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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inclusivity and acknowledgment of contributions, especially regarding information sharing and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Cast
    -0.15
    enburg
    -0.15
    bat
    -0.15
    æ¨Ĥ
    -0.14
     Estimated
    -0.14
     patron
    -0.14
     Burke
    -0.14
    inton
    -0.13
     Accessed
    -0.13
    Ä
    -0.13
    POSITIVE LOGITS
     included
    0.70
    included
    0.60
     Included
    0.59
     INCLUDED
    0.57
    Included
    0.56
     inclusion
    0.53
    cluded
    0.42
    INCLUDED
    0.41
     includ
    0.40
     include
    0.37
    Act Density 0.296%

    No Known Activations