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

    Neuronpedia

    INDEX
    Explanations

    confirmations or verifications of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirmed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.94
    DragonMagazine
    -0.75
    pmwiki
    -0.75
    neys
    -0.72
    pen
    -0.71
    onew
    -0.70
    mire
    -0.69
    ï¸
    -0.69
    brance
    -0.68
    forums
    -0.68
    POSITIVE LOGITS
    irmation
    0.79
    irms
    0.76
    ations
    0.72
    atory
    0.71
    ariat
    0.70
    ities
    0.70
     receipt
    0.69
     confirms
    0.69
     confirmed
    0.69
     unequivocally
    0.67
    Act Density 0.026%

    No Known Activations