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

    Neuronpedia

    INDEX
    Explanations

    references to people and their actions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     示
    -0.14
     CONSEQUENTIAL
    -0.14
     Pon
    -0.14
    çĶµè§Ĩ
    -0.14
     Horny
    -0.13
    ÏĦε
    -0.13
    лÑıд
    -0.13
     Lump
    -0.13
    ลา
    -0.13
     виÑģ
    -0.12
    POSITIVE LOGITS
    ingen
    0.15
    velle
    0.15
    lus
    0.15
    vous
    0.15
    imler
    0.14
     Nu
    0.14
    lush
    0.14
    abd
    0.14
    luk
    0.14
    ercul
    0.14
    Act Density 0.009%

    No Known Activations