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

    Neuronpedia

    INDEX
    Explanations

    descriptions of various subjects or topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of describing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oooooooo
    -0.66
    oooo
    -0.61
    ibo
    -0.60
    HT
    -0.60
    lymp
    -0.60
    zar
    -0.60
    azar
    -0.60
    orate
    -0.59
    intend
    -0.59
    oha
    -0.59
    POSITIVE LOGITS
     describing
    3.36
     explaining
    1.85
     referring
    1.78
     specifying
    1.70
     descriptions
    1.64
     describe
    1.62
     describ
    1.59
     outlining
    1.58
     depicting
    1.55
     detailing
    1.54
    Act Density 0.010%

    No Known Activations