGITS
    isters
    4.66
    ister
    1.88
    istered
    1.71
    ISTER
    1.69
    iblings
    1.31
    itters
    1.09
    adders
    1.08
    esters
    1.04
    cers
    1.04
    encers
    1.03
    Act Density 0.017%

    No Known Activations