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

    Neuronpedia

    INDEX
    Explanations

    URLs or web links in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.14
     themſelves
    -1.04
     itſelf
    -1.04
    ſelves
    -0.97
    AndEndTag
    -0.96
     مشين
    -0.91
    ſelf
    -0.88
     himſelf
    -0.85
     whoſe
    -0.83
     Jefus
    -0.81
    POSITIVE LOGITS
    opsida
    0.46
     Bild
    0.44
    يكب
    0.43
     j
    0.43
     Wiggins
    0.42
     églises
    0.41
    وار
    0.41
     gy
    0.41
     propres
    0.41
     petto
    0.40
    Act Density 0.006%

    No Known Activations