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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the majority or the largest part of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or describe the quantity of items being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zai
    -0.67
     reviewer
    -0.64
    uggest
    -0.63
     sugg
    -0.62
    haps
    -0.61
    ²¾
    -0.61
    roma
    -0.58
     Cosponsors
    -0.58
     willingness
    -0.58
    writer
    -0.57
    POSITIVE LOGITS
    tein
    0.76
    isites
    0.68
    ebted
    0.67
    ources
    0.66
    rued
    0.66
     EVs
    0.65
    oval
    0.65
    borgh
    0.64
    ussian
    0.62
    phies
    0.62
    Act Density 0.204%

    No Known Activations