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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases indicating conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.77
     himself
    -0.72
    lled
    -0.68
    lier
    -0.68
     hammered
    -0.67
    emic
    -0.67
     contingency
    -0.66
    iste
    -0.65
     conservatism
    -0.65
     criminal
    -0.65
    POSITIVE LOGITS
     Especially
    1.12
     Whether
    1.04
     Please
    1.02
     Specifically
    1.01
     Depending
    1.01
     Besides
    0.99
     Including
    0.98
     Learn
    0.97
     Includes
    0.97
     Unfortunately
    0.96
    Act Density 0.503%

    No Known Activations