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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating knowledge or familiarity, particularly in relation to public perception or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htë
    -0.51
     initialState
    -0.50
    過的
    -0.50
    manjaro
    -0.50
     sockaddr
    -0.49
     normally
    -0.48
    uary
    -0.47
     least
    -0.47
    clearfix
    -0.47
    εν
    -0.47
    POSITIVE LOGITS
    WidgetItem
    0.74
     المعيارى
    0.72
    featureID
    0.68
    存于互联网档案馆
    0.66
    RegressionTest
    0.65
    .*")]
    0.62
    tagHelperRunner
    0.61
     transférez
    0.61
     wikipagina
    0.59
     विश्वसनीयता
    0.59
    Act Density 0.112%

    No Known Activations