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

    Neuronpedia

    INDEX
    Explanations

    expressions starting with "Let me tell you" or equivalent phrases

    oai_token-act-pair · gpt-3.5-turbo

    conversational or explanatory phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     upkeep
    -0.67
     remod
    -0.62
    ibles
    -0.60
    UTC
    -0.58
    ourses
    -0.56
     spawns
    -0.56
    Pg
    -0.56
     hemor
    -0.55
     maintenance
    -0.55
    Offline
    -0.54
    POSITIVE LOGITS
     myself
    0.82
    odox
    0.73
    resso
    0.70
     iT
    0.70
    ayson
    0.66
     understatement
    0.66
     caveats
    0.65
    entious
    0.64
     caveat
    0.63
     Conspiracy
    0.62
    Act Density 0.750%

    No Known Activations