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

    Neuronpedia

    INDEX
    Explanations

    mentions of newsletters or sign-ups within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Newsletter"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    come
    -0.75
     screws
    -0.70
    had
    -0.69
    roo
    -0.64
    grave
    -0.64
    bows
    -0.63
    equality
    -0.62
    comes
    -0.62
    runs
    -0.62
    stood
    -0.62
    POSITIVE LOGITS
     Sign
    0.90
     inbox
    0.82
     Subscribe
    0.79
     Typ
    0.79
     subscriptions
    0.77
     subscribers
    0.76
     subscriber
    0.75
     Emails
    0.75
     SIGN
    0.74
    Sign
    0.73
    Act Density 0.009%

    No Known Activations