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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of variables or terms associated with data and analytics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tslib
    -0.18
    ибли
    -0.15
    aste
    -0.15
     ste
    -0.15
     Dix
    -0.15
    Ste
    -0.15
    ML
    -0.15
     ------------------------------------------------------------------------------------------------
    -0.14
    stein
    -0.14
    chia
    -0.14
    POSITIVE LOGITS
     Rotation
    0.16
    apol
    0.15
     Cas
    0.15
     cas
    0.15
    æĹĭ
    0.14
    otate
    0.14
    èŀº
    0.14
    opol
    0.14
    HandlerContext
    0.14
     Cutter
    0.14
    Act Density 0.046%

    No Known Activations