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

    Neuronpedia

    INDEX
    Explanations

    references to engagement and participation among various groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     被
    -0.21
    被
    -0.20
    icie
    -0.18
     åıĹ
    -0.17
     being
    -0.16
    raÄį
    -0.16
    aron
    -0.16
    Äįen
    -0.15
     être
    -0.14
    ivor
    -0.14
    POSITIVE LOGITS
     into
    0.23
     involved
    0.22
     onto
    0.21
     talking
    0.18
     thinking
    0.17
     excited
    0.17
     to
    0.17
    ÑģÑĤÑĢо
    0.16
     ready
    0.16
     onboard
    0.16
    Act Density 0.045%

    No Known Activations