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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important events, political decisions, and government actions

    oai_token-act-pair · gpt-3.5-turbo

    relative pronouns and clauses linking information or describing specifics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Untitled
    -0.76
    '/
    -0.61
     everlasting
    -0.60
    ÃĹ
    -0.59
     clipboard
    -0.59
    ãĤ¦ãĤ¹
    -0.58
     noticing
    -0.58
     resil
    -0.58
    Interstitial
    -0.57
     sleeve
    -0.57
    POSITIVE LOGITS
     analysts
    1.04
     critics
    1.03
     environmentalists
    0.93
     amounted
    0.91
     could
    0.90
     advocates
    0.89
     he
    0.89
     campaigners
    0.88
     culminated
    0.88
     would
    0.87
    Act Density 0.222%

    No Known Activations