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

    Neuronpedia

    INDEX
    Explanations

    phrases related to certain types or categories of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe types or categories of situations or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /,
    -0.64
     VIDEOS
    -0.62
    heid
    -0.59
    rawdownloadcloneembedreportprint
    -0.57
    ilaterally
    -0.57
    çīĪ
    -0.56
    aimon
    -0.56
     Bars
    -0.56
    ORY
    -0.55
    agnar
    -0.55
    POSITIVE LOGITS
    liest
    0.97
    etting
    0.87
    lihood
    0.83
    est
    0.77
    linger
    0.73
     of
    0.68
    hest
    0.68
    ridges
    0.67
    hearted
    0.67
    hots
    0.66
    Act Density 0.033%

    No Known Activations