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

    Neuronpedia

    INDEX
    Explanations

    the term "Pop" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Pop" in various contexts, indicating a focus on pop culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ||||
    -0.79
    BILITIES
    -0.76
    %%%%
    -0.72
    ¯¯
    -0.71
    Ø©
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.71
    terday
    -0.71
     destro
    -0.70
    IGHTS
    -0.70
     livest
    -0.70
    POSITIVE LOGITS
    ulations
    1.31
    corn
    1.26
    ularity
    1.19
    ulated
    1.14
    ulus
    1.12
    ulate
    1.07
    ular
    1.06
    ulates
    1.04
    ulating
    1.00
    ulation
    0.96
    Act Density 0.013%

    No Known Activations