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

    Neuronpedia

    INDEX
    Explanations

    words related to imitation or replication

    oai_token-act-pair · gpt-3.5-turbo

    words related to imitation and mimicking behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recall
    -0.66
     Kore
    -0.66
    orage
    -0.65
    IFE
    -0.61
     Cort
    -0.59
    spring
    -0.58
     awakening
    -0.58
     Ads
    -0.57
     Sahara
    -0.57
    orer
    -0.57
    POSITIVE LOGITS
    bley
    1.21
    pered
    1.20
    neys
    1.18
    kered
    1.14
    ped
    1.09
    ply
    1.07
    bered
    1.06
    ney
    1.04
    icked
    1.03
    etr
    1.01
    Act Density 0.116%

    No Known Activations