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

    Neuronpedia

    INDEX
    Explanations

    the word "welcome" along with other terms indicating invitation or inclusion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of acceptance or invitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.79
    orius
    -0.76
    oled
    -0.74
    sis
    -0.73
    ynasty
    -0.71
    romy
    -0.71
    aunder
    -0.70
    iph
    -0.70
    arcity
    -0.70
    urgy
    -0.70
    POSITIVE LOGITS
     welcome
    0.95
     additions
    0.91
     aboard
    0.81
     guests
    0.78
     laughter
    0.76
     hosts
    0.75
     welcoming
    0.74
     applause
    0.72
     Guest
    0.71
     flourish
    0.70
    Act Density 0.013%

    No Known Activations