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

    Neuronpedia

    INDEX
    Explanations

    words related to medication and pharmacy

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or patterns related to plural nouns and certain verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISM
    -0.68
     Mecca
    -0.65
    OPLE
    -0.62
    ZZ
    -0.61
    XY
    -0.59
     Yug
    -0.59
    Graphics
    -0.57
    ILY
    -0.57
     Springs
    -0.56
    pty
    -0.56
    POSITIVE LOGITS
    hirt
    1.26
    erve
    1.18
    uits
    1.17
    hips
    1.17
    mith
    1.12
    erver
    1.12
    peed
    1.09
    pace
    1.07
    chwitz
    1.05
    linger
    1.05
    Act Density 0.097%

    No Known Activations