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

    Neuronpedia

    INDEX
    Explanations

    expressions related to subscribing for content

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing gratitude for subscribing or signing up

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.79
    edin
    -0.71
    arro
    -0.70
    aults
    -0.68
    glers
    -0.66
    nil
    -0.66
    soDeliveryDate
    -0.64
    ioned
    -0.63
    Hop
    -0.62
    quickShipAvailable
    -0.62
    POSITIVE LOGITS
     subscribing
    1.08
     signing
    0.80
    giving
    0.78
     ordering
    0.77
     organising
    0.77
     visiting
    0.75
     helping
    0.74
     joining
    0.73
     supporting
    0.72
     sponsoring
    0.72
    Act Density 0.015%

    No Known Activations