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

    Neuronpedia

    INDEX
    Explanations

    specific phrases encouraging newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the source of information or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imates
    -0.77
    imental
    -0.75
    heim
    -0.74
    imate
    -0.73
    omsky
    -0.69
    gow
    -0.69
    Í
    -0.67
     retard
    -0.65
    RGB
    -0.62
    hetics
    -0.62
    POSITIVE LOGITS
     clicking
    1.35
     signing
    1.18
     subscribing
    1.16
     bookmark
    1.08
     downloading
    1.06
     submitting
    1.03
     joining
    1.01
     selecting
    1.01
     liking
    0.98
     visiting
    0.96
    Act Density 0.026%

    No Known Activations