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

    Neuronpedia

    INDEX
    Explanations

    key concepts and important terms that relate to critical discussions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.16
    ãĤµãĤ¤
    -0.15
    ennon
    -0.15
    TAB
    -0.14
     FindObjectOfType
    -0.14
     EITHER
    -0.14
    ONY
    -0.14
    valuator
    -0.13
    chw
    -0.13
    stru
    -0.13
    POSITIVE LOGITS
     specifically
    0.17
     expressly
    0.16
     strictly
    0.16
     explicitly
    0.16
     exclusively
    0.14
    оÑĪ
    0.14
    ymi
    0.14
    abcdefghijklmnop
    0.14
    	explicit
    0.14
     Jub
    0.13
    Act Density 0.005%

    No Known Activations