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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advertisements prompting the reader to continue reading a story

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases related to advertisements or prompts to proceed with reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.70
    ouls
    -0.69
    mith
    -0.67
    ionic
    -0.64
    axter
    -0.63
    lain
    -0.63
    knife
    -0.62
    ially
    -0.62
    otom
    -0.62
    gyn
    -0.61
    POSITIVE LOGITS
     Reading
    0.83
     reading
    0.82
     scrolling
    0.79
     clicking
    0.70
     Loading
    0.69
     Continue
    0.69
     arming
    0.62
    taboola
    0.61
     Below
    0.61
     contacting
    0.60
    Act Density 0.016%

    No Known Activations