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

    Neuronpedia

    INDEX
    Explanations

    phrases related to widespread occurrences or locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "all over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stewards
    -0.72
    0000000000000000
    -0.71
    ":[
    -0.62
    udging
    -0.61
     Engineers
    -0.61
    oka
    -0.61
    utenberg
    -0.60
    acles
    -0.58
    =-=-
    -0.57
    \<
    -0.57
    POSITIVE LOGITS
    iflower
    0.79
    sites
    0.75
    drive
    0.72
    roads
    0.72
    grown
    0.70
    kill
    0.70
    uffs
    0.69
    sided
    0.69
    lord
    0.69
    important
    0.67
    Act Density 0.030%

    No Known Activations