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

    Neuronpedia

    INDEX
    Explanations

    phrases related to newsletters being delivered

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription and the delivery of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wikipedia
    -0.76
    odan
    -0.71
     extraction
    -0.67
     Kirin
    -0.64
    atan
    -0.64
    ————————
    -0.63
    si
    -0.62
    Eth
    -0.61
     Sigma
    -0.61
     Barrier
    -0.61
    POSITIVE LOGITS
    ragon
    1.00
    imentary
    0.95
     delivered
    0.88
    ocalypse
    0.80
    Interstitial
    0.79
    nesday
    0.73
     upon
    0.70
    ients
    0.69
     baskets
    0.69
    icts
    0.68
    Act Density 0.022%

    No Known Activations