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

    Neuronpedia

    INDEX
    Explanations

    prompts related to receiving information or actions on a regular basis

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating frequency and subscription actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itudinal
    -0.67
    istically
    -0.60
    AAF
    -0.60
    ivan
    -0.60
     Azerb
    -0.59
    agall
    -0.58
    ciation
    -0.58
    pex
    -0.57
     FEMA
    -0.57
    selves
    -0.56
    POSITIVE LOGITS
     reader
    0.75
     weekday
    0.74
    malink
    0.73
    advertisement
    0.70
    interstitial
    0.70
     inbox
    0.69
     bookmark
    0.67
     subscribed
    0.67
     Featured
    0.65
     retweet
    0.65
    Act Density 0.050%

    No Known Activations