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

    Neuronpedia

    INDEX
    Explanations

    phrases related to welcoming or being welcomed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "welcome" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arcity
    -0.94
    uyomi
    -0.91
    tein
    -0.84
    iban
    -0.81
    unker
    -0.78
    aults
    -0.75
    aunder
    -0.75
    elling
    -0.73
    agra
    -0.72
    Downloadha
    -0.72
    POSITIVE LOGITS
     newcomers
    1.10
     arrivals
    0.97
     aboard
    0.94
     additions
    0.93
     guests
    0.92
     welcome
    0.91
     arrival
    0.90
     newcomer
    0.89
     surprises
    0.86
     welcomes
    0.86
    Act Density 0.058%

    No Known Activations