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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a sense of belonging or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪÙĤ
    -0.15
    ayacak
    -0.14
    hop
    -0.14
     åĵģ
    -0.14
     EAR
    -0.13
    $__
    -0.13
     ÙĦÙĦس
    -0.13
    iland
    -0.13
    å¥ī
    -0.13
    à¥Ģय
    -0.13
    POSITIVE LOGITS
     duty
    0.17
    æĺ
    0.16
     kiến
    0.15
     Duty
    0.15
     Bernard
    0.14
     Tanks
    0.14
    (strpos
    0.14
    ite
    0.13
    -duty
    0.13
    495
    0.13
    Act Density 0.014%

    No Known Activations