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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and formatting in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anger
    -0.15
    hr
    -0.14
    گار
    -0.14
    lein
    -0.14
     exc
    -0.14
    ino
    -0.14
    unami
    -0.13
    unu
    -0.13
    rror
    -0.13
    à¹Īà¸Ńย
    -0.13
    POSITIVE LOGITS
     Bell
    0.17
     addCriterion
    0.17
     Berk
    0.16
    KeyType
    0.15
    Bell
    0.15
    gos
    0.15
     Gallagher
    0.14
    rush
    0.14
     راÛĮ
    0.14
     bell
    0.14
    Act Density 0.074%

    No Known Activations