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

    Neuronpedia

    INDEX
    Explanations

    specific indicators of significant data patterns or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ьаж
    -0.67
     Vertrauen
    -0.65
     Neub
    -0.62
     propOrder
    -0.60
     للمعارف
    -0.60
    mybatisplus
    -0.60
     perdon
    -0.59
     piş
    -0.58
     sulph
    -0.57
     erstes
    -0.57
    POSITIVE LOGITS
     der
    0.98
    Der
    0.93
     DER
    0.93
     seiner
    0.88
     dieser
    0.87
    ]))
    0.86
     Der
    0.85
     ihrer
    0.83
    ]]]
    0.83
     Ihrer
    0.82
    Act Density 0.029%

    No Known Activations