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

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming or code-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    classNames
    -0.77
    grá
    -0.77
    mlen
    -0.74
    庄
    -0.74
    𝐞
    -0.73
    𝐥
    -0.72
    𝐮
    -0.70
    ActionBar
    -0.70
     Thra
    -0.70
     n
    -0.69
    POSITIVE LOGITS
     }}$,
    1.27
    \}$,
    1.26
    ])));
    1.21
    )}$,
    1.18
     }}"></
    1.17
    }}$,
    1.14
    })));
    1.14
     }}$.
    1.13
    ]$.
    1.13
    })$,
    1.12
    Act Density 0.204%

    No Known Activations