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

    Neuronpedia

    INDEX
    Explanations

    LaTeX syntax or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -1.03
    HideFlags
    -1.02
     يتيمه
    -0.98
    цездатний
    -0.90
    triangleq
    -0.89
    ensement
    -0.88
     Rajesh
    -0.83
    elang
    -0.82
     Goldberg
    -0.81
    دانشنامهٔ
    -0.81
    POSITIVE LOGITS
    \
    1.38
     \
    1.11
    </tr>
    0.93
    )\
    0.88
    <tbody>
    0.86
    \\\
    0.85
    %\
    0.85
     \\\
    0.85
    ))\
    0.82
     }\
    0.82
    Act Density 0.012%

    No Known Activations