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

    Neuronpedia

    INDEX
    Explanations

    articles with a focus on societal issues and human stories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agents
    -0.81
    Own
    -0.72
    Ord
    -0.69
    ï
    -0.66
     Mysteries
    -0.66
    African
    -0.66
    agree
    -0.66
    Area
    -0.66
    words
    -0.65
    achu
    -0.63
    POSITIVE LOGITS
     handful
    1.29
     consequ
    1.22
     slew
    1.17
     bunch
    1.15
     plethora
    1.14
    cknowled
    1.10
     few
    1.08
     lot
    1.07
     corresponding
    1.05
     penchant
    1.04
    Act Density 0.209%

    No Known Activations