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

    Neuronpedia

    INDEX
    Explanations

    references to change and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udas
    -0.16
    ',['
    -0.14
    okus
    -0.14
    ãĥ£
    -0.14
     amendment
    -0.14
    мм
    -0.13
    xee
    -0.13
     Ware
    -0.13
    ör
    -0.13
    ÑģÑĤÑĢÑĥменÑĤ
    -0.13
    POSITIVE LOGITS
    IDA
    0.17
    åºŃ
    0.15
     latter
    0.15
    hest
    0.14
    _COMPARE
    0.14
    shade
    0.14
    chy
    0.14
    eyer
    0.14
    ategories
    0.14
    ategory
    0.14
    Act Density 0.396%

    No Known Activations