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

    Neuronpedia

    INDEX
    Explanations

    texts related to beliefs or theories

    oai_token-act-pair · gpt-3.5-turbo

    themes related to justice and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.76
    iple
    -0.71
     confir
    -0.68
    displayText
    -0.65
    adel
    -0.64
    ilde
    -0.62
    orney
    -0.62
    ossibility
    -0.61
    ij士
    -0.59
     Monthly
    -0.59
    POSITIVE LOGITS
     rapists
    0.78
     unfairly
    0.73
     society
    0.70
     biologically
    0.70
     wealthier
    0.68
     UFOs
    0.66
     democracies
    0.66
     psychologically
    0.65
     terrorists
    0.64
     "'
    0.64
    Act Density 1.380%

    No Known Activations