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

    Neuronpedia

    INDEX
    Explanations

    percentages from survey data

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     condensed
    -0.75
    aviour
    -0.67
    operative
    -0.66
     reborn
    -0.65
     Bagg
    -0.64
     recomm
    -0.61
    lay
    -0.60
    Reviewer
    -0.60
    access
    -0.58
    DragonMagazine
    -0.57
    POSITIVE LOGITS
    %
    1.30
     percent
    1.21
    %-
    1.20
    %;
    1.07
    %,
    1.06
    %.
    0.99
    %"
    0.96
    %)
    0.94
    %:
    0.94
    %),
    0.94
    Act Density 0.208%

    No Known Activations