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

    Neuronpedia

    INDEX
    Explanations

    sentences that reflect goals, beliefs, and intentions related to social or community issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kom
    -0.18
    æ´ŀ
    -0.16
    جر
    -0.15
    ehr
    -0.14
    ADI
    -0.14
    lover
    -0.14
    öh
    -0.14
    Quiz
    -0.14
    quiz
    -0.14
     (;;
    -0.14
    POSITIVE LOGITS
     hope
    0.23
     intent
    0.18
    hope
    0.17
     hopes
    0.17
     rằng
    0.16
    pine
    0.15
     hoping
    0.15
     question
    0.15
     intention
    0.15
     dispers
    0.14
    Act Density 0.285%

    No Known Activations