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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing misfortune or negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    unfortunately

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.54
    BeginContext
    -0.52
     BoxDecoration
    -0.52
    Dossier
    -0.51
    AnchorStyles
    -0.51
    :✨
    -0.51
    новништво
    -0.50
     Dossier
    -0.48
     viewDidLoad
    -0.48
     ModelRenderer
    -0.48
    POSITIVE LOGITS
    unfortunately
    1.14
     unfortunately
    1.13
    Unfortunately
    1.08
     Unfortunately
    1.05
     purtroppo
    0.98
     malheureusement
    0.91
    felizmente
    0.90
     niestety
    0.85
    heureusement
    0.85
    värr
    0.77
    Act Density 0.020%

    No Known Activations