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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal roles and identity dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.84
     AssemblyCulture
    -0.72
     itſelf
    -0.67
    elemField
    -0.65
    AddTagHelper
    -0.64
    løs
    -0.63
     الحره
    -0.61
     للاسماء
    -0.61
    Rè
    -0.59
    yntaxException
    -0.59
    POSITIVE LOGITS
     themselves
    0.80
     who
    0.77
     whom
    0.73
     kteří
    0.68
     którzy
    0.68
     quienes
    0.64
     ktorí
    0.63
    KEYCODE
    0.60
     الذين
    0.60
     were
    0.58
    Act Density 0.744%

    No Known Activations