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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and community interactions related to safety and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è´¸
    -0.17
     Trident
    -0.16
    acker
    -0.16
     Templ
    -0.15
    arendra
    -0.14
     Mumbai
    -0.14
     templ
    -0.14
    uin
    -0.14
    ieee
    -0.14
     âĤ¹
    -0.14
    POSITIVE LOGITS
     Ethiopia
    0.20
    á
    0.19
     Ethi
    0.18
     Tig
    0.18
     Ethiopian
    0.18
     á
    0.15
     beneficiaries
    0.15
    Tes
    0.15
    EEP
    0.15
     potentials
    0.15
    Act Density 0.006%

    No Known Activations