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

    Neuronpedia

    INDEX
    Explanations

    statistics and percentages related to demographics and social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Millenn
    -0.17
    ayla
    -0.17
    ught
    -0.17
     è©ķ価
    -0.16
     Millennium
    -0.16
    orra
    -0.16
     millennium
    -0.16
    bourg
    -0.16
    bach
    -0.15
     mil
    -0.14
    POSITIVE LOGITS
    862
    0.15
    меÑĩ
    0.14
    84
    0.14
     AE
    0.14
    86
    0.13
     majority
    0.13
    YNAM
    0.13
    .Cond
    0.13
     Ear
    0.13
    andles
    0.13
    Act Density 0.037%

    No Known Activations