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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and future tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of first-person plural and singular pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pradesh
    -0.69
     disembark
    -0.68
    rising
    -0.67
     reconciliation
    -0.64
     continuation
    -0.64
     relations
    -0.64
    mere
    -0.63
     coron
    -0.62
     ceases
    -0.61
     unresolved
    -0.61
    POSITIVE LOGITS
     recommend
    1.51
     advise
    1.34
     recommends
    1.28
     advises
    1.21
     recommending
    1.11
     advice
    1.10
     suggest
    1.09
    recomm
    0.99
     recommended
    0.99
     recommendation
    0.92
    Act Density 0.239%

    No Known Activations