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-mini
    New Auto-Interp
    Negative Logits
     Majefty
    -0.92
     للاسماء
    -0.90
     Pries
    -0.87
     Hershey
    -0.86
    mbggenerated
    -0.81
     purpoſe
    -0.80
     Platon
    -0.79
     Cæsar
    -0.79
     Maura
    -0.79
    niająca
    -0.78
    POSITIVE LOGITS
     Se
    1.06
     se
    1.00
    Se
    0.84
     SE
    0.76
     haberse
    0.75
     се
    0.75
     Selig
    0.71
     fe
    0.68
     להת
    0.68
     sa
    0.65
    Act Density 0.007%

    No Known Activations