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

    Neuronpedia

    INDEX
    Explanations

    references to confidence or related states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apper
    -0.16
    ÑĤив
    -0.16
    _SPECIAL
    -0.15
    ereco
    -0.15
     pong
    -0.15
    .Sdk
    -0.14
    plib
    -0.14
     formulaire
    -0.14
    icking
    -0.14
    endcode
    -0.14
    POSITIVE LOGITS
    istory
    0.17
     conf
    0.16
    LEX
    0.15
    KL
    0.15
    Coverage
    0.15
    PELL
    0.14
    -syntax
    0.14
    edom
    0.14
    ستاÙĨ
    0.14
    urb
    0.14
    Act Density 0.022%

    No Known Activations