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

    Neuronpedia

    INDEX
    Explanations

    references to positional indicators such as "above" and "below."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    above and below references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ())))
    -0.42
    findpost
    -0.42
     PyLong
    -0.41
    usepackage
    -0.40
    "]}
    -0.40
    TintMode
    -0.39
    ()))
    -0.38
    )))));
    -0.37
    "]))
    -0.37
    ())),
    -0.37
    POSITIVE LOGITS
     theirs
    0.56
     ň
    0.52
     ours
    0.52
     nôtre
    0.52
     yours
    0.51
     mío
    0.51
     ostavi
    0.51
     desmotivaciones
    0.50
     dotyczą
    0.48
    mær
    0.48
    Act Density 0.028%

    No Known Activations