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

    Neuronpedia

    INDEX
    Explanations

    specific references to personal names, relationships, and title attributes within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veis
    -0.17
    048
    -0.16
    nee
    -0.14
    éł¼
    -0.14
     unk
    -0.14
    ãģĸ
    -0.14
    /WebAPI
    -0.14
    nder
    -0.14
    vae
    -0.14
    ceae
    -0.14
    POSITIVE LOGITS
     Martial
    0.23
     Forget
    0.21
     Ler
    0.20
     Bureau
    0.20
     Jacqu
    0.20
     Des
    0.19
     Colin
    0.19
     Rena
    0.19
     Dub
    0.19
     Dum
    0.19
    Act Density 0.128%

    No Known Activations