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

    Neuronpedia

    INDEX
    Explanations

    greetings and introductions in text

    oai_token-act-pair · gpt-3.5-turbo

    greetings or introductory phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.75
     excess
    -0.75
    ificantly
    -0.73
     deterior
    -0.72
     divest
    -0.70
     dwind
    -0.69
     destruction
    -0.67
     clauses
    -0.66
     neglect
    -0.65
     fail
    -0.64
    POSITIVE LOGITS
     welcome
    0.83
     hello
    0.83
     Login
    0.80
    Hello
    0.78
     Nir
    0.77
     Welcome
    0.77
     Fellow
    0.77
    Welcome
    0.75
    Morning
    0.75
     traveller
    0.75
    Act Density 0.054%

    No Known Activations