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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awareness and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScreenState
    -0.14
    aur
    -0.14
    onte
    -0.14
    ski
    -0.14
    .www
    -0.14
    afi
    -0.14
    alem
    -0.14
    leyin
    -0.13
     Worth
    -0.13
     Bauer
    -0.13
    POSITIVE LOGITS
     _______,
    0.15
    èªł
    0.14
    hangi
    0.14
    ến
    0.14
    herit
    0.14
    874
    0.14
     Reese
    0.14
     sut
    0.14
    amaz
    0.14
    spath
    0.13
    Act Density 0.154%

    No Known Activations