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

    Neuronpedia

    INDEX
    Explanations

    messages prompting a user to sign up for a newsletter or service

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to signing up or subscribing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bis
    -0.71
     Coul
    -0.69
     Manson
    -0.65
    mong
    -0.63
    matter
    -0.62
    knife
    -0.62
     wast
    -0.60
     knife
    -0.60
    phas
    -0.60
     fingert
    -0.60
    POSITIVE LOGITS
    ername
    0.96
    lish
    0.89
    dates
    0.87
    adesh
    0.82
    icts
    0.77
    grades
    0.74
    skirts
    0.74
    rights
    0.73
    Trend
    0.73
    np
    0.72
    Act Density 0.023%

    No Known Activations