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

    Neuronpedia

    INDEX
    Explanations

    verbal phrases indicating discovery or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahan
    -0.17
    ocket
    -0.15
    achat
    -0.14
    QUEST
    -0.14
     Fav
    -0.14
    ieder
    -0.14
    YW
    -0.13
     breach
    -0.13
    ucha
    -0.13
    еÑĩно
    -0.13
    POSITIVE LOGITS
     rằng
    0.23
     ÏĮÏĦι
    0.20
     bahwa
    0.19
     että
    0.18
    _utilities
    0.17
     that
    0.17
     about
    0.16
     Opport
    0.16
     how
    0.16
     ÑĩÑĤо
    0.16
    Act Density 0.138%

    No Known Activations