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

    Neuronpedia

    INDEX
    Explanations

    academic references and structural formatting in scholarly writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheng
    -0.15
    åı°
    -0.15
    chine
    -0.15
    teri
    -0.15
    bat
    -0.15
    adele
    -0.15
    оваÑĢи
    -0.15
    vir
    -0.15
    uo
    -0.14
    unter
    -0.14
    POSITIVE LOGITS
    æľ¬
    0.35
     this
    0.35
     æľ¬
    0.31
     herein
    0.29
    .this
    0.29
    this
    0.28
     본
    0.27
     THIS
    0.27
     This
    0.26
     here
    0.25
    Act Density 0.188%

    No Known Activations