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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning and end of sequences or sections in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.71
     MenuView
    -0.59
     econó
    -0.56
    GEBURTSDATUM
    -0.56
     wireType
    -0.55
     dewasa
    -0.55
    InitVars
    -0.54
     BorderSide
    -0.53
    Портал
    -0.51
     politique
    -0.51
    POSITIVE LOGITS
     scene
    0.83
     moment
    0.78
     room
    0.77
     crowd
    0.70
     startled
    0.67
     others
    0.65
     onlookers
    0.64
     scena
    0.63
     smell
    0.63
     words
    0.62
    Act Density 0.346%

    No Known Activations