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

    Neuronpedia

    INDEX
    Explanations

    expressions and references related to confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.87
    JvmStatic
    -0.66
    ftagPool
    -0.62
     архивлан
    -0.59
    MessageOf
    -0.59
     FixedUpdate
    -0.55
    routeProvider
    -0.54
     Sosten
    -0.54
     pañ
    -0.53
    loài
    -0.52
    POSITIVE LOGITS
     confidence
    1.51
     Confidence
    1.37
    Confidence
    1.30
     confident
    1.27
    confidence
    1.22
    confident
    1.15
     CONF
    0.98
    CONF
    0.97
    Conf
    0.91
     confid
    0.90
    Act Density 0.084%

    No Known Activations