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

    Neuronpedia

    INDEX
    Explanations

    dates or numbers in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    bullet-pointed lists or items presented in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udic
    -0.90
    othal
    -0.81
    aughter
    -0.80
    erer
    -0.79
    dfx
    -0.77
    uve
    -0.75
    obbies
    -0.73
    urch
    -0.71
    arez
    -0.71
    ascular
    -0.68
    POSITIVE LOGITS
    ··
    1.45
    âĢ¢âĢ¢
    0.88
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.78
    ting
    0.76
    0.74
    ¼
    0.71
    ¾
    0.71
    lat
    0.69
    te
    0.68
    µ
    0.67
    Act Density 0.019%

    No Known Activations