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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or references to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apon
    -0.71
    mbuds
    -0.65
    apons
    -0.63
     Tail
    -0.62
     Magical
    -0.60
    boro
    -0.60
    emies
    -0.59
    inyl
    -0.57
    geon
    -0.56
     âĸĪ
    -0.55
    POSITIVE LOGITS
    Prev
    0.73
    Sensor
    0.69
    BBC
    0.65
    Channel
    0.62
    venge
    0.62
    elsen
    0.62
     landfall
    0.59
     Adinida
    0.59
    Bus
    0.58
    GMT
    0.58
    Act Density 0.247%

    No Known Activations