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

    Neuronpedia

    INDEX
    Explanations

    repeated segments or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ár
    -1.00
     Lakeside
    -0.87
    GenerationType
    -0.86
     Tul
    -0.86
    findpost
    -0.83
     ddelweddau
    -0.83
    {{/
    -0.81
     curtains
    -0.81
     Hilde
    -0.80
    Tul
    -0.80
    POSITIVE LOGITS
             
    1.54
    いる
    0.96
                         
    0.94
    0.92
    0.89
    0.81
                            
    0.75
    .........
    0.74
                     
    0.73
    🤣🤣
    0.71
    Act Density 0.206%

    No Known Activations