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

    Neuronpedia

    INDEX
    Explanations

    personal greetings and introductions

    oai_token-act-pair · gpt-3.5-turbo

    greeting phrases and expressions of welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     euth
    -0.69
     playbook
    -0.67
     shred
    -0.65
     prev
    -0.65
     dehuman
    -0.65
     til
    -0.64
     deterior
    -0.64
     trophies
    -0.64
     maneu
    -0.63
     withstand
    -0.63
    POSITIVE LOGITS
     hello
    0.86
    asus
    0.85
    Hello
    0.84
    dy
    0.81
    cape
    0.77
    reetings
    0.75
    Hi
    0.74
     congratulations
    0.74
    Introdu
    0.74
    λ
    0.72
    Act Density 0.105%

    No Known Activations