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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of people

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³³³³
    -0.77
    BACK
    -0.72
     Bound
    -0.68
     Dos
    -0.64
     Glob
    -0.62
    MER
    -0.61
     Situation
    -0.61
    Georg
    -0.61
     Processing
    -0.60
     Due
    -0.60
    POSITIVE LOGITS
    soever
    1.21
    oping
    0.96
    oped
    0.88
    ever
    0.86
     oversaw
    0.86
     accompanies
    0.85
     attended
    0.85
     preceded
    0.85
     specialize
    0.80
     resided
    0.80
    Act Density 0.181%

    No Known Activations