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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sudden appearances or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pop/popping" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiIcon
    -0.82
    perse
    -0.71
    gregation
    -0.68
    ordan
    -0.68
     frontier
    -0.67
    ript
    -0.64
    ournal
    -0.64
    restrial
    -0.63
    ccording
    -0.62
     Correspond
    -0.61
    POSITIVE LOGITS
    corn
    0.95
    ulates
    0.92
    ulate
    0.87
    ULAR
    0.87
    urger
    0.86
     onto
    0.82
    ulations
    0.81
    anut
    0.80
    ulated
    0.78
    ulating
    0.78
    Act Density 0.014%

    No Known Activations