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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "was" followed by other words in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    currently
    -0.72
    icles
    -0.66
    wall
    -0.65
     Current
    -0.64
    veland
    -0.64
     Piercing
    -0.63
    otiation
    -0.61
    uras
    -0.61
     Extend
    -0.61
    rouse
    -0.61
    POSITIVE LOGITS
    hes
    0.99
     instrumental
    0.99
    wolves
    0.93
    wolf
    0.89
     mistaken
    0.89
    hers
    0.81
     intentional
    0.81
     careless
    0.80
     intentionally
    0.79
     negligent
    0.79
    Act Density 0.403%

    No Known Activations