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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subscribing to newsletters or email updates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aukee
    -0.77
    profits
    -0.70
     condu
    -0.64
    cule
    -0.64
     shading
    -0.63
    cular
    -0.63
    voy
    -0.61
     disadvant
    -0.61
    hes
    -0.61
    ylum
    -0.61
    POSITIVE LOGITS
     Subscribe
    0.77
     ARTICLE
    0.75
     receive
    0.71
     subscribe
    0.68
     Supp
    0.68
     ADS
    0.67
     Pastebin
    0.64
     Newsletter
    0.64
     Updates
    0.61
     TEXT
    0.61
    Act Density 8.151%

    No Known Activations