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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negotiations and agreements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to contracts or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hates
    -0.75
     loves
    -0.70
     fame
    -0.67
     sucks
    -0.67
     fucked
    -0.65
     lately
    -0.64
     Blog
    -0.61
    !]
    -0.61
    anity
    -0.60
    %]
    -0.60
    POSITIVE LOGITS
     2019
    0.85
     concess
    0.84
     existing
    0.83
    2020
    0.82
     2020
    0.81
     2021
    0.79
     bilateral
    0.76
     2025
    0.75
     administr
    0.75
     redund
    0.74
    Act Density 1.180%

    No Known Activations