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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting reader engagement or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JNI
    -0.15
     kli
    -0.14
    _CI
    -0.14
    à¸łà¸²à¸ŀ
    -0.14
    оваÑĢи
    -0.13
    ATALOG
    -0.13
    meric
    -0.13
     hại
    -0.13
     MagicMock
    -0.13
    .LayoutStyle
    -0.13
    POSITIVE LOGITS
     Comment
    0.23
     comment
    0.23
    Comment
    0.19
    acomment
    0.19
     COMMENT
    0.19
     feedback
    0.18
    alone
    0.18
     Feedback
    0.17
    -comment
    0.17
    comment
    0.17
    Act Density 0.006%

    No Known Activations