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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or reassurance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty or reassurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.83
    edin
    -0.77
    NAS
    -0.68
    inventoryQuantity
    -0.67
    ————————
    -0.66
    EMS
    -0.63
    regulated
    -0.63
    Bay
    -0.63
    âĵĺ
    -0.63
    Else
    -0.62
    POSITIVE LOGITS
     assurance
    0.94
     assured
    0.92
     shorth
    0.85
     assurances
    0.85
    tale
    0.84
    urances
    0.82
     unden
    0.78
    eers
    0.77
    ly
    0.76
    oire
    0.75
    Act Density 0.013%

    No Known Activations