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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical figures expressed in a particular format

    oai_token-act-pair · gpt-3.5-turbo

    bullet points or list items in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othal
    -0.82
    olyn
    -0.71
    udic
    -0.70
    erer
    -0.69
    ierre
    -0.69
     graz
    -0.67
    aughter
    -0.64
    uve
    -0.63
    enthal
    -0.61
    aults
    -0.59
    POSITIVE LOGITS
    ··
    1.23
    ·
    0.87
    âĢ¢âĢ¢
    0.86
    ¼
    0.82
    ¾
    0.76
    lat
    0.75
    µ
    0.75
     Joined
    0.70
    ilities
    0.69
    ties
    0.68
    Act Density 0.013%

    No Known Activations