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

    Neuronpedia

    INDEX
    Explanations

    phrases related to education and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ----------------------------------------------------------------------------↵
    -0.17
     accompl
    -0.14
    ongo
    -0.14
    obl
    -0.14
     Mitt
    -0.14
     Hond
    -0.14
    anager
    -0.14
     Karma
    -0.14
     Walters
    -0.13
     Kod
    -0.13
    POSITIVE LOGITS
     Singapore
    0.28
    Singapore
    0.26
     gazet
    0.24
     singapore
    0.24
     atas
    0.23
     Malays
    0.23
     lah
    0.22
     Joh
    0.22
    .sg
    0.22
     Malaysia
    0.21
    Act Density 0.673%

    No Known Activations