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

    Neuronpedia

    INDEX
    Explanations

    locations and events mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    the root of the word "eng" within various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Negative Logits
    IFIED
    -1.07
    senal
    -0.96
    ESA
    -0.89
    cale
    -0.89
     ESA
    -0.88
    istically
    -0.86
    pmwiki
    -0.85
    mia
    -0.83
    Ô
    -0.83
    \/\/
    -0.83
    POSITIVE LOGITS
    lishes
    1.65
    ravings
    1.42
    raved
    1.38
    iment
    1.31
    rish
    1.25
    iments
    1.24
    edin
    1.17
    eng
    1.16
    oing
    1.12
    irth
    1.11
    Act Density 0.640%

    No Known Activations