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

    Neuronpedia

    INDEX
    Explanations

    references to safety and accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     RELATED
    -0.17
    ëį°ìĿ´íĬ¸
    -0.16
     “[
    -0.16
    .pic
    -0.16
    âĸį
    -0.15
    fillType
    -0.14
    Pair
    -0.14
     alongside
    -0.14
     Him
    -0.14
    iya
    -0.14
    POSITIVE LOGITS
     Lets
    0.20
     please
    0.20
    BT
    0.20
    thus
    0.18
    Persons
    0.18
    Lets
    0.18
    please
    0.17
     Included
    0.17
     BT
    0.17
     PLEASE
    0.17
    Act Density 0.682%

    No Known Activations