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

    Neuronpedia

    INDEX
    Explanations

    reflexive verbs or actions involving self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actualité
    -0.71
    voorbeeld
    -0.70
     Majefty
    -0.67
     Prist
    -0.67
     Yud
    -0.61
    ángulo
    -0.60
     Pois
    -0.60
    Ruff
    -0.59
     flavor
    -0.59
     flavors
    -0.57
    POSITIVE LOGITS
     se
    1.09
     haberse
    0.85
     се
    0.79
    "},
    0.74
     ית
    0.73
    się
    0.72
    ']==
    0.70
     נ
    0.70
     يتم
    0.70
     si
    0.69
    Act Density 0.058%

    No Known Activations