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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "why" and "why isn't"

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions used in rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urst
    -0.84
    isers
    -0.70
    fter
    -0.65
    iser
    -0.65
    zer
    -0.64
     Intent
    -0.64
     understatement
    -0.64
     Invalid
    -0.62
     Operator
    -0.61
    oric
    -0.61
    POSITIVE LOGITS
    itia
    0.75
    hin
    0.71
     prosecute
    0.69
     assimil
    0.69
    ippi
    0.67
    amus
    0.66
     mention
    0.66
     vacc
    0.63
     nailed
    0.63
     promptly
    0.63
    Act Density 0.197%

    No Known Activations