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

    Neuronpedia

    INDEX
    Explanations

    words indicating frequency or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Occasional
    -0.52
    periodic
    -0.52
    holiday
    -0.50
     periodic
    -0.50
    Periodic
    -0.49
     StatefulWidget
    -0.49
    SOUNDBITE
    -0.49
    Poppins
    -0.47
     Periodic
    -0.46
     lig
    -0.46
    POSITIVE LOGITS
     constantly
    1.04
     constamment
    0.78
     constantemente
    0.69
     farm
    0.68
     continually
    0.68
     farming
    0.65
     farms
    0.64
     farmers
    0.63
     farmer
    0.60
     consistently
    0.59
    Act Density 0.108%

    No Known Activations