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

    Neuronpedia

    INDEX
    Explanations

    words relating to conspiracy theories and clandestine activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "fo" or variations in capitalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colleges
    -0.74
    lust
    -0.67
    Interstitial
    -0.65
    wise
    -0.65
     Halls
    -0.65
    âĶģ
    -0.63
    rats
    -0.63
     Donation
    -0.62
     Committees
    -0.61
     Visitors
    -0.61
    POSITIVE LOGITS
    obar
    1.15
    avored
    1.05
    ogle
    1.03
    xt
    1.01
    ortun
    1.00
    udge
    0.99
    ils
    0.95
    elin
    0.92
    acet
    0.91
    liction
    0.90
    Act Density 0.012%

    No Known Activations