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

    Neuronpedia

    INDEX
    Explanations

    affiliate links within text

    oai_token-act-pair · gpt-3.5-turbo

    references to affiliate marketing or affiliate links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STD
    -0.81
    pp
    -0.80
    ppo
    -0.75
    ests
    -0.73
    sen
    -0.73
    sa
    -0.71
    ft
    -0.69
     Quiet
    -0.68
    borgh
    -0.68
    boats
    -0.66
    POSITIVE LOGITS
     affiliate
    1.39
    iliate
    1.29
     affiliates
    1.00
     affiliated
    0.80
     affili
    0.78
     agre
    0.77
    iliated
    0.76
     affiliation
    0.75
     network
    0.74
     ende
    0.74
    Act Density 0.007%

    No Known Activations