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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number "200" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.89
    robe
    -0.73
    aken
    -0.73
    ime
    -0.71
    achi
    -0.70
    ake
    -0.70
    cone
    -0.70
    BOOK
    -0.69
    book
    -0.69
    stal
    -0.69
    POSITIVE LOGITS
    Hz
    1.02
    00000
    0.98
    mph
    0.86
    âĸĪ
    0.86
    MHz
    0.83
     MHz
    0.83
     kHz
    0.81
    lbs
    0.81
     Hz
    0.80
    kHz
    0.79
    Act Density 0.027%

    No Known Activations