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

    Neuronpedia

    INDEX
    Explanations

    words related to welcoming or approval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "welcome" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.88
    negie
    -0.79
    agnetic
    -0.74
    arcity
    -0.72
    Downloadha
    -0.71
    enture
    -0.66
     buckle
    -0.66
     choke
    -0.65
    ixtape
    -0.65
    vertisement
    -0.65
    POSITIVE LOGITS
     newcomers
    0.89
    enance
    0.89
     visitors
    0.76
    terson
    0.75
     arrivals
    0.73
    arthed
    0.70
     converts
    0.70
     guests
    0.69
    glers
    0.67
     laughter
    0.67
    Act Density 0.039%

    No Known Activations