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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns with the number 112

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, specifically those related to the number 112

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leck
    -0.85
    uyomi
    -0.81
    lev
    -0.72
    akin
    -0.70
    nington
    -0.69
    ges
    -0.69
    isman
    -0.68
    undai
    -0.67
    zzo
    -0.67
    cham
    -0.67
    POSITIVE LOGITS
     ILCS
    0.94
     114
    0.85
     113
    0.85
     111
    0.83
     112
    0.82
    111
    0.81
     "$:/
    0.80
    mph
    0.80
     dB
    0.79
    00000
    0.79
    Act Density 0.011%

    No Known Activations