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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues, activism, and reflections on historical events

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that emphasize collective actions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.72
    atory
    -0.69
     Publication
    -0.65
    Owner
    -0.60
    visor
    -0.58
     Tai
    -0.58
    cum
    -0.58
    math
    -0.56
     Mehran
    -0.56
    photos
    -0.56
    POSITIVE LOGITS
    're
    1.33
    've
    1.23
    akening
    1.08
    athered
    1.08
    'll
    1.06
    selves
    1.03
    'd
    0.99
     ourselves
    0.99
    ird
    0.95
    imar
    0.94
    Act Density 0.238%

    No Known Activations