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

    Neuronpedia

    INDEX
    Explanations

    expressions related to judgment and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </h6>
    -0.58
     .
    -0.57
    …
    -0.52
    ….
    -0.50
    .…
    -0.48
    （
    -0.47
     …
    -0.46
    </h2>
    -0.46
    「
    -0.46
     «
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    0.62
     يتيمه
    0.61
    RegressionTest
    0.57
     تضيفلها
    0.56
     cív
    0.53
     viata
    0.52
     masina
    0.51
     médec
    0.51
    enumii
    0.49
     wikipagina
    0.49
    Act Density 0.072%

    No Known Activations