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

    Neuronpedia

    INDEX
    Explanations

    newsletter subscription prompts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unintended
    -0.68
    DC
    -0.68
    OTT
    -0.67
    same
    -0.65
    comes
    -0.65
    WC
    -0.65
    had
    -0.63
    NRS
    -0.62
    stood
    -0.61
    ãĤ°
    -0.60
    POSITIVE LOGITS
    Newsletter
    0.98
     subscriptions
    0.88
     Sign
    0.87
    ertodd
    0.84
     Emails
    0.83
    oday
    0.76
    azines
    0.76
     Doodle
    0.75
     Advertisement
    0.74
     blockers
    0.73
    Act Density 0.006%

    No Known Activations