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

    Neuronpedia

    INDEX
    Explanations

    sentences that express understanding or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stery
    -0.15
    ategorical
    -0.15
    _regular
    -0.14
    borg
    -0.14
    felt
    -0.14
     Ton
    -0.14
    ettes
    -0.14
     Lage
    -0.14
    urum
    -0.13
     cours
    -0.13
    POSITIVE LOGITS
    üf
    0.16
    yz
    0.15
    .should
    0.15
    edes
    0.14
     sum
    0.14
    yect
    0.14
     пÑĢавилÑĮно
    0.14
    ysql
    0.14
    üç
    0.14
     صÙĨعت
    0.14
    Act Density 0.111%

    No Known Activations