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

    Neuronpedia

    INDEX
    Explanations

    technical and procedural language related to processes and actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    -
    -0.86
     
    -0.76
     up
    -0.69
    <h2>
    -0.69
    /
    -0.69
    t
    -0.68
    1
    -0.66
    \
    -0.66
    ,
    -0.65
    H
    -0.65
    POSITIVE LOGITS
     myſelf
    1.36
    )");
    1.25
     Efq
    1.13
     themſelves
    1.13
    )"),
    1.11
     ſeveral
    1.10
     itſelf
    1.09
    )";
    1.08
     Forumite
    1.07
     $_"
    1.07
    Act Density 6.587%

    No Known Activations