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

    Neuronpedia

    INDEX
    Explanations

    language related to giving reassurance or making promises

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize assurance or guarantees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entry
    -0.87
    pmwiki
    -0.77
    âĵĺ
    -0.70
    sites
    -0.68
    NAS
    -0.67
    sung
    -0.65
    regulated
    -0.64
    nature
    -0.64
    inn
    -0.64
    sle
    -0.63
    POSITIVE LOGITS
     assurance
    1.13
    urances
    1.01
     assured
    0.97
     assurances
    0.97
     assure
    0.95
     reassure
    0.87
     assures
    0.87
     reassured
    0.84
    ĸļ
    0.80
    ariat
    0.80
    Act Density 0.004%

    No Known Activations