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

    Neuronpedia

    INDEX
    Explanations

    subscribe-related phrases or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    subscription-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yugoslavia
    -0.68
    entity
    -0.66
    bered
    -0.65
    far
    -0.64
    stood
    -0.63
    prototype
    -0.62
    FT
    -0.61
    ark
    -0.60
    ondo
    -0.59
    ASC
    -0.59
    POSITIVE LOGITS
     Subscribe
    1.20
    Subscribe
    0.95
     subscribe
    0.86
    culosis
    0.86
    ickets
    0.84
     arrang
    0.83
    Interstitial
    0.82
    âĶģ
    0.81
    ettings
    0.80
     uncond
    0.79
    Act Density 0.006%

    No Known Activations