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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating loss or elimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     especially
    -0.43
     refroidissement
    -0.42
     law
    -0.42
     Закон
    -0.41
     lyd
    -0.41
    ("}");
    -0.40
     projects
    -0.40
     Wolken
    -0.39
     TAMBÉM
    -0.39
     pick
    -0.39
    POSITIVE LOGITS
    UserScript
    0.98
    AndEndTag
    0.92
     المعيارى
    0.81
    URLException
    0.80
    findpost
    0.79
    SharedCtor
    0.79
     محفوظة
    0.78
    AddTagHelper
    0.76
    NUMX
    0.76
    ########.
    0.76
    Act Density 0.529%

    No Known Activations