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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating responsibility and accountability

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jured
    -0.58
    eport
    -0.54
    rou
    -0.54
    ulum
    -0.52
    iple
    -0.48
     extras
    -0.47
     rooft
    -0.47
    ore
    -0.46
     consolation
    -0.46
     snow
    -0.45
    POSITIVE LOGITS
     namely
    1.23
     whereby
    1.01
     aka
    0.98
     whereas
    0.97
     ie
    0.97
     wherein
    0.92
     viz
    0.91
     thereby
    0.91
     albeit
    0.91
     which
    0.88
    Act Density 0.547%

    No Known Activations