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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unci
    -0.17
    inka
    -0.16
    yh
    -0.15
     пÑĢивед
    -0.15
     dat
    -0.14
    adb
    -0.13
    rlen
    -0.13
    ·
    -0.13
     alone
    -0.13
     addCriterion
    -0.13
    POSITIVE LOGITS
    aman
    0.15
    onne
    0.15
     Alo
    0.14
    аÑĢÑĩ
    0.14
    termin
    0.14
     HIP
    0.14
     <*>
    0.14
    ORIZ
    0.14
     Neptune
    0.14
    ata
    0.14
    Act Density 0.294%

    No Known Activations