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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.61
     Asimismo
    -0.57
     Roskov
    -0.55
    TagHelper
    -0.55
     –,
    -0.53
    ſelf
    -0.52
    ագրություններ
    -0.50
     themſelves
    -0.49
    AndEndTag
    -0.48
     uſed
    -0.48
    POSITIVE LOGITS
     soooo
    0.62
     irgend
    0.62
     sooooo
    0.60
    MLLoader
    0.60
    
    0.59
     sooo
    0.59
     REALLY
    0.58
     😁
    0.58
     irgendwie
    0.56
     google
    0.56
    Act Density 0.035%

    No Known Activations