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

    Neuronpedia

    INDEX
    Explanations

    references to social and political pressures or influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.16
     Bail
    -0.16
    ingle
    -0.15
    agues
    -0.15
     staples
    -0.14
    hots
    -0.14
    ys
    -0.14
     Baxter
    -0.14
    alem
    -0.14
    cape
    -0.14
    POSITIVE LOGITS
    pell
    0.17
     demands
    0.16
     åī
    0.15
     pressure
    0.15
     Energ
    0.15
    %S
    0.15
    orado
    0.15
    åĿĬ
    0.14
    pressure
    0.14
     demand
    0.14
    Act Density 0.287%

    No Known Activations