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

    Neuronpedia

    INDEX
    Explanations

    text related to newsletters or sign-ups

    oai_token-act-pair · gpt-3.5-turbo

    content related to newsletter subscriptions and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.71
    ibling
    -0.63
    alties
    -0.62
     scales
    -0.62
    walk
    -0.61
     coord
    -0.61
    iland
    -0.60
     distance
    -0.59
     pawn
    -0.58
    aimon
    -0.58
    POSITIVE LOGITS
    isode
    0.72
     newsletter
    0.70
     Newsletter
    0.68
    Newsletter
    0.66
    Balt
    0.65
    20439
    0.65
    vice
    0.62
    Beg
    0.59
    letters
    0.59
    ether
    0.59
    Act Density 0.050%

    No Known Activations