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

    Neuronpedia

    INDEX
    Explanations

    words containing the suffix "-ette"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific character string, particularly "ette"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icultural
    -0.82
     glim
    -0.81
    committee
    -0.80
    ifted
    -0.76
    rush
    -0.76
    arcity
    -0.75
    ifier
    -0.74
    ounding
    -0.74
     undermin
    -0.72
    ifying
    -0.71
    POSITIVE LOGITS
    lla
    0.91
    ette
    0.88
    Mania
    0.85
    brate
    0.82
    vre
    0.81
    brates
    0.81
    ttes
    0.78
    que
    0.78
     Scotia
    0.75
    ptin
    0.74
    Act Density 0.030%

    No Known Activations