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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tiz
    -0.85
     Lur
    -0.80
     Bue
    -0.76
    GEBURTSDATUM
    -0.75
     Schen
    -0.74
     Pitman
    -0.73
     TRI
    -0.72
     deacon
    -0.72
     Garrick
    -0.71
    ectady
    -0.70
    POSITIVE LOGITS
    selves
    1.41
    herself
    1.29
    Yourself
    1.29
    myself
    1.26
     Yourself
    1.25
     herself
    1.23
     Himself
    1.23
    Myself
    1.22
     himself
    1.21
     myself
    1.17
    Act Density 0.054%

    No Known Activations