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

    Neuronpedia

    INDEX
    Explanations

    phrases or constructs related to uncertainty and potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.59
    GroupLayout
    -0.48
    <bos>
    -0.44
     diurnal
    -0.43
    Rè
    -0.42
     autón
    -0.41
     acumen
    -0.41
    Xna
    -0.41
     Gemü
    -0.41
     StatefulWidget
    -0.40
    POSITIVE LOGITS
    TemporalType
    0.70
    erol
    0.66
     rétro
    0.63
    utnik
    0.63
     مشين
    0.62
    RegressionTest
    0.60
    Literatuur
    0.59
     محفوظة
    0.59
     slow
    0.58
     too
    0.58
    Act Density 0.812%

    No Known Activations