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

    Neuronpedia

    INDEX
    Explanations

    references to the organization Amnesty International

    oai_token-act-pair · gpt-3.5-turbo

    references to Amnesty International

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opic
    -0.73
    agers
    -0.71
    adal
    -0.66
     caffe
    -0.64
     ancest
    -0.64
    driver
    -0.62
     MTA
    -0.62
     impro
    -0.62
    haul
    -0.62
    gradient
    -0.61
    POSITIVE LOGITS
    nesty
    1.21
     Amnesty
    0.93
     International
    0.80
     Chomsky
    0.76
    Choice
    0.75
    endi
    0.73
     Rights
    0.72
    International
    0.71
    ij士
    0.71
    ileaks
    0.70
    Act Density 0.018%

    No Known Activations