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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating acceptance, approval, or invitation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of welcome or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.92
    arcity
    -0.76
    ynasty
    -0.75
    aults
    -0.74
    angler
    -0.73
    itect
    -0.72
    negie
    -0.70
    ouf
    -0.70
    enture
    -0.70
    uture
    -0.69
    POSITIVE LOGITS
     additions
    1.01
     newcomers
    0.98
     welcome
    0.87
     aboard
    0.86
     arrivals
    0.85
     visitors
    0.84
    glers
    0.83
     guests
    0.83
     welcomes
    0.80
     welcoming
    0.78
    Act Density 0.031%

    No Known Activations