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

    Neuronpedia

    INDEX
    Explanations

    phrases related to structured arguments or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $
    -0.52
    cí
    -0.48
    في
    -0.44
     Vann
    -0.44
    屁
    -0.43
     orígenes
    -0.43
    landes
    -0.43
     âges
    -0.43
     bénéfices
    -0.42
     Tom
    -0.42
    POSITIVE LOGITS
    httphttps
    1.11
    jspx
    1.01
     <<<<<<<<<<<<<<
    1.00
    MemoryWarning
    0.98
     متعلقه
    0.96
    findpost
    0.94
     مشين
    0.91
     חיצוניים
    0.89
    awtextra
    0.89
     Normdatei
    0.88
    Act Density 0.066%

    No Known Activations