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

    Neuronpedia

    INDEX
    Explanations

    links or prompts for subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to subscribing to newsletters or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.83
    inas
    -0.71
    ilde
    -0.68
    come
    -0.65
    ball
    -0.63
    ested
    -0.61
     glide
    -0.60
     realism
    -0.59
    put
    -0.59
    inho
    -0.59
    POSITIVE LOGITS
    Subscribe
    0.88
     Subscribe
    0.84
    Interstitial
    0.81
     unsub
    0.80
     subscribe
    0.79
    ombat
    0.78
    isodes
    0.77
    scribe
    0.77
    CHAT
    0.77
    henko
    0.77
    Act Density 0.015%

    No Known Activations