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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cri
    -0.15
     Bret
    -0.14
    034
    -0.14
     ontvangst
    -0.14
    ingo
    -0.14
     inert
    -0.14
     Cobb
    -0.14
     Corm
    -0.14
     Dexter
    -0.13
    elo
    -0.13
    POSITIVE LOGITS
    akov
    0.15
    endar
    0.15
    agini
    0.14
    ecies
    0.14
    intros
    0.14
    lingen
    0.14
    isses
    0.14
     Twig
    0.14
     lesb
    0.14
    idual
    0.14
    Act Density 0.003%

    No Known Activations