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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sudden appearances or movements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pop" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perse
    -0.70
    aves
    -0.67
    vil
    -0.65
    IVES
    -0.64
    RAW
    -0.63
    sen
    -0.63
    gregation
    -0.62
    mand
    -0.61
    ########
    -0.60
     Correspond
    -0.60
    POSITIVE LOGITS
     popped
    1.02
     pops
    0.97
     popping
    0.91
    ulates
    0.89
     pop
    0.86
    otle
    0.83
    ulations
    0.83
    ULAR
    0.82
    corn
    0.81
    ulating
    0.79
    Act Density 0.007%

    No Known Activations