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

    Neuronpedia

    INDEX
    Explanations

    references to pronouns and specific language constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĮ
    -0.16
    ëŀĢ
    -0.15
    etsk
    -0.15
    idon
    -0.15
    \Eloquent
    -0.14
    onis
    -0.14
    Reuse
    -0.14
     Star
    -0.13
    ÄĽ
    -0.13
    aises
    -0.13
    POSITIVE LOGITS
     Leban
    0.16
    ters
    0.16
    olley
    0.16
     nackte
    0.16
    HeaderCode
    0.15
    æĿ¾
    0.14
    etas
    0.14
    ÑĸÑģÑĤ
    0.13
    OffsetTable
    0.13
    jourd
    0.13
    Act Density 0.059%

    No Known Activations