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

    Neuronpedia

    INDEX
    Explanations

    phrases commonly found in online greetings and salutations

    oai_token-act-pair · gpt-3.5-turbo

    greetings and expressions of welcome in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arteries
    -0.75
     destroys
    -0.73
    staking
    -0.71
     crumble
    -0.71
     withstand
    -0.69
     deterior
    -0.68
     shred
    -0.68
     annexation
    -0.67
     destruction
    -0.67
     euth
    -0.66
    POSITIVE LOGITS
    Hello
    0.77
    Introdu
    0.75
    SEE
    0.73
    cape
    0.72
    λ
    0.71
    Hi
    0.70
     Fellow
    0.70
     Password
    0.70
     welcome
    0.70
     dear
    0.69
    Act Density 0.089%

    No Known Activations