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

    Neuronpedia

    INDEX
    Explanations

    contact information and calls to action

    oai_token-act-pair · gpt-3.5-turbo

    contact information and promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pher
    -0.68
    pires
    -0.66
    existence
    -0.65
     deduction
    -0.62
     correctness
    -0.62
    iola
    -0.61
    existent
    -0.60
    Marginal
    -0.60
     Galile
    -0.60
    adra
    -0.59
    POSITIVE LOGITS
     links
    0.77
     toll
    0.76
     Tickets
    0.75
    Email
    0.74
     email
    0.73
     Haf
    0.72
     Contact
    0.71
    rss
    0.71
     www
    0.69
     LINK
    0.67
    Act Density 0.247%

    No Known Activations