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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and phrases indicating relationships among quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    はじめに
    -0.88
     itſelf
    -0.88
     Jefus
    -0.78
     Efq
    -0.77
    BibitemShut
    -0.76
     insuffisamment
    -0.75
     beginnetje
    -0.75
     Monfieur
    -0.73
     themſelves
    -0.73
    İstinadlar
    -0.71
    POSITIVE LOGITS
     than
    0.69
    than
    0.59
    enumi
    0.57
    Beyond
    0.53
    lier
    0.50
     além
    0.49
     beyond
    0.49
     drier
    0.48
    bigger
    0.47
     bigger
    0.47
    Act Density 0.367%

    No Known Activations