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

    Neuronpedia

    INDEX
    Explanations

    terms related to distribution, such as channels, varying distribution, distribution models, and distribution platforms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    astical
    -0.71
    uddin
    -0.67
    glers
    -0.67
    --+
    -0.66
    chest
    -0.65
    ornings
    -0.65
    itude
    -0.64
    inx
    -0.64
    chers
    -0.63
    aired
    -0.62
    POSITIVE LOGITS
     distribution
    0.90
     Distribution
    0.85
    eering
    0.82
     distribut
    0.82
     distributions
    0.82
     Distribut
    0.81
     distribute
    0.77
    ally
    0.75
     channels
    0.73
    itarian
    0.73
    Act Density 6.807%

    No Known Activations