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

    Neuronpedia

    INDEX
    Explanations

    verbs in the future tense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "would" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.64
     Computing
    -0.62
    DAQ
    -0.61
     sqor
    -0.59
    pires
    -0.58
    Playing
    -0.57
    Building
    -0.57
    ception
    -0.56
    Kings
    -0.56
    quickShipAvailable
    -0.56
    POSITIVE LOGITS
     be
    1.04
     never
    0.94
    soon
    0.92
     reopen
    0.90
     eventually
    0.89
     soon
    0.88
    never
    0.88
     continue
    0.88
     leave
    0.87
     gladly
    0.85
    Act Density 0.169%

    No Known Activations