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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "actual"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "actual" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.72
    zy
    -0.70
     Beware
    -0.68
     ashore
    -0.66
    lust
    -0.64
    fu
    -0.64
     surely
    -0.63
    limit
    -0.62
    nan
    -0.62
    aday
    -0.61
    POSITIVE LOGITS
    isation
    1.05
    ity
    1.05
    izations
    1.03
    izable
    1.00
    idad
    0.98
    ITY
    0.95
    ities
    0.90
    ignment
    0.90
    isations
    0.89
    ization
    0.88
    Act Density 0.028%

    No Known Activations