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

    Neuronpedia

    INDEX
    Explanations

    phrases instructing readers to explore or examine something closely

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.61
     speaking
    -0.59
    lnie
    -0.56
     subject
    -0.55
    aung
    -0.54
    Transforms
    -0.53
     criterios
    -0.52
     walking
    -0.52
     Walking
    -0.52
    navbar
    -0.51
    POSITIVE LOGITS
    celotti
    0.82
    look
    0.79
    ✨:
    0.77
     AssemblyCulture
    0.74
     look
    0.70
    看看
    0.65
    MemoryWarning
    0.65
     peek
    0.63
     peep
    0.62
     glimpse
    0.62
    Act Density 0.108%

    No Known Activations