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

    references to newsletters and related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    come
    -0.74
    had
    -0.73
    stood
    -0.71
    amping
    -0.69
    jury
    -0.68
    roo
    -0.68
    ãĤ°
    -0.66
    run
    -0.65
    inth
    -0.64
    iera
    -0.64
    POSITIVE LOGITS
     Sign
    0.86
     subscriptions
    0.85
     Advertisement
    0.81
    Newsletter
    0.80
    ertodd
    0.76
    azines
    0.76
     Emails
    0.76
     Upgrade
    0.75
     grap
    0.73
     inbox
    0.73
    Act Density 0.007%

    No Known Activations