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

    Neuronpedia

    INDEX
    Explanations

    mentions of different kinds of groups of people or users

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of people, particularly younger demographics and users in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deadly
    -0.76
    inventoryQuantity
    -0.66
     srfAttach
    -0.66
    ĸļ
    -0.63
     Corpus
    -0.62
     Humane
    -0.62
    ãģĨ
    -0.61
     ESV
    -0.61
     Empress
    -0.59
     Levant
    -0.58
    POSITIVE LOGITS
     prefer
    0.94
     polled
    0.86
     surveyed
    0.83
     opted
    0.81
     hesitate
    0.80
     agree
    0.77
     believe
    0.77
     alike
    0.76
     swear
    0.75
     mistakenly
    0.75
    Act Density 0.248%

    No Known Activations