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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accumulation or acquiring something over time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accumulate" and its variations, indicating a focus on accumulation concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pher
    -0.73
    jah
    -0.72
    sey
    -0.72
    hift
    -0.70
    ĪĴ
    -0.69
    eller
    -0.68
    geon
    -0.68
    word
    -0.68
    elling
    -0.67
    psey
    -0.66
    POSITIVE LOGITS
    ulative
    1.20
     accumulation
    1.05
     accumulated
    1.02
     accumulate
    0.98
     accum
    0.96
     accumulating
    0.95
     piles
    0.92
    ulators
    0.82
    antine
    0.81
    ulator
    0.79
    Act Density 0.019%

    No Known Activations