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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "communities" at varying strengths of association

    oai_token-act-pair · gpt-3.5-turbo

    references to communities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.78
    Accessory
    -0.64
    ãĤ¦ãĤ¹
    -0.63
     Alps
    -0.62
    elight
    -0.60
    200000
    -0.59
    Attempts
    -0.57
    --+
    -0.57
    âĶĢâĶĢ
    -0.56
    sort
    -0.56
    POSITIVE LOGITS
    chool
    1.28
    wana
    1.04
    pace
    1.03
    mith
    1.02
    folk
    1.01
    hips
    0.97
    ongs
    0.97
    paces
    0.96
    ourcing
    0.90
    hip
    0.89
    Act Density 0.070%

    No Known Activations