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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the beginning of a story or anecdote

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.64
     respons
    -0.64
     thereafter
    -0.62
     thereof
    -0.57
     accordingly
    -0.56
    âĸº
    -0.56
     outwe
    -0.56
     thereto
    -0.56
     moreover
    -0.55
    ?,
    -0.53
    POSITIVE LOGITS
    reetings
    0.75
    anmar
    0.65
     SHARES
    0.62
    zbollah
    0.60
    stanbul
    0.59
    avascript
    0.59
     Vegan
    0.58
     Updated
    0.58
     Introduction
    0.57
    oÄŁan
    0.57
    Act Density 0.379%

    No Known Activations