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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sauvages
    -0.62
     NSCoder
    -0.62
     incontr
    -0.59
     ouvriers
    -0.59
    naje
    -0.58
     démocr
    -0.56
     mijne
    -0.56
     travailleurs
    -0.55
     activado
    -0.55
     crainte
    -0.54
    POSITIVE LOGITS
    itself
    0.79
     ourselves
    0.76
     itself
    0.75
     herself
    0.73
     himself
    0.69
    himself
    0.69
     oneself
    0.68
    ViewImports
    0.67
    themselves
    0.67
     themselves
    0.65
    Act Density 0.150%

    No Known Activations