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

    Neuronpedia

    INDEX
    Explanations

    words indicating conclusions or logical inferences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.84
     AssemblyCulture
    -0.81
    ValueStyle
    -0.81
    loài
    -0.74
    новништво
    -0.71
    glEnd
    -0.71
    endphp
    -0.69
     pinulongan
    -0.69
    extAlignment
    -0.68
    SBATCH
    -0.67
    POSITIVE LOGITS
    الدراسه
    0.58
     aange
    0.50
     Met
    0.43
     Madsen
    0.42
    اتي
    0.42
    arar
    0.42
    essive
    0.41
    YV
    0.41
    mittlung
    0.41
     defStyle
    0.41
    Act Density 0.010%

    No Known Activations