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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ((
    -0.41
     Sta
    -0.37
     Es
    -0.37
     w
    -0.37
     зато
    -0.36
     sem
    -0.36
     reply
    -0.35
     --
    -0.34
     i
    -0.34
    ort
    -0.34
    POSITIVE LOGITS
    parsedMessage
    0.79
     saveiro
    0.65
    RegressionTest
    0.64
    bootstrapcdn
    0.63
    ſehen
    0.63
    enderror
    0.62
    InjectAttribute
    0.62
     GenerationType
    0.62
     $_"
    0.61
     Geſch
    0.61
    Act Density 0.182%

    No Known Activations