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

    Neuronpedia

    INDEX
    Explanations

    modal verbs conveying expectation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing expectations or anticipations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.73
    pite
    -0.63
    grounds
    -0.62
     Eps
    -0.62
    ById
    -0.61
     Wasserman
    -0.61
     Esp
    -0.61
    Wan
    -0.60
    hots
    -0.60
     Huma
    -0.60
    POSITIVE LOGITS
     attach
    0.82
     recreate
    0.81
     sell
    0.79
     hear
    0.77
    eat
    0.77
     capitalize
    0.76
     bring
    0.76
     exceed
    0.76
     reap
    0.75
     get
    0.75
    Act Density 0.186%

    No Known Activations