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

    Neuronpedia

    INDEX
    Explanations

    references to colored lines and shapes in graphical data representations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.54
     trous
    -0.47
    q
    -0.44
    endpush
    -0.44
    WriteAttribute
    -0.42
     controllare
    -0.42
     missione
    -0.41
     dormitorios
    -0.40
     sond
    -0.40
    ad
    -0.40
    POSITIVE LOGITS
     NUKAT
    0.73
     defaultstate
    0.72
     AssemblyProduct
    0.66
    EDEFAULT
    0.66
    PYX
    0.65
    yntaxException
    0.64
     saites
    0.63
    tawesome
    0.62
    +#+
    0.62
    ########.
    0.61
    Act Density 0.016%

    No Known Activations