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

    Neuronpedia

    INDEX
    Explanations

    references to variable names in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stoll
    -0.83
    ]));
    -0.83
     FANDOM
    -0.73
    ```
    -0.72
    )
    -0.72
    hobo
    -0.71
    }));
    -0.67
    atever
    -0.67
    ;">
    -0.67
    {{-
    -0.66
    POSITIVE LOGITS
     NAME
    1.49
     names
    1.47
     name
    1.46
     Name
    1.40
     Names
    1.37
    names
    1.30
    NAME
    1.29
    name
    1.24
    Name
    1.22
    myname
    1.20
    Act Density 0.124%

    No Known Activations