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

    Neuronpedia

    INDEX
    Explanations

    references to names and their usage in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     écoulé
    -0.62
    ]));
    -0.56
     menilai
    -0.54
     obiet
    -0.54
    raska
    -0.54
     للغاية
    -0.53
     Abbé
    -0.53
    }));
    -0.53
    äki
    -0.52
    agoza
    -0.52
    POSITIVE LOGITS
     names
    1.66
     name
    1.65
     Names
    1.35
     Name
    1.25
     NAME
    1.18
    name
    1.18
     NAMES
    1.16
    names
    1.15
     Namen
    1.12
     naam
    1.09
    Act Density 0.156%

    No Known Activations