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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant increase in quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    terms related to increases or multiplications, particularly focusing on the concept of doubling and tripling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arty
    -0.64
    RAW
    -0.63
    ouri
    -0.62
    ogi
    -0.61
    cheat
    -0.61
    oria
    -0.61
    Stage
    -0.58
    otropic
    -0.58
    itives
    -0.58
    Interstitial
    -0.58
    POSITIVE LOGITS
     digits
    0.93
    peak
    0.80
     digit
    0.73
     yearly
    0.71
    amount
    0.66
     capacity
    0.66
     consecut
    0.66
    ustomed
    0.66
    plet
    0.64
     enrollment
    0.64
    Act Density 0.032%

    No Known Activations