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

    Neuronpedia

    INDEX
    Explanations

    references to subscription services or models

    oai_token-act-pair · gpt-3.5-turbo

    references to subscription services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ball
    -0.79
    umi
    -0.75
    erb
    -0.74
    ocks
    -0.74
    arnaev
    -0.71
    amm
    -0.71
    abouts
    -0.70
    balls
    -0.70
    oche
    -0.68
    ocent
    -0.68
    POSITIVE LOGITS
     subscription
    1.09
     subscriptions
    1.02
     Unlimited
    0.87
     subscriber
    0.86
     subscribers
    0.86
     renew
    0.83
     fee
    0.82
    scription
    0.80
     fees
    0.76
     dues
    0.74
    Act Density 0.010%

    No Known Activations