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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving derivatives and variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Freitas
    -0.86
    i
    -0.84
    y
    -0.82
    ExecuteReader
    -0.81
     Gente
    -0.79
     creases
    -0.78
     degeneracy
    -0.76
    DotNetBar
    -0.70
    ा
    -0.69
    ي
    -0.69
    POSITIVE LOGITS
    tsd
    0.82
     Gerd
    0.81
    maked
    0.78
    thd
    0.76
    ghed
    0.73
    vartheta
    0.73
     Wied
    0.72
    d
    0.72
     d
    0.71
     endforeach
    0.71
    Act Density 0.208%

    No Known Activations