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

    Neuronpedia

    INDEX
    Explanations

    mentions of private conversations or communications that are not meant for public disclosure

    oai_token-act-pair · gpt-3.5-turbo

    instances of private communication or undisclosed actions among political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Citation
    -0.78
     Omn
    -0.73
    ankind
    -0.70
    oise
    -0.70
     Miracle
    -0.68
    catch
    -0.66
     Surviv
    -0.65
     Vintage
    -0.65
    population
    -0.65
     conquest
    -0.65
    POSITIVE LOGITS
     briefed
    1.53
     privately
    1.22
     pressured
    1.22
     lobbied
    1.19
     resigned
    1.16
     briefings
    1.12
     Priebus
    1.07
     resign
    1.06
     misled
    1.05
     urged
    1.04
    Act Density 0.424%

    No Known Activations