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

    Neuronpedia

    INDEX
    Explanations

    phrases related to receiving updates and special offers

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving promotional content or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Borders
    -0.82
     Inher
    -0.71
     Pwr
    -0.71
    lain
    -0.70
    igans
    -0.69
    ufact
    -0.69
    stood
    -0.68
     Granger
    -0.65
    ibal
    -0.65
     Tsukuyomi
    -0.65
    POSITIVE LOGITS
     occasional
    0.89
    interstitial
    0.80
    month
    0.67
    ause
    0.67
     (%
    0.67
     intrusive
    0.65
    ãģı
    0.65
    */(
    0.65
    andel
    0.64
    optional
    0.63
    Act Density 0.032%

    No Known Activations