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

    Neuronpedia

    INDEX
    Explanations

    the word "usually" indicating habitual or typical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.83
    ViewFeatures
    -0.81
     contd
    -0.76
    )))));
    -0.73
     optimally
    -0.70
    TagHelper
    -0.66
    ListItemIcon
    -0.66
     plenamente
    -0.65
     fortemente
    -0.64
    }_{+
    -0.64
    POSITIVE LOGITS
     usually
    2.13
     usual
    2.02
     Usually
    1.98
    Usually
    1.94
    usual
    1.85
    usually
    1.81
     Usual
    1.68
    Usual
    1.67
     zwykle
    1.32
     обычно
    1.32
    Act Density 0.111%

    No Known Activations