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

    Neuronpedia

    INDEX
    Explanations

    references to sharing or recommending things to friends

    oai_token-act-pair · gpt-3.5-turbo

    references to friends and social sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.70
    assion
    -0.69
    grim
    -0.67
    phas
    -0.67
    yss
    -0.67
     chloride
    -0.66
    elsius
    -0.65
    ifer
    -0.64
     ceilings
    -0.62
    vette
    -0.62
    POSITIVE LOGITS
    hips
    0.99
    folk
    0.96
    liest
    0.89
    channelAvailability
    0.88
    liness
    0.87
    lies
    0.83
    lier
    0.80
     friends
    0.78
     buddies
    0.74
     acquaintances
    0.69
    Act Density 0.028%

    No Known Activations