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

    Neuronpedia

    INDEX
    Explanations

    signals related to significant numerical values or measurements in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.72
     tartalomajánló
    -0.65
    دانشنامهٔ
    -0.62
     CURIAM
    -0.57
    AndEndTag
    -0.56
     betweenstory
    -0.54
    apimachinery
    -0.50
     dé
    -0.47
     RVA
    -0.46
     kor
    -0.46
    POSITIVE LOGITS
     themſelves
    0.94
     pleaſure
    0.94
     himſelf
    0.92
    ſelves
    0.91
     Jefus
    0.90
     ſmall
    0.90
     myſelf
    0.90
     purpoſe
    0.90
     ſever
    0.85
     Chriftian
    0.85
    Act Density 0.140%

    No Known Activations