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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that indicate comparison, contrast, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sector
    -0.13
    ÙĦ
    -0.13
    inde
    -0.13
     eskort
    -0.13
    ildo
    -0.13
    Ãłm
    -0.13
     вов
    -0.12
     вÑģÑĤ
    -0.12
    âĢŀM
    -0.12
    FromBody
    -0.12
    POSITIVE LOGITS
    ,
    0.21
     ÙħÛĮÙĦادÛĮ
    0.18
    Ùį
    0.16
    ifiable
    0.15
    :
    0.15
    -ci
    0.15
    hoot
    0.15
    ooth
    0.14
    Ùĭ
    0.14
    uality
    0.14
    Act Density 0.229%

    No Known Activations