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

    Neuronpedia

    INDEX
    Explanations

    expressions of receptiveness or positivity towards participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of welcome or invitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arcity
    -0.87
    pard
    -0.80
    aunder
    -0.76
    angler
    -0.75
    oled
    -0.75
    ynasty
    -0.74
    sis
    -0.73
    chem
    -0.70
    ikuman
    -0.70
    iph
    -0.69
    POSITIVE LOGITS
     welcome
    0.92
     additions
    0.90
     newcomers
    0.84
    ãĤī
    0.83
     welcomes
    0.81
    ãĤĬ
    0.80
     aboard
    0.79
     guests
    0.79
    ãĤĮ
    0.78
    glers
    0.77
    Act Density 0.021%

    No Known Activations