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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "just" used to downplay significance or deliver information

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.73
    undai
    -0.71
     necks
    -0.71
     challeng
    -0.68
    ught
    -0.67
     destro
    -0.67
     sacrific
    -0.65
    pora
    -0.65
    glomer
    -0.64
    antis
    -0.62
    POSITIVE LOGITS
    ifiable
    1.28
    ifications
    1.04
     kidding
    0.94
    IFIED
    0.93
    if
    0.89
     plain
    0.87
    ified
    0.86
    ices
    0.86
     shy
    0.80
    itia
    0.76
    Act Density 0.067%

    No Known Activations