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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.75
    RegressionTest
    -0.74
    Autoritní
    -0.61
    :✨
    -0.61
    addCriterion
    -0.57
     TextAppearance
    -0.57
     createContext
    -0.56
    PerformLayout
    -0.55
     <=",
    -0.55
    ึก
    -0.52
    POSITIVE LOGITS
     mustn
    0.79
     shouldn
    0.69
     will
    0.68
     should
    0.67
     may
    0.67
     need
    0.67
     supposed
    0.66
     ought
    0.65
     shall
    0.63
     Shouldn
    0.60
    Act Density 0.392%

    No Known Activations