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

    Neuronpedia

    INDEX
    Explanations

    cleaning-related terms and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĭÑģ
    -0.14
    jah
    -0.14
    ickets
    -0.14
    oru
    -0.14
    ucks
    -0.14
    Closed
    -0.13
     Reconstruction
    -0.13
     Shorts
    -0.13
    /info
    -0.13
    StackTrace
    -0.13
    POSITIVE LOGITS
     Cleaning
    0.23
     cleaning
    0.22
    Cleaning
    0.17
    lint
    0.16
     bi
    0.16
    ARED
    0.16
    apiro
    0.16
    cano
    0.16
     thoroughly
    0.16
     تÙĨظÙĬÙģ
    0.15
    Act Density 0.134%

    No Known Activations