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

    Neuronpedia

    INDEX
    Explanations

    items related to technology and abbreviations like "MT"

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "MT" or its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hold
    -0.79
    critical
    -0.70
    readable
    -0.69
    minist
    -0.68
    nect
    -0.67
    holes
    -0.66
    fold
    -0.63
    éĹĺ
    -0.63
     Typhoon
    -0.61
    pta
    -0.61
    POSITIVE LOGITS
    ypes
    0.90
    olkien
    0.89
    MT
    0.86
    ullah
    0.84
    ument
    0.84
    ucket
    0.84
    angelo
    0.82
    orsi
    0.79
    TL
    0.78
    ired
    0.78
    Act Density 0.017%

    No Known Activations